generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

OpenCV reference manual (C++ part only for now) is now produced directly from RST, not from TeX.

Browse Source
This commit is contained in:
Vadim Pisarevsky 2011-02-22 20:43:26 +00:00
parent 32a2fde8ac
commit 371aa08006
65 changed files with 41233 additions and 98 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
CMakeLists.txt
View File

@ -554,8 +554,20 @@ if(BUILD_NEW_PYTHON_SUPPORT)
else()
set(PYTHON_USE_NUMPY 0)
endif()
execute_process(COMMAND ${PYTHON_EXECUTABLE} -c "import sphinx; print sphinx.__version__"
RESULT_VARIABLE SPHINX_PROCESS
OUTPUT_VARIABLE SPHINX_VERSION
OUTPUT_STRIP_TRAILING_WHITESPACE)
set(HAVE_SPHINX 0)
if(SPHINX_PROCESS EQUAL 0)
find_program(SPHINX_BUILD sphinx-build)
if(SPHINX_BUILD)
set(HAVE_SPHINX 1)
message(STATUS " Found Sphinx ${SPHINX_VERSION}: ${SPHINX_BUILD}")
endif()
endif()
endif()
#YV
@ -778,7 +790,7 @@ set(HAVE_OPENNI FALSE)
set(HAVE_OPENNI_PRIME_SENSOR_MODULE FALSE)
if(WITH_OPENNI)
include(OpenCVFindOpenNI.cmake)
include(OpenCVFindOpenNI.cmake)
endif()
############################## Eigen2 ##############################
@ -798,40 +810,40 @@ endif()
################## Extra HighGUI libs on Windows ###################
if(WIN32)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} comctl32 gdi32 ole32)
if (MSVC)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} vfw32)
endif()
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} comctl32 gdi32 ole32)
if (MSVC)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} vfw32)
endif()
if(MINGW)
if(MINGW64)
if(MINGW)
if(MINGW64)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} msvfw32 avifil32 avicap32 winmm)
if(HAVE_VIDEOINPUT)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} videoInput64 strmiids)
endif()
else()
if(HAVE_VIDEOINPUT)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} videoInput64 strmiids)
endif()
else()
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} vfw32 winmm)
if(HAVE_VIDEOINPUT)
if(HAVE_VIDEOINPUT)
set(HIGHGUI_LIBRARIES ${HIGHGUI_LIBRARIES} videoInput strmiids)
endif()
endif()
endif()
endif()
endif()
endif()
################## LATEX ##################
set(BUILD_LATEX_DOCS OFF CACHE BOOL "Build LaTeX OpenCV Documentation")
################## Reference Manual ##################
set(BUILD_REFMAN ON CACHE BOOL "Build OpenCV Reference Manual")
################### DOXYGEN ###############
find_package(Doxygen)
if(DOXYGEN_FOUND)
set(BUILD_DOXYGEN_DOCS ON CACHE BOOL "Generate HTML docs using Doxygen")
endif()
#find_package(Doxygen)
#
#if(DOXYGEN_FOUND)
# set(BUILD_DOXYGEN_DOCS ON CACHE BOOL "Generate HTML docs using Doxygen")
#endif()
# ----------------------------------------------------------------------------
@ -1246,9 +1258,9 @@ if(BUILD_PACKAGE)
install(DIRECTORY data samples DESTINATION "." COMPONENT main PATTERN ".svn" EXCLUDE)
install(DIRECTORY 3rdparty android modules tests DESTINATION "." COMPONENT src PATTERN ".svn" EXCLUDE)
install(DIRECTORY doc/ DESTINATION doc COMPONENT src FILES_MATCHING PATTERN "*.tex")
install(DIRECTORY doc/pics DESTINATION doc COMPONENT src PATTERN ".svn" EXCLUDE)
install(DIRECTORY doc/latex2sphinx DESTINATION doc COMPONENT src PATTERN ".svn" EXCLUDE)
#install(DIRECTORY doc/ DESTINATION doc COMPONENT src FILES_MATCHING PATTERN "*.tex")
#install(DIRECTORY doc/pics DESTINATION doc COMPONENT src PATTERN ".svn" EXCLUDE)
#install(DIRECTORY doc/latex2sphinx DESTINATION doc COMPONENT src PATTERN ".svn" EXCLUDE)
endif()
endif()
@ -1260,7 +1272,7 @@ endif()
add_subdirectory(include)
add_subdirectory(modules)
if(BUILD_LATEX_DOCS)
if(BUILD_REFMAN)
include(OpenCVFindLATEX.cmake REQUIRED)
if(PDFLATEX_COMPILER)
@ -1268,7 +1280,7 @@ if(BUILD_LATEX_DOCS)
endif()
endif()
add_subdirectory(doc)
add_subdirectory(docroot)
add_subdirectory(data)
if(BUILD_EXAMPLES OR INSTALL_PYTHON_EXAMPLES)
@ -1289,16 +1301,16 @@ add_subdirectory(3rdparty)
message(STATUS "")
message(STATUS "General configuration for opencv ${OPENCV_VERSION} =====================================")
message(STATUS "")
message(STATUS " Built as dynamic libs?: ${BUILD_SHARED_LIBS}")
message(STATUS " Compiler: ${CMAKE_COMPILER}")
message(STATUS " C++ flags (Release): ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_RELEASE}")
message(STATUS " C++ flags (Debug): ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_DEBUG}")
message(STATUS " Built as dynamic libs?: ${BUILD_SHARED_LIBS}")
message(STATUS " Compiler: ${CMAKE_COMPILER}")
message(STATUS " C++ flags (Release): ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_RELEASE}")
message(STATUS " C++ flags (Debug): ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_DEBUG}")
if(WIN32)
message(STATUS " Linker flags (Release): ${CMAKE_EXE_LINKER_FLAGS} ${CMAKE_EXE_LINKER_FLAGS_RELEASE}")
message(STATUS " Linker flags (Debug): ${CMAKE_EXE_LINKER_FLAGS} ${CMAKE_EXE_LINKER_FLAGS_DEBUG}")
message(STATUS " Linker flags (Release): ${CMAKE_EXE_LINKER_FLAGS} ${CMAKE_EXE_LINKER_FLAGS_RELEASE}")
message(STATUS " Linker flags (Debug): ${CMAKE_EXE_LINKER_FLAGS} ${CMAKE_EXE_LINKER_FLAGS_DEBUG}")
else()
message(STATUS " Linker flags (Release): ${CMAKE_SHARED_LINKER_FLAGS} ${CMAKE_SHARED_LINKER_FLAGS_RELEASE}")
message(STATUS " Linker flags (Debug): ${CMAKE_SHARED_LINKER_FLAGS} ${CMAKE_SHARED_LINKER_FLAGS_DEBUG}")
message(STATUS " Linker flags (Release): ${CMAKE_SHARED_LINKER_FLAGS} ${CMAKE_SHARED_LINKER_FLAGS_RELEASE}")
message(STATUS " Linker flags (Debug): ${CMAKE_SHARED_LINKER_FLAGS} ${CMAKE_SHARED_LINKER_FLAGS_DEBUG}")
endif()
#YV
@ -1306,21 +1318,21 @@ message(STATUS "")
message(STATUS " GUI: ")
if (HAVE_QT)
message(STATUS " QT 4.x: ${HAVE_QT}")
message(STATUS " QT OpenGL support: ${HAVE_QT_OPENGL}")
message(STATUS " QT 4.x: ${HAVE_QT}")
message(STATUS " QT OpenGL support: ${HAVE_QT_OPENGL}")
else()
if(WIN32)
message(STATUS " Win32 UI: 1")
message(STATUS " Win32 UI: YES")
else()
if(APPLE)
if(WITH_CARBON)
message(STATUS " Carbon: 1")
message(STATUS " Carbon: YES")
else()
message(STATUS " Cocoa: 1")
message(STATUS " Cocoa: YES")
endif()
else()
message(STATUS " GTK+ 2.x: ${HAVE_GTK}")
message(STATUS " GThread: ${HAVE_GTHREAD}")
message(STATUS " GTK+ 2.x: ${HAVE_GTK}")
message(STATUS " GThread: ${HAVE_GTHREAD}")
endif()
endif()
endif()
@ -1328,69 +1340,69 @@ endif()
message(STATUS "")
message(STATUS " Image I/O: ")
if(NOT WITH_JPEG OR JPEG_FOUND)
message(STATUS " JPEG: ${JPEG_FOUND}")
message(STATUS " JPEG: ${JPEG_FOUND}")
else()
message(STATUS " JPEG: build")
message(STATUS " JPEG: build")
endif()
if(NOT WITH_PNG OR PNG_FOUND)
message(STATUS " PNG: ${PNG_FOUND}")
message(STATUS " PNG: ${PNG_FOUND}")
else()
message(STATUS " PNG: build")
message(STATUS " PNG: build")
endif()
if(NOT WITH_TIFF OR TIFF_FOUND)
message(STATUS " TIFF: ${TIFF_FOUND}")
message(STATUS " TIFF: ${TIFF_FOUND}")
else()
message(STATUS " TIFF: build")
message(STATUS " TIFF: build")
endif()
if(NOT WITH_JASPER OR JASPER_FOUND)
message(STATUS " JPEG 2000: ${JASPER_FOUND}")
message(STATUS " JPEG 2000: ${JASPER_FOUND}")
else()
message(STATUS " JPEG 2000: build")
message(STATUS " JPEG 2000: build")
endif()
if(WITH_OPENEXR AND OPENEXR_FOUND)
message(STATUS " OpenEXR: YES")
message(STATUS " OpenEXR: YES")
else()
message(STATUS " OpenEXR: NO")
message(STATUS " OpenEXR: NO")
endif()
if(NOT HAVE_OPENNI OR HAVE_OPENNI_PRIME_SENSOR_MODULE)
message(STATUS " OpenNI: ${HAVE_OPENNI}")
message(STATUS " OpenNI: ${HAVE_OPENNI}")
else()
message(STATUS " OpenNI: ${HAVE_OPENNI} (WARNING: PrimeSensor Modules for OpenNI are not installed (not found in OPENNI_PRIME_SENSOR_MODULE_BIN_DIR).)")
message(STATUS " OpenNI: ${HAVE_OPENNI} (WARNING: PrimeSensor Modules for OpenNI are not installed (not found in OPENNI_PRIME_SENSOR_MODULE_BIN_DIR).)")
endif()
if(UNIX AND NOT APPLE)
message(STATUS "")
message(STATUS " Video I/O: ")
message(STATUS " DC1394 1.x: ${HAVE_DC1394}")
message(STATUS " DC1394 2.x: ${HAVE_DC1394_2}")
message(STATUS " FFMPEG: ${HAVE_FFMPEG}")
message(STATUS " codec: ${HAVE_FFMPEG_CODEC}")
message(STATUS " format: ${HAVE_FFMPEG_FORMAT}")
message(STATUS " util: ${HAVE_FFMPEG_UTIL}")
message(STATUS " swscale: ${HAVE_FFMPEG_SWSCALE}")
message(STATUS " gentoo-style: ${HAVE_GENTOO_FFMPEG}")
message(STATUS " GStreamer: ${HAVE_GSTREAMER}")
message(STATUS " UniCap: ${HAVE_UNICAP}")
message(STATUS " PvAPI: ${HAVE_PVAPI}")
message(STATUS " DC1394 1.x: ${HAVE_DC1394}")
message(STATUS " DC1394 2.x: ${HAVE_DC1394_2}")
message(STATUS " FFMPEG: ${HAVE_FFMPEG}")
message(STATUS " codec: ${HAVE_FFMPEG_CODEC}")
message(STATUS " format: ${HAVE_FFMPEG_FORMAT}")
message(STATUS " util: ${HAVE_FFMPEG_UTIL}")
message(STATUS " swscale: ${HAVE_FFMPEG_SWSCALE}")
message(STATUS " gentoo-style: ${HAVE_GENTOO_FFMPEG}")
message(STATUS " GStreamer: ${HAVE_GSTREAMER}")
message(STATUS " UniCap: ${HAVE_UNICAP}")
message(STATUS " PvAPI: ${HAVE_PVAPI}")
if(HAVE_LIBV4L)
message(STATUS " V4L/V4L2: Using libv4l")
message(STATUS " V4L/V4L2: Using libv4l")
else()
message(STATUS " V4L/V4L2: ${HAVE_CAMV4L}/${HAVE_CAMV4L2}")
message(STATUS " V4L/V4L2: ${HAVE_CAMV4L}/${HAVE_CAMV4L2}")
endif()
message(STATUS " Xine: ${HAVE_XINE}")
message(STATUS " Xine: ${HAVE_XINE}")
endif() #if(UNIX AND NOT APPLE)
if(APPLE)
message(STATUS "")
if(WITH_QUICKTIME)
message(STATUS " Video I/O: QuickTime")
message(STATUS " Video I/O: QuickTime")
else()
message(STATUS " Video I/O: QTKit")
message(STATUS " Video I/O: QTKit")
endif()
endif()
@ -1398,68 +1410,68 @@ if(WIN32)
message(STATUS "")
message(STATUS " Video I/O: ")
if(HAVE_VIDEOINPUT)
message(STATUS " VideoInput: 1")
message(STATUS " VideoInput: YES")
else()
message(STATUS " VideoInput: 0")
message(STATUS " VideoInput: NO")
endif()
endif()
message(STATUS "")
message(STATUS " Interfaces: ")
message(STATUS " Python: ${BUILD_NEW_PYTHON_SUPPORT}")
message(STATUS " Python interpreter: ${PYTHON_EXECUTABLE}")
message(STATUS " Python: ${BUILD_NEW_PYTHON_SUPPORT}")
message(STATUS " Python interpreter: ${PYTHON_EXECUTABLE}")
if (PYTHON_USE_NUMPY)
message(STATUS " Python numpy: YES")
message(STATUS " Python numpy: YES")
else()
message(STATUS " Python numpy: NO (Python interface will not cover OpenCV 2.x API)")
message(STATUS " Python numpy: NO (Python interface will not cover OpenCV 2.x API)")
endif()
if(WITH_IPP AND IPP_FOUND)
message(STATUS " Use IPP: ${IPP_LATEST_VERSION_STR} [${IPP_LATEST_VERSION_MAJOR}.${IPP_LATEST_VERSION_MINOR}.${IPP_LATEST_VERSION_BUILD}]")
message(STATUS " at: ${IPP_ROOT_DIR}")
message(STATUS " Use IPP: ${IPP_LATEST_VERSION_STR} [${IPP_LATEST_VERSION_MAJOR}.${IPP_LATEST_VERSION_MINOR}.${IPP_LATEST_VERSION_BUILD}]")
message(STATUS " at: ${IPP_ROOT_DIR}")
elseif(WITH_IPP AND NOT IPP_FOUND)
message(STATUS " Use IPP: IPP not found")
message(STATUS " Use IPP: IPP not found")
else()
message(STATUS " Use IPP: NO")
message(STATUS " Use IPP: NO")
endif()
if(HAVE_TBB)
message(STATUS " Use TBB: YES")
message(STATUS " Use TBB: YES")
else()
message(STATUS " Use TBB: NO")
message(STATUS " Use TBB: NO")
endif()
if (HAVE_CUDA)
message(STATUS " Use Cuda: YES")
message(STATUS " Use Cuda: YES")
else()
message(STATUS " Use Cuda: NO")
message(STATUS " Use Cuda: NO")
endif()
if(HAVE_EIGEN2)
message(STATUS " Use Eigen2: YES")
message(STATUS " Use Eigen2: YES")
else()
message(STATUS " Use Eigen2: NO")
message(STATUS " Use Eigen2: NO")
endif()
message(STATUS "")
message(STATUS " Documentation: ")
if(BUILD_LATEX_DOCS AND PDFLATEX_COMPILER)
message(STATUS " Build PDF YES")
if(BUILD_REFMAN AND PDFLATEX_COMPILER AND HAVE_SPHINX)
message(STATUS " Build Reference Manual: YES")
else()
message(STATUS " Build PDF NO")
message(STATUS " Build Reference Manual: NO")
endif()
if(BUILD_DOXYGEN_DOCS AND DOXYGEN_FOUND)
message(STATUS " Doxygen HTMLs YES")
else()
message(STATUS " Doxygen HTMLs NO")
endif()
#if(BUILD_DOXYGEN_DOCS AND DOXYGEN_FOUND)
#message(STATUS " Doxygen HTMLs YES")
#else()
#message(STATUS " Doxygen HTMLs NO")
#endif()
message(STATUS "")
message(STATUS " Install path: ${CMAKE_INSTALL_PREFIX}")
message(STATUS " Install path: ${CMAKE_INSTALL_PREFIX}")
message(STATUS "")
message(STATUS " cvconfig.h is in: ${OPENCV_CONFIG_FILE_INCLUDE_DIR}")
message(STATUS " cvconfig.h is in: ${OPENCV_CONFIG_FILE_INCLUDE_DIR}")
message(STATUS "-----------------------------------------------------------------")
message(STATUS "")

19
docroot/CMakeLists.txt Normal file
View File

@ -0,0 +1,19 @@
if(BUILD_REFMAN AND PDFLATEX_COMPILER AND HAVE_SPHINX)
project(opencv_refman)
file(GLOB_RECURSE FILES_PICT ../modules/*.png ../modules/*.jpg)
file(GLOB_RECURSE FILES_RST *.rst ../modules/*.rst)
add_custom_target(refman ${SPHINX_BUILD} -b latex -c ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_SOURCE_DIR}/../modules .
COMMAND ${CMAKE_COMMAND} -E copy_directory ${CMAKE_SOURCE_DIR}/doc/pics ${CMAKE_CURRENT_BINARY_DIR}/pics
COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_SOURCE_DIR}/doc/latex2sphinx/mymath.sty ${CMAKE_CURRENT_BINARY_DIR}
COMMAND ${PDFLATEX_COMPILER} opencv
COMMAND ${PDFLATEX_COMPILER} opencv
DEPENDS conf.py ${FILES_RST} ${FILES_PICT}
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
COMMENT "Generating the Reference Manual")
install(FILES ${CURRENT_BINARY_DIR}/opencv.pdf DESTINATION "${OPENCV_DOC_INSTALL_PATH}" COMPONENT main)
endif()

220
docroot/conf.py Normal file
View File

@ -0,0 +1,220 @@
# -*- coding: utf-8 -*-
#
# opencvstd documentation build configuration file, created by
# sphinx-quickstart on Mon Feb 14 00:30:43 2011.
#
# This file is execfile()d with the current directory set to its containing dir.
#
# Note that not all possible configuration values are present in this
# autogenerated file.
#
# All configuration values have a default; values that are commented out
# serve to show the default.
import sys, os
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#sys.path.insert(0, os.path.abspath('.'))
# -- General configuration -----------------------------------------------------
# If your documentation needs a minimal Sphinx version, state it here.
#needs_sphinx = '1.0'
# Add any Sphinx extension module names here, as strings. They can be extensions
# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
extensions = ['sphinx.ext.pngmath', 'sphinx.ext.ifconfig', 'sphinx.ext.todo']
doctest_test_doctest_blocks = 'block'
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# The suffix of source filenames.
source_suffix = '.rst'
# The encoding of source files.
#source_encoding = 'utf-8-sig'
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = u'opencvrefman'
copyright = u'2011, opencv dev team'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
version = '2.3'
# The full version, including alpha/beta/rc tags.
release = '2.3'
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
#language = None
# There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used:
#today = ''
# Else, today_fmt is used as the format for a strftime call.
#today_fmt = '%B %d, %Y'
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
exclude_patterns = []
# The reST default role (used for this markup: `text`) to use for all documents.
#default_role = None
# If true, '()' will be appended to :func: etc. cross-reference text.
#add_function_parentheses = True
# If true, the current module name will be prepended to all description
# unit titles (such as .. function::).
#add_module_names = True
# If true, sectionauthor and moduleauthor directives will be shown in the
# output. They are ignored by default.
#show_authors = False
# The name of the Pygments (syntax highlighting) style to use.
pygments_style = 'sphinx'
# A list of ignored prefixes for module index sorting.
#modindex_common_prefix = []
todo_include_todos=True
# -- Options for HTML output ---------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
html_theme = 'default'
# Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the
# documentation.
#html_theme_options = {}
# Add any paths that contain custom themes here, relative to this directory.
#html_theme_path = []
# The name for this set of Sphinx documents. If None, it defaults to
# "<project> v<release> documentation".
#html_title = None
# A shorter title for the navigation bar. Default is the same as html_title.
#html_short_title = None
# The name of an image file (relative to this directory) to place at the top
# of the sidebar.
#html_logo = None
# The name of an image file (within the static path) to use as favicon of the
# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
# pixels large.
#html_favicon = None
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static']
# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
# using the given strftime format.
#html_last_updated_fmt = '%b %d, %Y'
# If true, SmartyPants will be used to convert quotes and dashes to
# typographically correct entities.
#html_use_smartypants = True
# Custom sidebar templates, maps document names to template names.
#html_sidebars = {}
# Additional templates that should be rendered to pages, maps page names to
# template names.
#html_additional_pages = {}
# If false, no module index is generated.
#html_domain_indices = True
# If false, no index is generated.
#html_use_index = True
# If true, the index is split into individual pages for each letter.
#html_split_index = False
# If true, links to the reST sources are added to the pages.
#html_show_sourcelink = True
# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
#html_show_sphinx = True
# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
#html_show_copyright = True
# If true, an OpenSearch description file will be output, and all pages will
# contain a <link> tag referring to it. The value of this option must be the
# base URL from which the finished HTML is served.
#html_use_opensearch = ''
# This is the file name suffix for HTML files (e.g. ".xhtml").
#html_file_suffix = None
# Output file base name for HTML help builder.
htmlhelp_basename = 'opencv'
# -- Options for LaTeX output --------------------------------------------------
# The paper size ('letter' or 'a4').
#latex_paper_size = 'letter'
# The font size ('10pt', '11pt' or '12pt').
#latex_font_size = '10pt'
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title, author, documentclass [howto/manual]).
latex_documents = [
('index', 'opencv.tex', u'The OpenCV Reference Manual',
u'', 'manual'),
]
latex_elements = {'preamble': '\usepackage{mymath}\usepackage{amssymb}\usepackage{amsmath}\usepackage{bbm}'}
# The name of an image file (relative to this directory) to place at the top of
# the title page.
#latex_logo = None
# For "manual" documents, if this is true, then toplevel headings are parts,
# not chapters.
#latex_use_parts = False
# If true, show page references after internal links.
#latex_show_pagerefs = False
# If true, show URL addresses after external links.
#latex_show_urls = False
# Additional stuff for the LaTeX preamble.
#latex_preamble = ''
# Documents to append as an appendix to all manuals.
#latex_appendices = []
# If false, no module index is generated.
#latex_domain_indices = True
# -- Options for manual page output --------------------------------------------
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
('index', 'opencv', u'The OpenCV Reference Manual',
[u'opencv-dev@itseez.com'], 1)
]

9
modules/calib3d/doc/calib3d.rst Normal file
View File

@ -0,0 +1,9 @@
****************************************
Camera Calibration and 3D Reconstruction
****************************************
.. toctree::
:maxdepth: 2
camera_calibration_and_3d_reconstruction

2413
modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst Normal file
View File

File diff suppressed because it is too large Load Diff

4533
modules/core/doc/basic_structures.rst Normal file
View File

File diff suppressed because it is too large Load Diff

138
modules/core/doc/clustering.rst Normal file
View File

@ -0,0 +1,138 @@
Clustering
==========
.. highlight:: cpp
.. index:: kmeans
cv::kmeans
----------
`id=0.0672046481842 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/kmeans>`__
.. cfunction:: double kmeans( const Mat\& samples, int clusterCount, Mat\& labels, TermCriteria termcrit, int attempts, int flags, Mat* centers )
Finds the centers of clusters and groups the input samples around the clusters.
:param samples: Floating-point matrix of input samples, one row per sample
:param clusterCount: The number of clusters to split the set by
:param labels: The input/output integer array that will store the cluster indices for every sample
:param termcrit: Specifies maximum number of iterations and/or accuracy (distance the centers can move by between subsequent iterations)
:param attempts: How many times the algorithm is executed using different initial labelings. The algorithm returns the labels that yield the best compactness (see the last function parameter)
:param flags: It can take the following values:
* **KMEANS_RANDOM_CENTERS** Random initial centers are selected in each attempt
* **KMEANS_PP_CENTERS** Use kmeans++ center initialization by Arthur and Vassilvitskii
* **KMEANS_USE_INITIAL_LABELS** During the first (and possibly the only) attempt, the
function uses the user-supplied labels instaed of computing them from the initial centers. For the second and further attempts, the function will use the random or semi-random centers (use one of ``KMEANS_*_CENTERS`` flag to specify the exact method)
:param centers: The output matrix of the cluster centers, one row per each cluster center
The function
``kmeans``
implements a k-means algorithm that finds the
centers of
``clusterCount``
clusters and groups the input samples
around the clusters. On output,
:math:`\texttt{labels}_i`
contains a 0-based cluster index for
the sample stored in the
:math:`i^{th}`
row of the
``samples``
matrix.
The function returns the compactness measure, which is computed as
.. math::
\sum _i \| \texttt{samples} _i - \texttt{centers} _{ \texttt{labels} _i} \| ^2
after every attempt; the best (minimum) value is chosen and the
corresponding labels and the compactness value are returned by the function.
Basically, the user can use only the core of the function, set the number of
attempts to 1, initialize labels each time using some custom algorithm and pass them with
(
``flags``
=
``KMEANS_USE_INITIAL_LABELS``
) flag, and then choose the best (most-compact) clustering.
.. index:: partition
cv::partition
-------------
`id=0.0923567235062 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/partition>`__
.. cfunction:: template<typename _Tp, class _EqPredicate> int
.. cfunction:: partition( const vector<_Tp>\& vec, vector<int>\& labels, _EqPredicate predicate=_EqPredicate())
Splits an element set into equivalency classes.
:param vec: The set of elements stored as a vector
:param labels: The output vector of labels; will contain as many elements as ``vec`` . Each label ``labels[i]`` is 0-based cluster index of ``vec[i]``
:param predicate: The equivalence predicate (i.e. pointer to a boolean function of two arguments or an instance of the class that has the method ``bool operator()(const _Tp& a, const _Tp& b)`` . The predicate returns true when the elements are certainly if the same class, and false if they may or may not be in the same class
The generic function
``partition``
implements an
:math:`O(N^2)`
algorithm for
splitting a set of
:math:`N`
elements into one or more equivalency classes, as described in
http://en.wikipedia.org/wiki/Disjoint-set_data_structure
. The function
returns the number of equivalency classes.

15
modules/core/doc/core.rst Normal file
View File

@ -0,0 +1,15 @@
******************
Core Functionality
******************
.. toctree::
:maxdepth: 2
basic_structures
operations_on_arrays
dynamic_structures
drawing_functions
xml_yaml_persistence
clustering
utility_and_system_functions_and_macros

770
modules/core/doc/drawing_functions.rst Normal file
View File

@ -0,0 +1,770 @@
Drawing Functions
=================
.. highlight:: cpp
Drawing functions work with matrices/images of arbitrary depth.
The boundaries of the shapes can be rendered with antialiasing (implemented only for 8-bit images for now).
All the functions include the parameter color that uses a rgb value (that may be constructed
with
``CV_RGB``
or the :ref:`Scalar` constructor
) for color
images and brightness for grayscale images. For color images the order channel
is normally
*Blue, Green, Red*
, this is what
:func:`imshow`
,
:func:`imread`
and
:func:`imwrite`
expect
, so if you form a color using
:ref:`Scalar`
constructor, it should look like:
.. math::
\texttt{Scalar} (blue \_ component, green \_ component, red \_ component[, alpha \_ component])
If you are using your own image rendering and I/O functions, you can use any channel ordering, the drawing functions process each channel independently and do not depend on the channel order or even on the color space used. The whole image can be converted from BGR to RGB or to a different color space using
:func:`cvtColor`
.
If a drawn figure is partially or completely outside the image, the drawing functions clip it. Also, many drawing functions can handle pixel coordinates specified with sub-pixel accuracy, that is, the coordinates can be passed as fixed-point numbers, encoded as integers. The number of fractional bits is specified by the
``shift``
parameter and the real point coordinates are calculated as
:math:`\texttt{Point}(x,y)\rightarrow\texttt{Point2f}(x*2^{-shift},y*2^{-shift})`
. This feature is especially effective wehn rendering antialiased shapes.
Also, note that the functions do not support alpha-transparency - when the target image is 4-channnel, then the
``color[3]``
is simply copied to the repainted pixels. Thus, if you want to paint semi-transparent shapes, you can paint them in a separate buffer and then blend it with the main image.
.. index:: circle
cv::circle
----------
`id=0.143685141364 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/circle>`__
.. cfunction:: void circle(Mat\& img, Point center, int radius, const Scalar\& color, int thickness=1, int lineType=8, int shift=0)
Draws a circle
:param img: Image where the circle is drawn
:param center: Center of the circle
:param radius: Radius of the circle
:param color: Circle color
:param thickness: Thickness of the circle outline if positive; negative thickness means that a filled circle is to be drawn
:param lineType: Type of the circle boundary, see :func:`line` description
:param shift: Number of fractional bits in the center coordinates and radius value
The function
``circle``
draws a simple or filled circle with a
given center and radius.
.. index:: clipLine
cv::clipLine
------------
`id=0.715949286846 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/clipLine>`__
.. cfunction:: bool clipLine(Size imgSize, Point\& pt1, Point\& pt2)
.. cfunction:: bool clipLine(Rect imgRect, Point\& pt1, Point\& pt2)
Clips the line against the image rectangle
:param imgSize: The image size; the image rectangle will be ``Rect(0, 0, imgSize.width, imgSize.height)``
:param imgSize: The image rectangle
:param pt1: The first line point
:param pt2: The second line point
The functions
``clipLine``
calculate a part of the line
segment which is entirely within the specified rectangle.
They return
``false``
if the line segment is completely outside the rectangle and
``true``
otherwise.
.. index:: ellipse
cv::ellipse
-----------
`id=0.0631091216884 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/ellipse>`__
.. cfunction:: void ellipse(Mat\& img, Point center, Size axes, double angle, double startAngle, double endAngle, const Scalar\& color, int thickness=1, int lineType=8, int shift=0)
.. cfunction:: void ellipse(Mat\& img, const RotatedRect\& box, const Scalar\& color, int thickness=1, int lineType=8)
Draws a simple or thick elliptic arc or an fills ellipse sector.
:param img: The image
:param center: Center of the ellipse
:param axes: Length of the ellipse axes
:param angle: The ellipse rotation angle in degrees
:param startAngle: Starting angle of the elliptic arc in degrees
:param endAngle: Ending angle of the elliptic arc in degrees
:param box: Alternative ellipse representation via a :ref:`RotatedRect` , i.e. the function draws an ellipse inscribed in the rotated rectangle
:param color: Ellipse color
:param thickness: Thickness of the ellipse arc outline if positive, otherwise this indicates that a filled ellipse sector is to be drawn
:param lineType: Type of the ellipse boundary, see :func:`line` description
:param shift: Number of fractional bits in the center coordinates and axes' values
The functions
``ellipse``
with less parameters draw an ellipse outline, a filled ellipse, an elliptic
arc or a filled ellipse sector.
A piecewise-linear curve is used to approximate the elliptic arc boundary. If you need more control of the ellipse rendering, you can retrieve the curve using
:func:`ellipse2Poly`
and then render it with
:func:`polylines`
or fill it with
:func:`fillPoly`
. If you use the first variant of the function and want to draw the whole ellipse, not an arc, pass
``startAngle=0``
and
``endAngle=360``
. The picture below
explains the meaning of the parameters.
Parameters of Elliptic Arc
.. image:: ../../pics/ellipse.png
.. index:: ellipse2Poly
cv::ellipse2Poly
----------------
`id=0.644340648167 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/ellipse2Poly>`__
.. cfunction:: void ellipse2Poly( Point center, Size axes, int angle, int startAngle, int endAngle, int delta, vector<Point>\& pts )
Approximates an elliptic arc with a polyline
:param center: Center of the arc
:param axes: Half-sizes of the arc. See :func:`ellipse`
:param angle: Rotation angle of the ellipse in degrees. See :func:`ellipse`
:param startAngle: Starting angle of the elliptic arc in degrees
:param endAngle: Ending angle of the elliptic arc in degrees
:param delta: Angle between the subsequent polyline vertices. It defines the approximation accuracy.
:param pts: The output vector of polyline vertices
The function
``ellipse2Poly``
computes the vertices of a polyline that approximates the specified elliptic arc. It is used by
:func:`ellipse`
.
.. index:: fillConvexPoly
cv::fillConvexPoly
------------------
`id=0.345453533071 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/fillConvexPoly>`__
.. cfunction:: void fillConvexPoly(Mat\& img, const Point* pts, int npts, const Scalar\& color, int lineType=8, int shift=0)
Fills a convex polygon.
:param img: Image
:param pts: The polygon vertices
:param npts: The number of polygon vertices
:param color: Polygon color
:param lineType: Type of the polygon boundaries, see :func:`line` description
:param shift: The number of fractional bits in the vertex coordinates
The function
``fillConvexPoly``
draws a filled convex polygon.
This function is much faster than the function
``fillPoly``
and can fill not only convex polygons but any monotonic polygon without self-intersections,
i.e., a polygon whose contour intersects every horizontal line (scan
line) twice at the most (though, its top-most and/or the bottom edge could be horizontal).
.. index:: fillPoly
cv::fillPoly
------------
`id=0.00272984452496 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/fillPoly>`__
.. cfunction:: void fillPoly(Mat\& img, const Point** pts, const int* npts, int ncontours, const Scalar\& color, int lineType=8, int shift=0, Point offset=Point() )
Fills the area bounded by one or more polygons
:param img: Image
:param pts: Array of polygons, each represented as an array of points
:param npts: The array of polygon vertex counters
:param ncontours: The number of contours that bind the filled region
:param color: Polygon color
:param lineType: Type of the polygon boundaries, see :func:`line` description
:param shift: The number of fractional bits in the vertex coordinates
The function
``fillPoly``
fills an area bounded by several
polygonal contours. The function can fills complex areas, for example,
areas with holes, contours with self-intersections (some of thier parts), and so forth.
.. index:: getTextSize
cv::getTextSize
---------------
`id=0.364618843078 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/getTextSize>`__
.. cfunction:: Size getTextSize(const string\& text, int fontFace, double fontScale, int thickness, int* baseLine)
Calculates the width and height of a text string.
:param text: The input text string
:param fontFace: The font to use; see :func:`putText`
:param fontScale: The font scale; see :func:`putText`
:param thickness: The thickness of lines used to render the text; see :func:`putText`
:param baseLine: The output parameter - y-coordinate of the baseline relative to the bottom-most text point
The function
``getTextSize``
calculates and returns size of the box that contain the specified text.
That is, the following code will render some text, the tight box surrounding it and the baseline:
::
// Use "y" to show that the baseLine is about
string text = "Funny text inside the box";
int fontFace = FONT_HERSHEY_SCRIPT_SIMPLEX;
double fontScale = 2;
int thickness = 3;
Mat img(600, 800, CV_8UC3, Scalar::all(0));
int baseline=0;
Size textSize = getTextSize(text, fontFace,
fontScale, thickness, &baseline);
baseline += thickness;
// center the text
Point textOrg((img.cols - textSize.width)/2,
(img.rows + textSize.height)/2);
// draw the box
rectangle(img, textOrg + Point(0, baseline),
textOrg + Point(textSize.width, -textSize.height),
Scalar(0,0,255));
// ... and the baseline first
line(img, textOrg + Point(0, thickness),
textOrg + Point(textSize.width, thickness),
Scalar(0, 0, 255));
// then put the text itself
putText(img, text, textOrg, fontFace, fontScale,
Scalar::all(255), thickness, 8);
..
.. index:: line
cv::line
--------
`id=0.645160739861 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/line>`__
.. cfunction:: void line(Mat\& img, Point pt1, Point pt2, const Scalar\& color, int thickness=1, int lineType=8, int shift=0)
Draws a line segment connecting two points
:param img: The image
:param pt1: First point of the line segment
:param pt2: Second point of the line segment
:param color: Line color
:param thickness: Line thickness
:param lineType: Type of the line:
* **8** (or omitted) 8-connected line.
* **4** 4-connected line.
* **CV_AA** antialiased line.
:param shift: Number of fractional bits in the point coordinates
The function
``line``
draws the line segment between
``pt1``
and
``pt2``
points in the image. The line is
clipped by the image boundaries. For non-antialiased lines
with integer coordinates the 8-connected or 4-connected Bresenham
algorithm is used. Thick lines are drawn with rounding endings.
Antialiased lines are drawn using Gaussian filtering. To specify
the line color, the user may use the macro
``CV_RGB(r, g, b)``
.
.. index:: LineIterator
.. _LineIterator:
LineIterator
------------
`id=0.913176469223 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/LineIterator>`__
.. ctype:: LineIterator
Class for iterating pixels on a raster line
::
class LineIterator
{
public:
// creates iterators for the line connecting pt1 and pt2
// the line will be clipped on the image boundaries
// the line is 8-connected or 4-connected
// If leftToRight=true, then the iteration is always done
// from the left-most point to the right most,
// not to depend on the ordering of pt1 and pt2 parameters
LineIterator(const Mat& img, Point pt1, Point pt2,
int connectivity=8, bool leftToRight=false);
// returns pointer to the current line pixel
uchar* operator *();
// move the iterator to the next pixel
LineIterator& operator ++();
LineIterator operator ++(int);
// internal state of the iterator
uchar* ptr;
int err, count;
int minusDelta, plusDelta;
int minusStep, plusStep;
};
..
The class
``LineIterator``
is used to get each pixel of a raster line. It can be treated as versatile implementation of the Bresenham algorithm, where you can stop at each pixel and do some extra processing, for example, grab pixel values along the line, or draw a line with some effect (e.g. with XOR operation).
The number of pixels along the line is store in
``LineIterator::count``
.
::
// grabs pixels along the line (pt1, pt2)
// from 8-bit 3-channel image to the buffer
LineIterator it(img, pt1, pt2, 8);
vector<Vec3b> buf(it.count);
for(int i = 0; i < it.count; i++, ++it)
buf[i] = *(const Vec3b)*it;
..
.. index:: rectangle
cv::rectangle
-------------
`id=0.494030339931 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/rectangle>`__
.. cfunction:: void rectangle(Mat\& img, Point pt1, Point pt2, const Scalar\& color, int thickness=1, int lineType=8, int shift=0)
Draws a simple, thick, or filled up-right rectangle.
:param img: Image
:param pt1: One of the rectangle's vertices
:param pt2: Opposite to ``pt1`` rectangle vertex
:param color: Rectangle color or brightness (grayscale image)
:param thickness: Thickness of lines that make up the rectangle. Negative values, e.g. ``CV_FILLED`` , mean that the function has to draw a filled rectangle.
:param lineType: Type of the line, see :func:`line` description
:param shift: Number of fractional bits in the point coordinates
The function
``rectangle``
draws a rectangle outline or a filled rectangle, which two opposite corners are
``pt1``
and
``pt2``
.
.. index:: polylines
cv::polylines
-------------
`id=0.550422277453 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/polylines>`__
.. cfunction:: void polylines(Mat\& img, const Point** pts, const int* npts, int ncontours, bool isClosed, const Scalar\& color, int thickness=1, int lineType=8, int shift=0 )
Draws several polygonal curves
:param img: The image
:param pts: Array of polygonal curves
:param npts: Array of polygon vertex counters
:param ncontours: The number of curves
:param isClosed: Indicates whether the drawn polylines are closed or not. If they are closed, the function draws the line from the last vertex of each curve to its first vertex
:param color: Polyline color
:param thickness: Thickness of the polyline edges
:param lineType: Type of the line segments, see :func:`line` description
:param shift: The number of fractional bits in the vertex coordinates
The function
``polylines``
draws one or more polygonal curves.
.. index:: putText
cv::putText
-----------
`id=0.164290316532 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/putText>`__
.. cfunction:: void putText( Mat\& img, const string\& text, Point org, int fontFace, double fontScale, Scalar color, int thickness=1, int lineType=8, bool bottomLeftOrigin=false )
Draws a text string
:param img: The image
:param text: The text string to be drawn
:param org: The bottom-left corner of the text string in the image
:param fontFace: The font type, one of ``FONT_HERSHEY_SIMPLEX`` , ``FONT_HERSHEY_PLAIN`` ,
``FONT_HERSHEY_DUPLEX`` , ``FONT_HERSHEY_COMPLEX`` , ``FONT_HERSHEY_TRIPLEX`` ,
``FONT_HERSHEY_COMPLEX_SMALL`` , ``FONT_HERSHEY_SCRIPT_SIMPLEX`` or ``FONT_HERSHEY_SCRIPT_COMPLEX`` ,
where each of the font id's can be combined with ``FONT_HERSHEY_ITALIC`` to get the slanted letters.
:param fontScale: The font scale factor that is multiplied by the font-specific base size
:param color: The text color
:param thickness: Thickness of the lines used to draw the text
:param lineType: The line type; see ``line`` for details
:param bottomLeftOrigin: When true, the image data origin is at the bottom-left corner, otherwise it's at the top-left corner
The function
``putText``
renders the specified text string in the image.
Symbols that can not be rendered using the specified font are
replaced by question marks. See
:func:`getTextSize`
for a text rendering code example.

6
modules/core/doc/dynamic_structures.rst Normal file
View File

@ -0,0 +1,6 @@
Dynamic Structures
==================
.. highlight:: cpp

248
modules/core/doc/intro.rst Normal file
View File

@ -0,0 +1,248 @@
************
Introduction
************
.. highlight:: cpp
OpenCV (Open Source Computer Vision Library: http://opencv.willowgarage.com/wiki/) is open-source BSD-licensed library that includes several hundreds computer vision algorithms. It is very popular in the Computer Vision community. Some people call it “de-facto standard” API. The document aims to specify the stable parts of the library, as well as some abstract interfaces for high-level interfaces, with the final goal to make it an official standard.
API specifications in the document use the standard C++ (http://www.open-std.org/jtc1/sc22/wg21/) and the standard C++ library.
The current OpenCV implementation has a modular structure (i.e. the binary package includes several shared or static libraries), where we have:
* **core** - the compact module defining basic data structures, including the dense multi-dimensional array ``Mat``, and basic functions, used by all other modules.
* **imgproc** - image processing module that includes linear and non-linear image filtering, geometrical image transformations (resize, affine and perspective warping, generic table-based remap), color space conversion, histograms etc.
* **video** - video analysis module that includes motion estimation, background subtraction and object tracking algorithms.
* **calib3d** - basic multiple-view geometry algorithms, single and stereo camera calibration, object pose estimation, stereo correspondence algorithms, elements of 3d reconstruction.
* **features2d** - salient feature detectors, descriptors and the descriptor matchers.
* **objdetect** - detection of objects, instances of the predefined classes (e.g faces, eyes, mugs, people, cars etc.)
* **highgui** - easy-to-use interface to video capturing, image and video codecs APIs, as well as simple UI capabilities.
* **gpu** - GPU-accelerated algorithms from different OpenCV modules.
* ... some other helper modules, such as FLANN and Google test wrappers, Python bindings etc.
Although the alternative implementations of the proposed standard may be structured differently, the proposed standard draft is organized by the functionality groups that reflect the decomposition of the library by modules.
Below are the other main concepts of the OpenCV API, implied everywhere in the document.
The API Concepts
================
*"cv"* namespace
----------------
All the OpenCV classes and functions are placed into *"cv"* namespace. Therefore, to access this functionality from your code, use
``cv::`` specifier or ``using namespace cv;`` directive:
.. code-block:: c
#include "opencv2/core/core.hpp"
...
cv::Mat H = cv::findHomography(points1, points2, CV_RANSAC, 5);
...
or
::
#include "opencv2/core/core.hpp"
using namespace cv;
...
Mat H = findHomography(points1, points2, CV_RANSAC, 5 );
...
It is probable that some of the current or future OpenCV external names conflict with STL
or other libraries, in this case use explicit namespace specifiers to resolve the name conflicts:
::
Mat a(100, 100, CV_32F);
randu(a, Scalar::all(1), Scalar::all(std::rand()));
cv::log(a, a);
a /= std::log(2.);
Automatic Memory Management
---------------------------
OpenCV handles all the memory automatically.
First of all, ``std::vector``, ``Mat`` and other data structures used by the functions and methods have destructors that deallocate the underlying memory buffers when needed.
Secondly, in the case of ``Mat`` this *when needed* means that the destructors do not always deallocate the buffers, they take into account possible data sharing. That is, destructor decrements the reference counter, associated with the matrix data buffer, and the buffer is deallocated if and only if the reference counter reaches zero, that is, when no other structures refer to the same buffer. Similarly, when ``Mat`` instance is copied, not actual data is really copied; instead, the associated with it reference counter is incremented to memorize that there is another owner of the same data. There is also ``Mat::clone`` method that creates a full copy of the matrix data. Here is the example
::
// create a big 8Mb matrix
Mat A(1000, 1000, CV_64F);
// create another header for the same matrix;
// this is instant operation, regardless of the matrix size.
Mat B = A;
// create another header for the 3-rd row of A; no data is copied either
Mat C = B.row(3);
// now create a separate copy of the matrix
Mat D = B.clone();
// copy the 5-th row of B to C, that is, copy the 5-th row of A
// to the 3-rd row of A.
B.row(5).copyTo(C);
// now let A and D share the data; after that the modified version
// of A is still referenced by B and C.
A = D;
// now make B an empty matrix (which references no memory buffers),
// but the modified version of A will still be referenced by C,
// despite that C is just a single row of the original A
B.release();
// finally, make a full copy of C. In result, the big modified
// matrix will be deallocated, since it's not referenced by anyone
C = C.clone();
Therefore, ``Mat`` and other basic structures use is simple. But what about high-level classes or even user data types that have been created without automatic memory management in mind? For them OpenCV offers ``Ptr<>`` template class, which is similar to the ``std::shared_ptr`` from C++ TR1. That is, instead of using plain pointers::
T* ptr = new T(...);
one can use::
Ptr<T> ptr = new T(...);
That is, ``Ptr<T> ptr`` incapsulates a pointer to ``T`` instance and a reference counter associated with the pointer. See ``Ptr`` description for details.
.. todo::
Should we replace Ptr<> with the semi-standard shared_ptr<>?
Automatic Allocation of the Output Data
---------------------------------------
OpenCV does not only deallocate the memory automatically, it can also allocate memory for the output function parameters automatically most of the time. That is, if a function has one or more input arrays (``cv::Mat`` instances) and some output arrays, the output arrays automatically allocated or reallocated. The size and type of the output arrays are determined from the input arrays' size and type. If needed, the functions take extra parameters that help to figure out the output array properties.
Here is the example: ::
#include "cv.h"
#include "highgui.h"
using namespace cv;
int main(int, char**)
{
VideoCapture cap(0);
if(!cap.isOpened()) return -1;
Mat frame, edges;
namedWindow("edges",1);
for(;;)
{
cap >> frame;
cvtColor(frame, edges, CV_BGR2GRAY);
GaussianBlur(edges, edges, Size(7,7), 1.5, 1.5);
Canny(edges, edges, 0, 30, 3);
imshow("edges", edges);
if(waitKey(30) >= 0) break;
}
return 0;
}
..
The array ``frame`` is automatically allocated by ``>>`` operator, since the video frame resolution and bit-depth is known to the video capturing module. The array ``edges`` is automatically allocated by ``cvtColor`` function. It will have the same size and the bit-depth as the input array, and the number of channels will be 1, because we passed the color conversion code ``CV_BGR2GRAY`` (that means color to grayscale conversion). Note that ``frame`` and ``edges`` will be allocated only once during the first execution of the loop body, since all the next video frames will have the same resolution (unless user somehow changes the video resolution, in this case the arrays will be automatically reallocated).
The key component of this technology is the method ``Mat::create``. It takes the desired array size and type. If the array already has the specified size and type, the method does nothing. Otherwise, it releases the previously allocated data, if any (this part involves decrementing the reference counter and comparing it with zero), and then allocates a new buffer of the required size. Most functions call this ``Mat::create`` method for each output array and so the automatic output data allocation is implemented.
Some notable exceptions from this scheme are ``cv::mixChannels``, ``cv::RNG::fill`` and a few others functions and methods. They are not able to allocate the output array, so the user has to do that in advance.
Saturation Arithmetics
----------------------
As computer vision library, OpenCV deals a lot with image pixels that are often encoded in a compact 8- or 16-bit per channel form and thus have a limited value range. Furthermore, certain operations on images, like color space conversions, brightness/contrast adjustments, sharpening, complex interpolation (bi-cubic, Lanczos) can produce values out of the available range. If we just store the lowest 8 (16) bit of the result, that will result in some visual artifacts and may affect the further image analysis. To solve this problem, we use so-called *saturation* arithmetics, e.g. to store ``r``, a result of some operation, to 8-bit image, we find the nearest value within 0..255 range:
.. math::
I(x,y)= \min ( \max (\textrm{round}(r), 0), 255)
The similar rules are applied to 8-bit signed and 16-bit signed and unsigned types. This semantics is used everywhere in the library. In C++ code it is done using ``saturate_cast<>`` functions that resembler the standard C++ cast operations. Here is the implementation of the above formula::
I.at<uchar>(y, x) = saturate_cast<uchar>(r);
where ``cv::uchar`` is OpenCV's 8-bit unsigned integer type. In optimized SIMD code we use specialized instructions, like SSE2' ``paddusb``, ``packuswb`` etc. to achieve exactly the same behavior as in C++ code.
Fixed Pixel Types. Limited Use of Templates
-------------------------------------------
Templates is a great feature of C++ that enables implementation of very powerful, efficient and yet safe data structures and algorithms. However, the extensive use of templates may dramatically increase compile time and code size. Besides, it is difficult to separate interface and implementation when templates are used exclusively, which is fine for basic algorithms, but not good for computer vision libraries, where a single algorithm may span a thousands lines of code. Because of this, and also to simplify development of bindings for other languages, like Python, Java, Matlab, that do not have templates at all or have limited template capabilities, we prefer polymorphism and runtime dispatching over templates. In the places where runtime dispatching would be too slow (like pixel access operators), impossible (generic Ptr<> implementation) or just very inconvenient (saturate_cast<>()) we introduce small template classes, methods and functions. Everywhere else we prefer not to use templates.
Because of this, there is a limited fixed set of primitive data types that the library can operate on. That is, an array elements should have one of the following types:
* 8-bit unsigned integer (uchar)
* 8-bit signed integer (schar)
* 16-bit unsigned integer (ushort)
* 16-bit signed integer (short)
* 32-bit signed integer (int)
* 32-bit floating-point number (float)
* 64-bit floating-point number (double)
* a tuple of several elements, where all elements have the same type (one of the above). Array, which elements are such tuples, are called multi-channel arrays, as opposite to the single-channel arrays, which elements are scalar values. The maximum possible number of channels is defined by ``CV_CN_MAX`` constant (which is not smaller than 32).
.. todo::
Need we extend the above list? Shouldn't we throw away 8-bit signed (schar)?
For these basic types there is enumeration::
enum { CV_8U=0, CV_8S=1, CV_16U=2, CV_16S=3, CV_32S=4, CV_32F=5, CV_64F=6 };
Multi-channel (``n``-channel) types can be specified using ``CV_8UC1`` ... ``CV_64FC4`` constants (for number of channels from 1 to 4), or using ``CV_8UC(n)`` ... ``CV_64FC(n)`` or ``CV_MAKETYPE(CV_8U, n)`` ... ``CV_MAKETYPE(CV_64F, n)`` macros when the number of channels is more than 4 or unknown at compile time.
.. note::
``CV_32FC1 == CV_32F``, ``CV_32FC2 == CV_32FC(2) == CV_MAKETYPE(CV_32F, 2)`` and ``CV_MAKETYPE(depth, n) == ((x&7)<<3) + (n-1)``, that is, the type constant is formed from the ``depth``, taking the lowest 3 bits, and the number of channels minus 1, taking the next ``log2(CV_CN_MAX)`` bits.
Here are some examples::
Mat mtx(3, 3, CV_32F); // make 3x3 floating-point matrix
Mat cmtx(10, 1, CV_64FC2); // make 10x1 2-channel floating-point
// matrix (i.e. 10-element complex vector)
Mat img(Size(1920, 1080), CV_8UC3); // make 3-channel (color) image
// of 1920 columns and 1080 rows.
Mat grayscale(image.size(), CV_MAKETYPE(image.depth(), 1)); // make 1-channel image of
// the same size and same
// channel type as img
Arrays, which elements are more complex, can not be constructed or processed using OpenCV. Furthermore, each function or method can handle only a subset of all possible array types. Usually, the more complex is the algorithm, the smaller is the supported subset of formats. Here are some typical examples of such limitations:
* The face detection algorithm only works with 8-bit grayscale or color images.
* Linear algebra functions and most of the machine learning algorithms work with floating-point arrays only.
* Basic functions, such as ``cv::add``, support all types, except for ``CV_8SC(n)``.
* Color space conversion functions support 8-bit unsigned, 16-bit unsigned and 32-bit floating-point types.
The subset of supported types for each functions has been defined from practical needs. All this information about supported types can be put together into a special table. In different implementations of the standard the tables may look differently, for example, on embedded platforms double-precision floating-point type (``CV_64F``) may be unavailable.
.. todo::
Should we include such a table into the standard?
Should we specify minimum "must-have" set of supported formats for each functions?
Error handling
--------------
OpenCV uses exceptions to signal about the critical errors. When the input data has correct format and within the specified value range, but the algorithm can not succeed for some reason (e.g. the optimization algorithm did not converge), it returns a special error code (typically, just a boolean variable).
The exceptions can be instances of ``cv::Exception`` class or its derivatives. In its turn, ``cv::Exception`` is a derivative of std::exception, so it can be gracefully handled in the code using other standard C++ library components.
The exception is typically thrown using ``CV_Error(errcode, description)`` macro, or its printf-like ``CV_Error_(errcode, printf-spec, (printf-args))`` variant, or using ``CV_Assert(condition)`` macro that checks the condition and throws exception when it is not satisfied. For performance-critical code there is ``CV_DbgAssert(condition)`` that is only retained in Debug configuration. Thanks to the automatic memory management, all the intermediate buffers are automatically deallocated in the case of sudden error; user only needs to put a try statement to catch the exceptions, if needed:
::
try
{
... // call OpenCV
}
catch( cv::Exception& e )
{
const char* err_msg = e.what();
std::cout << "exception caught: " << err_msg << std::endl;
}
Multi-threading and reenterability
----------------------------------
The current OpenCV implementation is fully reenterable, and so should be any alternative implementation targeted for multi-threaded environments. That is, the same function, the same *constant* method of a class instance, or the same *non-constant* method of different class instances can be called from different threads. Also, the same ``cv::Mat`` can be used in different threads, because the reference-counting operations use the architecture-specific atomic instructions.

6552
modules/core/doc/operations_on_arrays.rst Normal file
View File

File diff suppressed because it is too large Load Diff

568
modules/core/doc/utility_and_system_functions_and_macros.rst Normal file
View File

@ -0,0 +1,568 @@
Utility and System Functions and Macros
=======================================
.. highlight:: cpp
.. index:: alignPtr
cv::alignPtr
------------
`id=0.732441674276 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/alignPtr>`__
.. cfunction:: template<typename _Tp> _Tp* alignPtr(_Tp* ptr, int n=sizeof(_Tp))
Aligns pointer to the specified number of bytes
:param ptr: The aligned pointer
:param n: The alignment size; must be a power of two
The function returns the aligned pointer of the same type as the input pointer:
.. math::
\texttt{(\_Tp*)(((size\_t)ptr + n-1) \& -n)}
.. index:: alignSize
cv::alignSize
-------------
`id=0.0293178300141 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/alignSize>`__
.. cfunction:: size_t alignSize(size_t sz, int n)
Aligns a buffer size to the specified number of bytes
:param sz: The buffer size to align
:param n: The alignment size; must be a power of two
The function returns the minimum number that is greater or equal to
``sz``
and is divisble by
``n``
:
.. math::
\texttt{(sz + n-1) \& -n}
.. index:: allocate
cv::allocate
------------
`id=0.672857293821 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/allocate>`__
.. cfunction:: template<typename _Tp> _Tp* allocate(size_t n)
Allocates an array of elements
:param n: The number of elements to allocate
The generic function
``allocate``
allocates buffer for the specified number of elements. For each element the default constructor is called.
.. index:: deallocate
cv::deallocate
--------------
`id=0.907199792708 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/deallocate>`__
.. cfunction:: template<typename _Tp> void deallocate(_Tp* ptr, size_t n)
Allocates an array of elements
:param ptr: Pointer to the deallocated buffer
:param n: The number of elements in the buffer
The generic function
``deallocate``
deallocates the buffer allocated with
:func:`allocate`
. The number of elements must match the number passed to
:func:`allocate`
.
.. index:: CV_Assert
.. _CV_Assert:
CV_Assert
---------
`id=0.132247699783 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/CV_Assert>`__
.. cfunction:: CV_Assert(expr)
Checks a condition at runtime.
::
#define CV_Assert( expr ) ...
#define CV_DbgAssert(expr) ...
..
:param expr: The checked expression
The macros
``CV_Assert``
and
``CV_DbgAssert``
evaluate the specified expression and if it is 0, the macros raise an error (see
:func:`error`
). The macro
``CV_Assert``
checks the condition in both Debug and Release configurations, while
``CV_DbgAssert``
is only retained in the Debug configuration.
.. index:: error
cv::error
---------
`id=0.274198769781 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/error>`__
.. cfunction:: void error( const Exception\& exc )
.. cfunction:: \#define CV_Error( code, msg ) <...>
.. cfunction:: \#define CV_Error_( code, args ) <...>
Signals an error and raises the exception
:param exc: The exception to throw
:param code: The error code, normally, a negative value. The list of pre-defined error codes can be found in ``cxerror.h``
:param msg: Text of the error message
:param args: printf-like formatted error message in parantheses
The function and the helper macros
``CV_Error``
and
``CV_Error_``
call the error handler. Currently, the error handler prints the error code (
``exc.code``
), the context (
``exc.file``
,
``exc.line``
and the error message
``exc.err``
to the standard error stream
``stderr``
. In Debug configuration it then provokes memory access violation, so that the execution stack and all the parameters can be analyzed in debugger. In Release configuration the exception
``exc``
is thrown.
The macro
``CV_Error_``
can be used to construct the error message on-fly to include some dynamic information, for example:
::
// note the extra parentheses around the formatted text message
CV_Error_(CV_StsOutOfRange,
("the matrix element (
i, j, mtx.at<float>(i,j)))
..
.. index:: Exception
.. _Exception:
Exception
---------
`id=0.792198322059 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/Exception>`__
.. ctype:: Exception
The exception class passed to error
::
class Exception
{
public:
// various constructors and the copy operation
Exception() { code = 0; line = 0; }
Exception(int _code, const string& _err,
const string& _func, const string& _file, int _line);
Exception(const Exception& exc);
Exception& operator = (const Exception& exc);
// the error code
int code;
// the error text message
string err;
// function name where the error happened
string func;
// the source file name where the error happened
string file;
// the source file line where the error happened
int line;
};
..
The class
``Exception``
encapsulates all or almost all the necessary information about the error happened in the program. The exception is usually constructed and thrown implicitly, via
``CV_Error``
and
``CV_Error_``
macros, see
:func:`error`
.
.. index:: fastMalloc
cv::fastMalloc
--------------
`id=0.913748026438 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/fastMalloc>`__
.. cfunction:: void* fastMalloc(size_t size)
Allocates aligned memory buffer
:param size: The allocated buffer size
The function allocates buffer of the specified size and returns it. When the buffer size is 16 bytes or more, the returned buffer is aligned on 16 bytes.
.. index:: fastFree
cv::fastFree
------------
`id=0.486348253472 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/fastFree>`__
.. cfunction:: void fastFree(void* ptr)
Deallocates memory buffer
:param ptr: Pointer to the allocated buffer
The function deallocates the buffer, allocated with
:func:`fastMalloc`
.
If NULL pointer is passed, the function does nothing.
.. index:: format
cv::format
----------
`id=0.359045522761 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/format>`__
.. cfunction:: string format( const char* fmt, ... )
Returns a text string formatted using printf-like expression
:param fmt: The printf-compatible formatting specifiers
The function acts like
``sprintf``
, but forms and returns STL string. It can be used for form the error message in
:func:`Exception`
constructor.
.. index:: getNumThreads
cv::getNumThreads
-----------------
`id=0.665594834701 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/getNumThreads>`__
.. cfunction:: int getNumThreads()
Returns the number of threads used by OpenCV
The function returns the number of threads that is used by OpenCV.
See also:
:func:`setNumThreads`
,
:func:`getThreadNum`
.
.. index:: getThreadNum
cv::getThreadNum
----------------
`id=0.835208450402 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/getThreadNum>`__
.. cfunction:: int getThreadNum()
Returns index of the currently executed thread
The function returns 0-based index of the currently executed thread. The function is only valid inside a parallel OpenMP region. When OpenCV is built without OpenMP support, the function always returns 0.
See also:
:func:`setNumThreads`
,
:func:`getNumThreads`
.
.. index:: getTickCount
cv::getTickCount
----------------
`id=0.682548115061 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/getTickCount>`__
.. cfunction:: int64 getTickCount()
Returns the number of ticks
The function returns the number of ticks since the certain event (e.g. when the machine was turned on).
It can be used to initialize
:func:`RNG`
or to measure a function execution time by reading the tick count before and after the function call. See also the tick frequency.
.. index:: getTickFrequency
cv::getTickFrequency
--------------------
`id=0.85013360741 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/getTickFrequency>`__
.. cfunction:: double getTickFrequency()
Returns the number of ticks per second
The function returns the number of ticks per second.
That is, the following code computes the execution time in seconds.
::
double t = (double)getTickCount();
// do something ...
t = ((double)getTickCount() - t)/getTickFrequency();
..
.. index:: setNumThreads
cv::setNumThreads
-----------------
`id=0.215563071229 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/setNumThreads>`__
.. cfunction:: void setNumThreads(int nthreads)
Sets the number of threads used by OpenCV
:param nthreads: The number of threads used by OpenCV
The function sets the number of threads used by OpenCV in parallel OpenMP regions. If
``nthreads=0``
, the function will use the default number of threads, which is usually equal to the number of the processing cores.
See also:
:func:`getNumThreads`
,
:func:`getThreadNum`

203
modules/core/doc/xml_yaml_persistence.rst Normal file
View File

@ -0,0 +1,203 @@
XML/YAML Persistence
====================
.. highlight:: cpp
.. index:: FileStorage
.. _FileStorage:
FileStorage
-----------
`id=0.36488878292 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/FileStorage>`__
.. ctype:: FileStorage
The XML/YAML file storage class
::
class FileStorage
{
public:
enum { READ=0, WRITE=1, APPEND=2 };
enum { UNDEFINED=0, VALUE_EXPECTED=1, NAME_EXPECTED=2, INSIDE_MAP=4 };
// the default constructor
FileStorage();
// the constructor that opens the file for reading
// (flags=FileStorage::READ) or writing (flags=FileStorage::WRITE)
FileStorage(const string& filename, int flags);
// wraps the already opened CvFileStorage*
FileStorage(CvFileStorage* fs);
// the destructor; closes the file if needed
virtual ~FileStorage();
// opens the specified file for reading (flags=FileStorage::READ)
// or writing (flags=FileStorage::WRITE)
virtual bool open(const string& filename, int flags);
// checks if the storage is opened
virtual bool isOpened() const;
// closes the file
virtual void release();
// returns the first top-level node
FileNode getFirstTopLevelNode() const;
// returns the root file node
// (it's the parent of the first top-level node)
FileNode root(int streamidx=0) const;
// returns the top-level node by name
FileNode operator[](const string& nodename) const;
FileNode operator[](const char* nodename) const;
// returns the underlying CvFileStorage*
CvFileStorage* operator *() { return fs; }
const CvFileStorage* operator *() const { return fs; }
// writes the certain number of elements of the specified format
// (see DataType) without any headers
void writeRaw( const string& fmt, const uchar* vec, size_t len );
// writes an old-style object (CvMat, CvMatND etc.)
void writeObj( const string& name, const void* obj );
// returns the default object name from the filename
// (used by cvSave() with the default object name etc.)
static string getDefaultObjectName(const string& filename);
Ptr<CvFileStorage> fs;
string elname;
vector<char> structs;
int state;
};
..
.. index:: FileNode
.. _FileNode:
FileNode
--------
`id=0.228849909258 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/FileNode>`__
.. ctype:: FileNode
The XML/YAML file node class
::
class CV_EXPORTS FileNode
{
public:
enum { NONE=0, INT=1, REAL=2, FLOAT=REAL, STR=3,
STRING=STR, REF=4, SEQ=5, MAP=6, TYPE_MASK=7,
FLOW=8, USER=16, EMPTY=32, NAMED=64 };
FileNode();
FileNode(const CvFileStorage* fs, const CvFileNode* node);
FileNode(const FileNode& node);
FileNode operator[](const string& nodename) const;
FileNode operator[](const char* nodename) const;
FileNode operator[](int i) const;
int type() const;
int rawDataSize(const string& fmt) const;
bool empty() const;
bool isNone() const;
bool isSeq() const;
bool isMap() const;
bool isInt() const;
bool isReal() const;
bool isString() const;
bool isNamed() const;
string name() const;
size_t size() const;
operator int() const;
operator float() const;
operator double() const;
operator string() const;
FileNodeIterator begin() const;
FileNodeIterator end() const;
void readRaw( const string& fmt, uchar* vec, size_t len ) const;
void* readObj() const;
// do not use wrapper pointer classes for better efficiency
const CvFileStorage* fs;
const CvFileNode* node;
};
..
.. index:: FileNodeIterator
.. _FileNodeIterator:
FileNodeIterator
----------------
`id=0.575104633905 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/core/FileNodeIterator>`__
.. ctype:: FileNodeIterator
The XML/YAML file node iterator class
::
class CV_EXPORTS FileNodeIterator
{
public:
FileNodeIterator();
FileNodeIterator(const CvFileStorage* fs,
const CvFileNode* node, size_t ofs=0);
FileNodeIterator(const FileNodeIterator& it);
FileNode operator *() const;
FileNode operator ->() const;
FileNodeIterator& operator ++();
FileNodeIterator operator ++(int);
FileNodeIterator& operator --();
FileNodeIterator operator --(int);
FileNodeIterator& operator += (int);
FileNodeIterator& operator -= (int);
FileNodeIterator& readRaw( const string& fmt, uchar* vec,
size_t maxCount=(size_t)INT_MAX );
const CvFileStorage* fs;
const CvFileNode* container;
CvSeqReader reader;
size_t remaining;
};
..

446
modules/features2d/doc/common_interfaces_of_descriptor_extractors.rst Normal file
View File

@ -0,0 +1,446 @@
Common Interfaces of Descriptor Extractors
==========================================
.. highlight:: cpp
Extractors of keypoint descriptors in OpenCV have wrappers with common interface that enables to switch easily
between different algorithms solving the same problem. This section is devoted to computing descriptors
that are represented as vectors in a multidimensional space. All objects that implement ''vector''
descriptor extractors inherit
:func:`DescriptorExtractor`
interface.
.. index:: DescriptorExtractor
.. _DescriptorExtractor:
DescriptorExtractor
-------------------
`id=0.00924308242838 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorExtractor>`__
.. ctype:: DescriptorExtractor
Abstract base class for computing descriptors for image keypoints.
::
class CV_EXPORTS DescriptorExtractor
{
public:
virtual ~DescriptorExtractor();
void compute( const Mat& image, vector<KeyPoint>& keypoints,
Mat& descriptors ) const;
void compute( const vector<Mat>& images, vector<vector<KeyPoint> >& keypoints,
vector<Mat>& descriptors ) const;
virtual void read( const FileNode& );
virtual void write( FileStorage& ) const;
virtual int descriptorSize() const = 0;
virtual int descriptorType() const = 0;
static Ptr<DescriptorExtractor> create( const string& descriptorExtractorType );
protected:
...
};
..
In this interface we assume a keypoint descriptor can be represented as a
dense, fixed-dimensional vector of some basic type. Most descriptors used
in practice follow this pattern, as it makes it very easy to compute
distances between descriptors. Therefore we represent a collection of
descriptors as a
:func:`Mat`
, where each row is one keypoint descriptor.
.. index:: DescriptorExtractor::compute
cv::DescriptorExtractor::compute
--------------------------------
`id=0.622580160404 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorExtractor%3A%3Acompute>`__
.. cfunction:: void DescriptorExtractor::compute( const Mat\& image, vector<KeyPoint>\& keypoints, Mat\& descriptors ) const
Compute the descriptors for a set of keypoints detected in an image (first variant)
or image set (second variant).
:param image: The image.
:param keypoints: The keypoints. Keypoints for which a descriptor cannot be computed are removed.
:param descriptors: The descriptors. Row i is the descriptor for keypoint i.
.. cfunction:: void DescriptorExtractor::compute( const vector<Mat>\& images, vector<vector<KeyPoint> >\& keypoints, vector<Mat>\& descriptors ) const
* **images** The image set.
* **keypoints** Input keypoints collection. keypoints[i] is keypoints
detected in images[i]. Keypoints for which a descriptor
can not be computed are removed.
* **descriptors** Descriptor collection. descriptors[i] are descriptors computed for
a set keypoints[i].
.. index:: DescriptorExtractor::read
cv::DescriptorExtractor::read
-----------------------------
`id=0.708176779821 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorExtractor%3A%3Aread>`__
.. cfunction:: void DescriptorExtractor::read( const FileNode\& fn )
Read descriptor extractor object from file node.
:param fn: File node from which detector will be read.
.. index:: DescriptorExtractor::write
cv::DescriptorExtractor::write
------------------------------
`id=0.206682397054 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorExtractor%3A%3Awrite>`__
.. cfunction:: void DescriptorExtractor::write( FileStorage\& fs ) const
Write descriptor extractor object to file storage.
:param fs: File storage in which detector will be written.
.. index:: DescriptorExtractor::create
cv::DescriptorExtractor::create
-------------------------------
`id=0.923714079643 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorExtractor%3A%3Acreate>`__
:func:`DescriptorExtractor`
.. cfunction:: Ptr<DescriptorExtractor> DescriptorExtractor::create( const string\& descriptorExtractorType )
Descriptor extractor factory that creates of given type with
default parameters (rather using default constructor).
:param descriptorExtractorType: Descriptor extractor type.
Now the following descriptor extractor types are supported:
\
``"SIFT"``
--
:func:`SiftFeatureDetector`
,
\
``"SURF"``
--
:func:`SurfFeatureDetector`
,
\
``"BRIEF"``
--
:func:`BriefFeatureDetector`
.
\
Also combined format is supported: descriptor extractor adapter name (
``"Opponent"``
--
:func:`OpponentColorDescriptorExtractor`
) + descriptor extractor name (see above),
e.g.
``"OpponentSIFT"``
, etc.
.. index:: SiftDescriptorExtractor
.. _SiftDescriptorExtractor:
SiftDescriptorExtractor
-----------------------
`id=0.676546819501 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/SiftDescriptorExtractor>`__
.. ctype:: SiftDescriptorExtractor
Wrapping class for descriptors computing using
:func:`SIFT`
class.
::
class SiftDescriptorExtractor : public DescriptorExtractor
{
public:
SiftDescriptorExtractor(
const SIFT::DescriptorParams& descriptorParams=SIFT::DescriptorParams(),
const SIFT::CommonParams& commonParams=SIFT::CommonParams() );
SiftDescriptorExtractor( double magnification, bool isNormalize=true,
bool recalculateAngles=true, int nOctaves=SIFT::CommonParams::DEFAULT_NOCTAVES,
int nOctaveLayers=SIFT::CommonParams::DEFAULT_NOCTAVE_LAYERS,
int firstOctave=SIFT::CommonParams::DEFAULT_FIRST_OCTAVE,
int angleMode=SIFT::CommonParams::FIRST_ANGLE );
virtual void read (const FileNode &fn);
virtual void write (FileStorage &fs) const;
virtual int descriptorSize() const;
virtual int descriptorType() const;
protected:
...
}
..
.. index:: SurfDescriptorExtractor
.. _SurfDescriptorExtractor:
SurfDescriptorExtractor
-----------------------
`id=0.638581739296 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/SurfDescriptorExtractor>`__
.. ctype:: SurfDescriptorExtractor
Wrapping class for descriptors computing using
:func:`SURF`
class.
::
class SurfDescriptorExtractor : public DescriptorExtractor
{
public:
SurfDescriptorExtractor( int nOctaves=4,
int nOctaveLayers=2, bool extended=false );
virtual void read (const FileNode &fn);
virtual void write (FileStorage &fs) const;
virtual int descriptorSize() const;
virtual int descriptorType() const;
protected:
...
}
..
.. index:: CalonderDescriptorExtractor
.. _CalonderDescriptorExtractor:
CalonderDescriptorExtractor
---------------------------
`id=0.301561509204 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/CalonderDescriptorExtractor>`__
.. ctype:: CalonderDescriptorExtractor
Wrapping class for descriptors computing using
:func:`RTreeClassifier`
class.
::
template<typename T>
class CalonderDescriptorExtractor : public DescriptorExtractor
{
public:
CalonderDescriptorExtractor( const string& classifierFile );
virtual void read( const FileNode &fn );
virtual void write( FileStorage &fs ) const;
virtual int descriptorSize() const;
virtual int descriptorType() const;
protected:
...
}
..
.. index:: OpponentColorDescriptorExtractor
.. _OpponentColorDescriptorExtractor:
OpponentColorDescriptorExtractor
--------------------------------
`id=0.081563051622 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/OpponentColorDescriptorExtractor>`__
.. ctype:: OpponentColorDescriptorExtractor
Adapts a descriptor extractor to compute descripors in Opponent Color Space
(refer to van de Sande et al., CGIV 2008 "Color Descriptors for Object Category Recognition").
Input RGB image is transformed in Opponent Color Space. Then unadapted descriptor extractor
(set in constructor) computes descriptors on each of the three channel and concatenate
them into a single color descriptor.
::
class OpponentColorDescriptorExtractor : public DescriptorExtractor
{
public:
OpponentColorDescriptorExtractor( const Ptr<DescriptorExtractor>& dextractor );
virtual void read( const FileNode& );
virtual void write( FileStorage& ) const;
virtual int descriptorSize() const;
virtual int descriptorType() const;
protected:
...
};
..
.. index:: BriefDescriptorExtractor
.. _BriefDescriptorExtractor:
BriefDescriptorExtractor
------------------------
`id=0.207875021385 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BriefDescriptorExtractor>`__
.. ctype:: BriefDescriptorExtractor
Class for computing BRIEF descriptors described in paper of Calonder M., Lepetit V.,
Strecha C., Fua P.: ''BRIEF: Binary Robust Independent Elementary Features.''
11th European Conference on Computer Vision (ECCV), Heraklion, Crete. LNCS Springer, September 2010.
::
class BriefDescriptorExtractor : public DescriptorExtractor
{
public:
static const int PATCH_SIZE = 48;
static const int KERNEL_SIZE = 9;
// bytes is a length of descriptor in bytes. It can be equal 16, 32 or 64 bytes.
BriefDescriptorExtractor( int bytes = 32 );
virtual void read( const FileNode& );
virtual void write( FileStorage& ) const;
virtual int descriptorSize() const;
virtual int descriptorType() const;
protected:
...
};
..

637
modules/features2d/doc/common_interfaces_of_descriptor_matchers.rst Normal file
View File

@ -0,0 +1,637 @@
Common Interfaces of Descriptor Matchers
========================================
.. highlight:: cpp
Matchers of keypoint descriptors in OpenCV have wrappers with common interface that enables to switch easily
between different algorithms solving the same problem. This section is devoted to matching descriptors
that are represented as vectors in a multidimensional space. All objects that implement ''vector''
descriptor matchers inherit
:func:`DescriptorMatcher`
interface.
.. index:: DMatch
.. _DMatch:
DMatch
------
`id=0.193402930617 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DMatch>`__
.. ctype:: DMatch
Match between two keypoint descriptors: query descriptor index,
train descriptor index, train image index and distance between descriptors.
::
struct DMatch
{
DMatch() : queryIdx(-1), trainIdx(-1), imgIdx(-1),
distance(std::numeric_limits<float>::max()) {}
DMatch( int _queryIdx, int _trainIdx, float _distance ) :
queryIdx(_queryIdx), trainIdx(_trainIdx), imgIdx(-1),
distance(_distance) {}
DMatch( int _queryIdx, int _trainIdx, int _imgIdx, float _distance ) :
queryIdx(_queryIdx), trainIdx(_trainIdx), imgIdx(_imgIdx),
distance(_distance) {}
int queryIdx; // query descriptor index
int trainIdx; // train descriptor index
int imgIdx; // train image index
float distance;
// less is better
bool operator<( const DMatch &m ) const;
};
..
.. index:: DescriptorMatcher
.. _DescriptorMatcher:
DescriptorMatcher
-----------------
`id=0.0185035556985 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher>`__
.. ctype:: DescriptorMatcher
Abstract base class for matching keypoint descriptors. It has two groups
of match methods: for matching descriptors of one image with other image or
with image set.
::
class DescriptorMatcher
{
public:
virtual ~DescriptorMatcher();
virtual void add( const vector<Mat>& descriptors );
const vector<Mat>& getTrainDescriptors() const;
virtual void clear();
bool empty() const;
virtual bool isMaskSupported() const = 0;
virtual void train();
/*
* Group of methods to match descriptors from image pair.
*/
void match( const Mat& queryDescriptors, const Mat& trainDescriptors,
vector<DMatch>& matches, const Mat& mask=Mat() ) const;
void knnMatch( const Mat& queryDescriptors, const Mat& trainDescriptors,
vector<vector<DMatch> >& matches, int k,
const Mat& mask=Mat(), bool compactResult=false ) const;
void radiusMatch( const Mat& queryDescriptors, const Mat& trainDescriptors,
vector<vector<DMatch> >& matches, float maxDistance,
const Mat& mask=Mat(), bool compactResult=false ) const;
/*
* Group of methods to match descriptors from one image to image set.
*/
void match( const Mat& queryDescriptors, vector<DMatch>& matches,
const vector<Mat>& masks=vector<Mat>() );
void knnMatch( const Mat& queryDescriptors, vector<vector<DMatch> >& matches,
int k, const vector<Mat>& masks=vector<Mat>(),
bool compactResult=false );
void radiusMatch( const Mat& queryDescriptors, vector<vector<DMatch> >& matches,
float maxDistance, const vector<Mat>& masks=vector<Mat>(),
bool compactResult=false );
virtual void read( const FileNode& );
virtual void write( FileStorage& ) const;
virtual Ptr<DescriptorMatcher> clone( bool emptyTrainData=false ) const = 0;
static Ptr<DescriptorMatcher> create( const string& descriptorMatcherType );
protected:
vector<Mat> trainDescCollection;
...
};
..
.. index:: DescriptorMatcher::add
cv::DescriptorMatcher::add
--------------------------
`id=0.549221986718 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Aadd>`__
````
.. cfunction:: void add( const vector<Mat>\& descriptors )
Add descriptors to train descriptor collection. If collection trainDescCollectionis not empty
the new descriptors are added to existing train descriptors.
:param descriptors: Descriptors to add. Each ``descriptors[i]`` is a set of descriptors
from the same (one) train image.
.. index:: DescriptorMatcher::getTrainDescriptors
cv::DescriptorMatcher::getTrainDescriptors
------------------------------------------
`id=0.354691082433 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3AgetTrainDescriptors>`__
````
.. cfunction:: const vector<Mat>\& getTrainDescriptors() const
Returns constant link to the train descriptor collection (i.e. trainDescCollection).
.. index:: DescriptorMatcher::clear
cv::DescriptorMatcher::clear
----------------------------
`id=0.776403699262 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Aclear>`__
.. cfunction:: void DescriptorMatcher::clear()
Clear train descriptor collection.
.. index:: DescriptorMatcher::empty
cv::DescriptorMatcher::empty
----------------------------
`id=0.186730120991 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Aempty>`__
.. cfunction:: bool DescriptorMatcher::empty() const
Return true if there are not train descriptors in collection.
.. index:: DescriptorMatcher::isMaskSupported
cv::DescriptorMatcher::isMaskSupported
--------------------------------------
`id=0.4880242426 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3AisMaskSupported>`__
.. cfunction:: bool DescriptorMatcher::isMaskSupported()
Returns true if descriptor matcher supports masking permissible matches.
.. index:: DescriptorMatcher::train
cv::DescriptorMatcher::train
----------------------------
`id=0.708209257367 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Atrain>`__
.. cfunction:: void DescriptorMatcher::train()
Train descriptor matcher (e.g. train flann index). In all methods to match the method train()
is run every time before matching. Some descriptor matchers (e.g. BruteForceMatcher) have empty
implementation of this method, other matchers realy train their inner structures (e.g. FlannBasedMatcher
trains flann::Index)
.. index:: DescriptorMatcher::match
cv::DescriptorMatcher::match
----------------------------
`id=0.803878673329 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Amatch>`__
````
````
````
````
.. cfunction:: void DescriptorMatcher::match( const Mat\& queryDescriptors, const Mat\& trainDescriptors, vector<DMatch>\& matches, const Mat\& mask=Mat() ) const
Find the best match for each descriptor from a query set with train descriptors.
Supposed that the query descriptors are of keypoints detected on the same query image.
In first variant of this method train descriptors are set as input argument and
supposed that they are of keypoints detected on the same train image. In second variant
of the method train descriptors collection that was set using addmethod is used.
Optional mask (or masks) can be set to describe which descriptors can be matched. queryDescriptors[i]can be matched with trainDescriptors[j]only if mask.at<uchar>(i,j)is non-zero.
.. cfunction:: void DescriptorMatcher::match( const Mat\& queryDescriptors, vector<DMatch>\& matches, const vector<Mat>\& masks=vector<Mat>() )
:param queryDescriptors: Query set of descriptors.
:param trainDescriptors: Train set of descriptors. This will not be added to train descriptors collection
stored in class object.
:param matches: Matches. If some query descriptor masked out in ``mask`` no match will be added for this descriptor.
So ``matches`` size may be less query descriptors count.
:param mask: Mask specifying permissible matches between input query and train matrices of descriptors.
:param masks: The set of masks. Each ``masks[i]`` specifies permissible matches between input query descriptors
and stored train descriptors from i-th image (i.e. ``trainDescCollection[i])`` .
.. index:: DescriptorMatcher::knnMatch
cv::DescriptorMatcher::knnMatch
-------------------------------
`id=0.510078848403 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3AknnMatch>`__
:func:`DescriptorMatcher::match`
.. cfunction:: void DescriptorMatcher::knnMatch( const Mat\& queryDescriptors, const Mat\& trainDescriptors, vector<vector<DMatch> >\& matches, int k, const Mat\& mask=Mat(), bool compactResult=false ) const
Find the k best matches for each descriptor from a query set with train descriptors.
Found k (or less if not possible) matches are returned in distance increasing order.
Details about query and train descriptors see in .
.. cfunction:: void DescriptorMatcher::knnMatch( const Mat\& queryDescriptors, vector<vector<DMatch> >\& matches, int k, const vector<Mat>\& masks=vector<Mat>(), bool compactResult=false )
:param queryDescriptors, trainDescriptors, mask, masks: See in :func:`DescriptorMatcher::match` .
:param matches: Mathes. Each ``matches[i]`` is k or less matches for the same query descriptor.
:param k: Count of best matches will be found per each query descriptor (or less if it's not possible).
:param compactResult: It's used when mask (or masks) is not empty. If ``compactResult`` is false ``matches`` vector will have the same size as ``queryDescriptors`` rows. If ``compactResult``
is true ``matches`` vector will not contain matches for fully masked out query descriptors.
.. index:: DescriptorMatcher::radiusMatch
cv::DescriptorMatcher::radiusMatch
----------------------------------
`id=0.763278154174 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3AradiusMatch>`__
:func:`DescriptorMatcher::match`
.. cfunction:: void DescriptorMatcher::radiusMatch( const Mat\& queryDescriptors, const Mat\& trainDescriptors, vector<vector<DMatch> >\& matches, float maxDistance, const Mat\& mask=Mat(), bool compactResult=false ) const
Find the best matches for each query descriptor which have distance less than given threshold.
Found matches are returned in distance increasing order. Details about query and train
descriptors see in .
.. cfunction:: void DescriptorMatcher::radiusMatch( const Mat\& queryDescriptors, vector<vector<DMatch> >\& matches, float maxDistance, const vector<Mat>\& masks=vector<Mat>(), bool compactResult=false )
:param queryDescriptors, trainDescriptors, mask, masks: See in :func:`DescriptorMatcher::match` .
:param matches, compactResult: See in :func:`DescriptorMatcher::knnMatch` .
:param maxDistance: The threshold to found match distances.
.. index:: DescriptorMatcher::clone
cv::DescriptorMatcher::clone
----------------------------
`id=0.743679534249 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Aclone>`__
.. cfunction:: Ptr<DescriptorMatcher> \\DescriptorMatcher::clone( bool emptyTrainData ) const
Clone the matcher.
:param emptyTrainData: If emptyTrainData is false the method create deep copy of the object, i.e. copies
both parameters and train data. If emptyTrainData is true the method create object copy with current parameters
but with empty train data..
.. index:: DescriptorMatcher::create
cv::DescriptorMatcher::create
-----------------------------
`id=0.681869512138 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/DescriptorMatcher%3A%3Acreate>`__
:func:`DescriptorMatcher`
.. cfunction:: Ptr<DescriptorMatcher> DescriptorMatcher::create( const string\& descriptorMatcherType )
Descriptor matcher factory that creates of
given type with default parameters (rather using default constructor).
:param descriptorMatcherType: Descriptor matcher type.
Now the following matcher types are supported:
``"BruteForce"``
(it uses
``L2``
),
``"BruteForce-L1"``
,
``"BruteForce-Hamming"``
,
``"BruteForce-HammingLUT"``
,
``"FlannBased"``
.
.. index:: BruteForceMatcher
.. _BruteForceMatcher:
BruteForceMatcher
-----------------
`id=0.47821275438 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BruteForceMatcher>`__
.. ctype:: BruteForceMatcher
Brute-force descriptor matcher. For each descriptor in the first set, this matcher finds the closest
descriptor in the second set by trying each one. This descriptor matcher supports masking
permissible matches between descriptor sets.
::
template<class Distance>
class BruteForceMatcher : public DescriptorMatcher
{
public:
BruteForceMatcher( Distance d = Distance() );
virtual ~BruteForceMatcher();
virtual bool isMaskSupported() const;
virtual Ptr<DescriptorMatcher> clone( bool emptyTrainData=false ) const;
protected:
...
}
..
For efficiency, BruteForceMatcher is templated on the distance metric.
For float descriptors, a common choice would be
``L2<float>``
. Class of supported distances are:
::
template<typename T>
struct Accumulator
{
typedef T Type;
};
template<> struct Accumulator<unsigned char> { typedef unsigned int Type; };
template<> struct Accumulator<unsigned short> { typedef unsigned int Type; };
template<> struct Accumulator<char> { typedef int Type; };
template<> struct Accumulator<short> { typedef int Type; };
/*
* Squared Euclidean distance functor
*/
template<class T>
struct L2
{
typedef T ValueType;
typedef typename Accumulator<T>::Type ResultType;
ResultType operator()( const T* a, const T* b, int size ) const;
};
/*
* Manhattan distance (city block distance) functor
*/
template<class T>
struct CV_EXPORTS L1
{
typedef T ValueType;
typedef typename Accumulator<T>::Type ResultType;
ResultType operator()( const T* a, const T* b, int size ) const;
...
};
/*
* Hamming distance (city block distance) functor
*/
struct HammingLUT
{
typedef unsigned char ValueType;
typedef int ResultType;
ResultType operator()( const unsigned char* a, const unsigned char* b,
int size ) const;
...
};
struct Hamming
{
typedef unsigned char ValueType;
typedef int ResultType;
ResultType operator()( const unsigned char* a, const unsigned char* b,
int size ) const;
...
};
..
.. index:: FlannBasedMatcher
.. _FlannBasedMatcher:
FlannBasedMatcher
-----------------
`id=0.721140850904 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/FlannBasedMatcher>`__
.. ctype:: FlannBasedMatcher
Flann based descriptor matcher. This matcher trains
:func:`flann::Index`
on
train descriptor collection and calls it's nearest search methods to find best matches.
So this matcher may be faster in cases of matching to large train collection than
brute force matcher.
``FlannBasedMatcher``
does not support masking permissible
matches between descriptor sets, because
:func:`flann::Index`
does not
support this.
::
class FlannBasedMatcher : public DescriptorMatcher
{
public:
FlannBasedMatcher(
const Ptr<flann::IndexParams>& indexParams=new flann::KDTreeIndexParams(),
const Ptr<flann::SearchParams>& searchParams=new flann::SearchParams() );
virtual void add( const vector<Mat>& descriptors );
virtual void clear();
virtual void train();
virtual bool isMaskSupported() const;
virtual Ptr<DescriptorMatcher> clone( bool emptyTrainData=false ) const;
protected:
...
};
..

1045
modules/features2d/doc/common_interfaces_of_feature_detectors.rst Normal file
View File

File diff suppressed because it is too large Load Diff

677
modules/features2d/doc/common_interfaces_of_generic_descriptor_matchers.rst Normal file
View File

@ -0,0 +1,677 @@
Common Interfaces of Generic Descriptor Matchers
================================================
.. highlight:: cpp
Matchers of keypoint descriptors in OpenCV have wrappers with common interface that enables to switch easily
between different algorithms solving the same problem. This section is devoted to matching descriptors
that can not be represented as vectors in a multidimensional space.
``GenericDescriptorMatcher``
is a more generic interface for descriptors. It does not make any assumptions about descriptor representation.
Every descriptor with
:func:`DescriptorExtractor`
interface has a wrapper with
``GenericDescriptorMatcher``
interface (see
:func:`VectorDescriptorMatcher`
).
There are descriptors such as One way descriptor and Ferns that have
``GenericDescriptorMatcher``
interface implemented, but do not support
:func:`DescriptorExtractor`
.
.. index:: GenericDescriptorMatcher
.. _GenericDescriptorMatcher:
GenericDescriptorMatcher
------------------------
`id=0.973387347242 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher>`__
.. ctype:: GenericDescriptorMatcher
Abstract interface for a keypoint descriptor extracting and matching.
There is
:func:`DescriptorExtractor`
and
:func:`DescriptorMatcher`
for these purposes too, but their interfaces are intended for descriptors
represented as vectors in a multidimensional space.
``GenericDescriptorMatcher``
is a more generic interface for descriptors.
As
:func:`DescriptorMatcher`
,
``GenericDescriptorMatcher``
has two groups
of match methods: for matching keypoints of one image with other image or
with image set.
::
class GenericDescriptorMatcher
{
public:
GenericDescriptorMatcher();
virtual ~GenericDescriptorMatcher();
virtual void add( const vector<Mat>& images,
vector<vector<KeyPoint> >& keypoints );
const vector<Mat>& getTrainImages() const;
const vector<vector<KeyPoint> >& getTrainKeypoints() const;
virtual void clear();
virtual void train() = 0;
virtual bool isMaskSupported() = 0;
void classify( const Mat& queryImage,
vector<KeyPoint>& queryKeypoints,
const Mat& trainImage,
vector<KeyPoint>& trainKeypoints ) const;
void classify( const Mat& queryImage,
vector<KeyPoint>& queryKeypoints );
/*
* Group of methods to match keypoints from image pair.
*/
void match( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
const Mat& trainImage, vector<KeyPoint>& trainKeypoints,
vector<DMatch>& matches, const Mat& mask=Mat() ) const;
void knnMatch( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
const Mat& trainImage, vector<KeyPoint>& trainKeypoints,
vector<vector<DMatch> >& matches, int k,
const Mat& mask=Mat(), bool compactResult=false ) const;
void radiusMatch( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
const Mat& trainImage, vector<KeyPoint>& trainKeypoints,
vector<vector<DMatch> >& matches, float maxDistance,
const Mat& mask=Mat(), bool compactResult=false ) const;
/*
* Group of methods to match keypoints from one image to image set.
*/
void match( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
vector<DMatch>& matches, const vector<Mat>& masks=vector<Mat>() );
void knnMatch( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
vector<vector<DMatch> >& matches, int k,
const vector<Mat>& masks=vector<Mat>(), bool compactResult=false );
void radiusMatch( const Mat& queryImage, vector<KeyPoint>& queryKeypoints,
vector<vector<DMatch> >& matches, float maxDistance,
const vector<Mat>& masks=vector<Mat>(), bool compactResult=false );
virtual void read( const FileNode& );
virtual void write( FileStorage& ) const;
virtual Ptr<GenericDescriptorMatcher> clone( bool emptyTrainData=false ) const = 0;
protected:
...
};
..
.. index:: GenericDescriptorMatcher::add
cv::GenericDescriptorMatcher::add
---------------------------------
`id=0.507600777855 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Aadd>`__
.. cfunction:: void GenericDescriptorMatcher::add( const vector<Mat>\& images, vector<vector<KeyPoint> >\& keypoints )
Adds images and keypoints from them to the train collection (descriptors are supposed to be calculated here).
If train collection is not empty new image and keypoints from them will be added to
existing data.
:param images: Image collection.
:param keypoints: Point collection. Assumes that ``keypoints[i]`` are keypoints
detected in an image ``images[i]`` .
.. index:: GenericDescriptorMatcher::getTrainImages
cv::GenericDescriptorMatcher::getTrainImages
--------------------------------------------
`id=0.520364236881 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3AgetTrainImages>`__
.. cfunction:: const vector<Mat>\& GenericDescriptorMatcher::getTrainImages() const
Returns train image collection.
.. index:: GenericDescriptorMatcher::getTrainKeypoints
cv::GenericDescriptorMatcher::getTrainKeypoints
-----------------------------------------------
`id=0.179197628979 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3AgetTrainKeypoints>`__
.. cfunction:: const vector<vector<KeyPoint> >\& GenericDescriptorMatcher::getTrainKeypoints() const
Returns train keypoints collection.
.. index:: GenericDescriptorMatcher::clear
cv::GenericDescriptorMatcher::clear
-----------------------------------
`id=0.163507435554 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Aclear>`__
.. cfunction:: void GenericDescriptorMatcher::clear()
Clear train collection (iamges and keypoints).
.. index:: GenericDescriptorMatcher::train
cv::GenericDescriptorMatcher::train
-----------------------------------
`id=0.270072381935 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Atrain>`__
.. cfunction:: void GenericDescriptorMatcher::train()
Train the object, e.g. tree-based structure to extract descriptors or
to optimize descriptors matching.
.. index:: GenericDescriptorMatcher::isMaskSupported
cv::GenericDescriptorMatcher::isMaskSupported
---------------------------------------------
`id=0.208711469863 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3AisMaskSupported>`__
.. cfunction:: void GenericDescriptorMatcher::isMaskSupported()
Returns true if generic descriptor matcher supports masking permissible matches.
.. index:: GenericDescriptorMatcher::classify
cv::GenericDescriptorMatcher::classify
--------------------------------------
`id=0.550844968727 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Aclassify>`__
:func:`GenericDescriptorMatcher::add`
.. cfunction:: void GenericDescriptorMatcher::classify( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, const Mat\& trainImage, vector<KeyPoint>\& trainKeypoints ) const
Classifies query keypoints under keypoints of one train image qiven as input argument
(first version of the method) or train image collection that set using (second version).
.. cfunction:: void GenericDescriptorMatcher::classify( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints )
:param queryImage: The query image.
:param queryKeypoints: Keypoints from the query image.
:param trainImage: The train image.
:param trainKeypoints: Keypoints from the train image.
.. index:: GenericDescriptorMatcher::match
cv::GenericDescriptorMatcher::match
-----------------------------------
`id=0.91509902003 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Amatch>`__
:func:`GenericDescriptorMatcher::add`
:func:`DescriptorMatcher::match`
.. cfunction:: void GenericDescriptorMatcher::match( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, const Mat\& trainImage, vector<KeyPoint>\& trainKeypoints, vector<DMatch>\& matches, const Mat\& mask=Mat() ) const
Find best match for query keypoints to the training set. In first version of method
one train image and keypoints detected on it - are input arguments. In second version
query keypoints are matched to training collectin that set using . As in the mask can be set.
.. cfunction:: void GenericDescriptorMatcher::match( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, vector<DMatch>\& matches, const vector<Mat>\& masks=vector<Mat>() )
:param queryImage: Query image.
:param queryKeypoints: Keypoints detected in ``queryImage`` .
:param trainImage: Train image. This will not be added to train image collection
stored in class object.
:param trainKeypoints: Keypoints detected in ``trainImage`` . They will not be added to train points collection
stored in class object.
:param matches: Matches. If some query descriptor (keypoint) masked out in ``mask``
no match will be added for this descriptor.
So ``matches`` size may be less query keypoints count.
:param mask: Mask specifying permissible matches between input query and train keypoints.
:param masks: The set of masks. Each ``masks[i]`` specifies permissible matches between input query keypoints
and stored train keypointss from i-th image.
.. index:: GenericDescriptorMatcher::knnMatch
cv::GenericDescriptorMatcher::knnMatch
--------------------------------------
`id=0.828361496735 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3AknnMatch>`__
:func:`GenericDescriptorMatcher::match`
:func:`DescriptorMatcher::knnMatch`
.. cfunction:: void GenericDescriptorMatcher::knnMatch( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, const Mat\& trainImage, vector<KeyPoint>\& trainKeypoints, vector<vector<DMatch> >\& matches, int k, const Mat\& mask=Mat(), bool compactResult=false ) const
Find the knn best matches for each keypoint from a query set with train keypoints.
Found knn (or less if not possible) matches are returned in distance increasing order.
Details see in and .
.. cfunction:: void GenericDescriptorMatcher::knnMatch( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, vector<vector<DMatch> >\& matches, int k, const vector<Mat>\& masks=vector<Mat>(), bool compactResult=false )
.. index:: GenericDescriptorMatcher::radiusMatch
cv::GenericDescriptorMatcher::radiusMatch
-----------------------------------------
`id=0.732845229707 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3AradiusMatch>`__
:func:`GenericDescriptorMatcher::match`
:func:`DescriptorMatcher::radiusMatch`
.. cfunction:: void GenericDescriptorMatcher::radiusMatch( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, const Mat\& trainImage, vector<KeyPoint>\& trainKeypoints, vector<vector<DMatch> >\& matches, float maxDistance, const Mat\& mask=Mat(), bool compactResult=false ) const
Find the best matches for each query keypoint which have distance less than given threshold.
Found matches are returned in distance increasing order. Details see in and .
.. cfunction:: void GenericDescriptorMatcher::radiusMatch( const Mat\& queryImage, vector<KeyPoint>\& queryKeypoints, vector<vector<DMatch> >\& matches, float maxDistance, const vector<Mat>\& masks=vector<Mat>(), bool compactResult=false )
.. index:: GenericDescriptorMatcher::read
cv::GenericDescriptorMatcher::read
----------------------------------
`id=0.937930388921 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Aread>`__
.. cfunction:: void GenericDescriptorMatcher::read( const FileNode\& fn )
Reads matcher object from a file node.
.. index:: GenericDescriptorMatcher::write
cv::GenericDescriptorMatcher::write
-----------------------------------
`id=0.509497773169 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Awrite>`__
.. cfunction:: void GenericDescriptorMatcher::write( FileStorage\& fs ) const
Writes match object to a file storage
.. index:: GenericDescriptorMatcher::clone
cv::GenericDescriptorMatcher::clone
-----------------------------------
`id=0.864304581549 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/GenericDescriptorMatcher%3A%3Aclone>`__
.. cfunction:: Ptr<GenericDescriptorMatcher>\\GenericDescriptorMatcher::clone( bool emptyTrainData ) const
Clone the matcher.
:param emptyTrainData: If emptyTrainData is false the method create deep copy of the object, i.e. copies
both parameters and train data. If emptyTrainData is true the method create object copy with current parameters
but with empty train data.
.. index:: OneWayDescriptorMatcher
.. _OneWayDescriptorMatcher:
OneWayDescriptorMatcher
-----------------------
`id=0.295296902287 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/OneWayDescriptorMatcher>`__
.. ctype:: OneWayDescriptorMatcher
Wrapping class for computing, matching and classification of descriptors using
:func:`OneWayDescriptorBase`
class.
::
class OneWayDescriptorMatcher : public GenericDescriptorMatcher
{
public:
class Params
{
public:
static const int POSE_COUNT = 500;
static const int PATCH_WIDTH = 24;
static const int PATCH_HEIGHT = 24;
static float GET_MIN_SCALE() { return 0.7f; }
static float GET_MAX_SCALE() { return 1.5f; }
static float GET_STEP_SCALE() { return 1.2f; }
Params( int poseCount = POSE_COUNT,
Size patchSize = Size(PATCH_WIDTH, PATCH_HEIGHT),
string pcaFilename = string(),
string trainPath = string(), string trainImagesList = string(),
float minScale = GET_MIN_SCALE(), float maxScale = GET_MAX_SCALE(),
float stepScale = GET_STEP_SCALE() );
int poseCount;
Size patchSize;
string pcaFilename;
string trainPath;
string trainImagesList;
float minScale, maxScale, stepScale;
};
OneWayDescriptorMatcher( const Params& params=Params() );
virtual ~OneWayDescriptorMatcher();
void initialize( const Params& params, const Ptr<OneWayDescriptorBase>& base=Ptr<OneWayDescriptorBase>() );
// Clears keypoints storing in collection and OneWayDescriptorBase
virtual void clear();
virtual void train();
virtual bool isMaskSupported();
virtual void read( const FileNode &fn );
virtual void write( FileStorage& fs ) const;
virtual Ptr<GenericDescriptorMatcher> clone( bool emptyTrainData=false ) const;
protected:
...
};
..
.. index:: FernDescriptorMatcher
.. _FernDescriptorMatcher:
FernDescriptorMatcher
---------------------
`id=0.410971973421 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/FernDescriptorMatcher>`__
.. ctype:: FernDescriptorMatcher
Wrapping class for computing, matching and classification of descriptors using
:func:`FernClassifier`
class.
::
class FernDescriptorMatcher : public GenericDescriptorMatcher
{
public:
class Params
{
public:
Params( int nclasses=0,
int patchSize=FernClassifier::PATCH_SIZE,
int signatureSize=FernClassifier::DEFAULT_SIGNATURE_SIZE,
int nstructs=FernClassifier::DEFAULT_STRUCTS,
int structSize=FernClassifier::DEFAULT_STRUCT_SIZE,
int nviews=FernClassifier::DEFAULT_VIEWS,
int compressionMethod=FernClassifier::COMPRESSION_NONE,
const PatchGenerator& patchGenerator=PatchGenerator() );
Params( const string& filename );
int nclasses;
int patchSize;
int signatureSize;
int nstructs;
int structSize;
int nviews;
int compressionMethod;
PatchGenerator patchGenerator;
string filename;
};
FernDescriptorMatcher( const Params& params=Params() );
virtual ~FernDescriptorMatcher();
virtual void clear();
virtual void train();
virtual bool isMaskSupported();
virtual void read( const FileNode &fn );
virtual void write( FileStorage& fs ) const;
virtual Ptr<GenericDescriptorMatcher> clone( bool emptyTrainData=false ) const;
protected:
...
};
..
.. index:: VectorDescriptorMatcher
.. _VectorDescriptorMatcher:
VectorDescriptorMatcher
-----------------------
`id=0.89575693039 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/VectorDescriptorMatcher>`__
.. ctype:: VectorDescriptorMatcher
Class used for matching descriptors that can be described as vectors in a finite-dimensional space.
::
class CV_EXPORTS VectorDescriptorMatcher : public GenericDescriptorMatcher
{
public:
VectorDescriptorMatcher( const Ptr<DescriptorExtractor>& extractor, const Ptr<DescriptorMatcher>& matcher );
virtual ~VectorDescriptorMatcher();
virtual void add( const vector<Mat>& imgCollection,
vector<vector<KeyPoint> >& pointCollection );
virtual void clear();
virtual void train();
virtual bool isMaskSupported();
virtual void read( const FileNode& fn );
virtual void write( FileStorage& fs ) const;
virtual Ptr<GenericDescriptorMatcher> clone( bool emptyTrainData=false ) const;
protected:
...
};
..
Example of creating:
::
VectorDescriptorMatcher matcher( new SurfDescriptorExtractor,
new BruteForceMatcher<L2<float> > );
..

140
modules/features2d/doc/drawing_function_of_keypoints_and_matches.rst Normal file
View File

@ -0,0 +1,140 @@
Drawing Function of Keypoints and Matches
=========================================
.. highlight:: cpp
.. index:: drawMatches
cv::drawMatches
---------------
`id=0.919261687295 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/drawMatches>`__
.. cfunction:: void drawMatches( const Mat\& img1, const vector<KeyPoint>\& keypoints1, const Mat\& img2, const vector<KeyPoint>\& keypoints2, const vector<DMatch>\& matches1to2, Mat\& outImg, const Scalar\& matchColor=Scalar::all(-1), const Scalar\& singlePointColor=Scalar::all(-1), const vector<char>\& matchesMask=vector<char>(), int flags=DrawMatchesFlags::DEFAULT )
This function draws matches of keypints from two images on output image.
Match is a line connecting two keypoints (circles).
.. cfunction:: void drawMatches( const Mat\& img1, const vector<KeyPoint>\& keypoints1, const Mat\& img2, const vector<KeyPoint>\& keypoints2, const vector<vector<DMatch> >\& matches1to2, Mat\& outImg, const Scalar\& matchColor=Scalar::all(-1), const Scalar\& singlePointColor=Scalar::all(-1), const vector<vector<char>>\& matchesMask= vector<vector<char> >(), int flags=DrawMatchesFlags::DEFAULT )
:param img1: First source image.
:param keypoints1: Keypoints from first source image.
:param img2: Second source image.
:param keypoints2: Keypoints from second source image.
:param matches: Matches from first image to second one, i.e. ``keypoints1[i]``
has corresponding point ``keypoints2[matches[i]]`` .
:param outImg: Output image. Its content depends on ``flags`` value
what is drawn in output image. See below possible ``flags`` bit values.
:param matchColor: Color of matches (lines and connected keypoints).
If ``matchColor==Scalar::all(-1)`` color will be generated randomly.
:param singlePointColor: Color of single keypoints (circles), i.e. keypoints not having the matches.
If ``singlePointColor==Scalar::all(-1)`` color will be generated randomly.
:param matchesMask: Mask determining which matches will be drawn. If mask is empty all matches will be drawn.
:param flags: Each bit of ``flags`` sets some feature of drawing.
Possible ``flags`` bit values is defined by ``DrawMatchesFlags`` , see below.
::
struct DrawMatchesFlags
{
enum{ DEFAULT = 0, // Output image matrix will be created (Mat::create),
// i.e. existing memory of output image may be reused.
// Two source image, matches and single keypoints
// will be drawn.
// For each keypoint only the center point will be
// drawn (without the circle around keypoint with
// keypoint size and orientation).
DRAW_OVER_OUTIMG = 1, // Output image matrix will not be
// created (Mat::create). Matches will be drawn
// on existing content of output image.
NOT_DRAW_SINGLE_POINTS = 2, // Single keypoints will not be drawn.
DRAW_RICH_KEYPOINTS = 4 // For each keypoint the circle around
// keypoint with keypoint size and orientation will
// be drawn.
};
};
..
.. index:: drawKeypoints
cv::drawKeypoints
-----------------
`id=0.694314481427 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/drawKeypoints>`__
.. cfunction:: void drawKeypoints( const Mat\& image, const vector<KeyPoint>\& keypoints, Mat\& outImg, const Scalar\& color=Scalar::all(-1), int flags=DrawMatchesFlags::DEFAULT )
Draw keypoints.
:param image: Source image.
:param keypoints: Keypoints from source image.
:param outImg: Output image. Its content depends on ``flags`` value
what is drawn in output image. See possible ``flags`` bit values.
:param color: Color of keypoints
.
:param flags: Each bit of ``flags`` sets some feature of drawing.
Possible ``flags`` bit values is defined by ``DrawMatchesFlags`` ,
see above in :func:`drawMatches` .

975
modules/features2d/doc/feature_detection_and_description.rst Normal file
View File

@ -0,0 +1,975 @@
Feature detection and description
=================================
.. highlight:: cpp
.. index:: FAST
cv::FAST
--------
`id=0.180338558353 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/FAST>`__
.. cfunction:: void FAST( const Mat\& image, vector<KeyPoint>\& keypoints, int threshold, bool nonmaxSupression=true )
Detects corners using FAST algorithm by E. Rosten (''Machine learning for high-speed corner detection'', 2006).
:param image: The image. Keypoints (corners) will be detected on this.
:param keypoints: Keypoints detected on the image.
:param threshold: Threshold on difference between intensity of center pixel and
pixels on circle around this pixel. See description of the algorithm.
:param nonmaxSupression: If it is true then non-maximum supression will be applied to detected corners (keypoints).
.. index:: MSER
.. _MSER:
MSER
----
`id=0.0333368188128 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/MSER>`__
.. ctype:: MSER
Maximally-Stable Extremal Region Extractor
::
class MSER : public CvMSERParams
{
public:
// default constructor
MSER();
// constructor that initializes all the algorithm parameters
MSER( int _delta, int _min_area, int _max_area,
float _max_variation, float _min_diversity,
int _max_evolution, double _area_threshold,
double _min_margin, int _edge_blur_size );
// runs the extractor on the specified image; returns the MSERs,
// each encoded as a contour (vector<Point>, see findContours)
// the optional mask marks the area where MSERs are searched for
void operator()( const Mat& image, vector<vector<Point> >& msers, const Mat& mask ) const;
};
..
The class encapsulates all the parameters of MSER (see
http://en.wikipedia.org/wiki/Maximally_stable_extremal_regions
) extraction algorithm.
.. index:: StarDetector
.. _StarDetector:
StarDetector
------------
`id=0.378812518152 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/StarDetector>`__
.. ctype:: StarDetector
Implements Star keypoint detector
::
class StarDetector : CvStarDetectorParams
{
public:
// default constructor
StarDetector();
// the full constructor initialized all the algorithm parameters:
// maxSize - maximum size of the features. The following
// values of the parameter are supported:
// 4, 6, 8, 11, 12, 16, 22, 23, 32, 45, 46, 64, 90, 128
// responseThreshold - threshold for the approximated laplacian,
// used to eliminate weak features. The larger it is,
// the less features will be retrieved
// lineThresholdProjected - another threshold for the laplacian to
// eliminate edges
// lineThresholdBinarized - another threshold for the feature
// size to eliminate edges.
// The larger the 2 threshold, the more points you get.
StarDetector(int maxSize, int responseThreshold,
int lineThresholdProjected,
int lineThresholdBinarized,
int suppressNonmaxSize);
// finds keypoints in an image
void operator()(const Mat& image, vector<KeyPoint>& keypoints) const;
};
..
The class implements a modified version of CenSurE keypoint detector described in
Agrawal08
.. index:: SIFT
.. _SIFT:
SIFT
----
`id=0.385373212311 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/SIFT>`__
.. ctype:: SIFT
Class for extracting keypoints and computing descriptors using approach named Scale Invariant Feature Transform (SIFT).
::
class CV_EXPORTS SIFT
{
public:
struct CommonParams
{
static const int DEFAULT_NOCTAVES = 4;
static const int DEFAULT_NOCTAVE_LAYERS = 3;
static const int DEFAULT_FIRST_OCTAVE = -1;
enum{ FIRST_ANGLE = 0, AVERAGE_ANGLE = 1 };
CommonParams();
CommonParams( int _nOctaves, int _nOctaveLayers, int _firstOctave,
int _angleMode );
int nOctaves, nOctaveLayers, firstOctave;
int angleMode;
};
struct DetectorParams
{
static double GET_DEFAULT_THRESHOLD()
{ return 0.04 / SIFT::CommonParams::DEFAULT_NOCTAVE_LAYERS / 2.0; }
static double GET_DEFAULT_EDGE_THRESHOLD() { return 10.0; }
DetectorParams();
DetectorParams( double _threshold, double _edgeThreshold );
double threshold, edgeThreshold;
};
struct DescriptorParams
{
static double GET_DEFAULT_MAGNIFICATION() { return 3.0; }
static const bool DEFAULT_IS_NORMALIZE = true;
static const int DESCRIPTOR_SIZE = 128;
DescriptorParams();
DescriptorParams( double _magnification, bool _isNormalize,
bool _recalculateAngles );
double magnification;
bool isNormalize;
bool recalculateAngles;
};
SIFT();
//! sift-detector constructor
SIFT( double _threshold, double _edgeThreshold,
int _nOctaves=CommonParams::DEFAULT_NOCTAVES,
int _nOctaveLayers=CommonParams::DEFAULT_NOCTAVE_LAYERS,
int _firstOctave=CommonParams::DEFAULT_FIRST_OCTAVE,
int _angleMode=CommonParams::FIRST_ANGLE );
//! sift-descriptor constructor
SIFT( double _magnification, bool _isNormalize=true,
bool _recalculateAngles = true,
int _nOctaves=CommonParams::DEFAULT_NOCTAVES,
int _nOctaveLayers=CommonParams::DEFAULT_NOCTAVE_LAYERS,
int _firstOctave=CommonParams::DEFAULT_FIRST_OCTAVE,
int _angleMode=CommonParams::FIRST_ANGLE );
SIFT( const CommonParams& _commParams,
const DetectorParams& _detectorParams = DetectorParams(),
const DescriptorParams& _descriptorParams = DescriptorParams() );
//! returns the descriptor size in floats (128)
int descriptorSize() const { return DescriptorParams::DESCRIPTOR_SIZE; }
//! finds the keypoints using SIFT algorithm
void operator()(const Mat& img, const Mat& mask,
vector<KeyPoint>& keypoints) const;
//! finds the keypoints and computes descriptors for them using SIFT algorithm.
//! Optionally it can compute descriptors for the user-provided keypoints
void operator()(const Mat& img, const Mat& mask,
vector<KeyPoint>& keypoints,
Mat& descriptors,
bool useProvidedKeypoints=false) const;
CommonParams getCommonParams () const { return commParams; }
DetectorParams getDetectorParams () const { return detectorParams; }
DescriptorParams getDescriptorParams () const { return descriptorParams; }
protected:
...
};
..
.. index:: SURF
.. _SURF:
SURF
----
`id=0.43149154692 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/SURF>`__
.. ctype:: SURF
Class for extracting Speeded Up Robust Features from an image.
::
class SURF : public CvSURFParams
{
public:
// default constructor
SURF();
// constructor that initializes all the algorithm parameters
SURF(double _hessianThreshold, int _nOctaves=4,
int _nOctaveLayers=2, bool _extended=false);
// returns the number of elements in each descriptor (64 or 128)
int descriptorSize() const;
// detects keypoints using fast multi-scale Hessian detector
void operator()(const Mat& img, const Mat& mask,
vector<KeyPoint>& keypoints) const;
// detects keypoints and computes the SURF descriptors for them;
// output vector "descriptors" stores elements of descriptors and has size
// equal descriptorSize()*keypoints.size() as each descriptor is
// descriptorSize() elements of this vector.
void operator()(const Mat& img, const Mat& mask,
vector<KeyPoint>& keypoints,
vector<float>& descriptors,
bool useProvidedKeypoints=false) const;
};
..
The class
``SURF``
implements Speeded Up Robust Features descriptor
Bay06
.
There is fast multi-scale Hessian keypoint detector that can be used to find the keypoints
(which is the default option), but the descriptors can be also computed for the user-specified keypoints.
The function can be used for object tracking and localization, image stitching etc. See the
``find_obj.cpp``
demo in OpenCV samples directory.
.. index:: RandomizedTree
.. _RandomizedTree:
RandomizedTree
--------------
`id=0.539311466248 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RandomizedTree>`__
.. ctype:: RandomizedTree
The class contains base structure for
``RTreeClassifier``
::
class CV_EXPORTS RandomizedTree
{
public:
friend class RTreeClassifier;
RandomizedTree();
~RandomizedTree();
void train(std::vector<BaseKeypoint> const& base_set,
cv::RNG &rng, int depth, int views,
size_t reduced_num_dim, int num_quant_bits);
void train(std::vector<BaseKeypoint> const& base_set,
cv::RNG &rng, PatchGenerator &make_patch, int depth,
int views, size_t reduced_num_dim, int num_quant_bits);
// following two funcs are EXPERIMENTAL
//(do not use unless you know exactly what you do)
static void quantizeVector(float *vec, int dim, int N, float bnds[2],
int clamp_mode=0);
static void quantizeVector(float *src, int dim, int N, float bnds[2],
uchar *dst);
// patch_data must be a 32x32 array (no row padding)
float* getPosterior(uchar* patch_data);
const float* getPosterior(uchar* patch_data) const;
uchar* getPosterior2(uchar* patch_data);
void read(const char* file_name, int num_quant_bits);
void read(std::istream &is, int num_quant_bits);
void write(const char* file_name) const;
void write(std::ostream &os) const;
int classes() { return classes_; }
int depth() { return depth_; }
void discardFloatPosteriors() { freePosteriors(1); }
inline void applyQuantization(int num_quant_bits)
{ makePosteriors2(num_quant_bits); }
private:
int classes_;
int depth_;
int num_leaves_;
std::vector<RTreeNode> nodes_;
float **posteriors_; // 16-bytes aligned posteriors
uchar **posteriors2_; // 16-bytes aligned posteriors
std::vector<int> leaf_counts_;
void createNodes(int num_nodes, cv::RNG &rng);
void allocPosteriorsAligned(int num_leaves, int num_classes);
void freePosteriors(int which);
// which: 1=posteriors_, 2=posteriors2_, 3=both
void init(int classes, int depth, cv::RNG &rng);
void addExample(int class_id, uchar* patch_data);
void finalize(size_t reduced_num_dim, int num_quant_bits);
int getIndex(uchar* patch_data) const;
inline float* getPosteriorByIndex(int index);
inline uchar* getPosteriorByIndex2(int index);
inline const float* getPosteriorByIndex(int index) const;
void convertPosteriorsToChar();
void makePosteriors2(int num_quant_bits);
void compressLeaves(size_t reduced_num_dim);
void estimateQuantPercForPosteriors(float perc[2]);
};
..
.. index:: RandomizedTree::train
cv::RandomizedTree::train
-------------------------
`id=0.360469298211 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RandomizedTree%3A%3Atrain>`__
.. cfunction:: void train(std::vector<BaseKeypoint> const\& base_set, cv::RNG \&rng, PatchGenerator \&make_patch, int depth, int views, size_t reduced_num_dim, int num_quant_bits)
Trains a randomized tree using input set of keypoints
.. cfunction:: void train(std::vector<BaseKeypoint> const\& base_set, cv::RNG \&rng, PatchGenerator \&make_patch, int depth, int views, size_t reduced_num_dim, int num_quant_bits)
{Vector of
``BaseKeypoint``
type. Contains keypoints from the image are used for training}
{Random numbers generator is used for training}
{Patch generator is used for training}
{Maximum tree depth}
{Number of dimensions are used in compressed signature}
{Number of bits are used for quantization}
.. index:: RandomizedTree::read
cv::RandomizedTree::read
------------------------
`id=0.663893576705 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RandomizedTree%3A%3Aread>`__
.. cfunction:: read(const char* file_name, int num_quant_bits)
Reads pre-saved randomized tree from file or stream
.. cfunction:: read(std::istream \&is, int num_quant_bits)
:param file_name: Filename of file contains randomized tree data
:param is: Input stream associated with file contains randomized tree data
{Number of bits are used for quantization}
.. index:: RandomizedTree::write
cv::RandomizedTree::write
-------------------------
`id=0.640726433619 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RandomizedTree%3A%3Awrite>`__
.. cfunction:: void write(const char* file_name) const
Writes current randomized tree to a file or stream
.. cfunction:: void write(std::ostream \&os) const
:param file_name: Filename of file where randomized tree data will be stored
:param is: Output stream associated with file where randomized tree data will be stored
.. index:: RandomizedTree::applyQuantization
cv::RandomizedTree::applyQuantization
-------------------------------------
`id=0.113364904421 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RandomizedTree%3A%3AapplyQuantization>`__
.. cfunction:: void applyQuantization(int num_quant_bits)
Applies quantization to the current randomized tree
{Number of bits are used for quantization}
.. index:: RTreeNode
.. _RTreeNode:
RTreeNode
---------
`id=0.718763052087 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeNode>`__
.. ctype:: RTreeNode
The class contains base structure for
``RandomizedTree``
::
struct RTreeNode
{
short offset1, offset2;
RTreeNode() {}
RTreeNode(uchar x1, uchar y1, uchar x2, uchar y2)
: offset1(y1*PATCH_SIZE + x1),
offset2(y2*PATCH_SIZE + x2)
{}
//! Left child on 0, right child on 1
inline bool operator() (uchar* patch_data) const
{
return patch_data[offset1] > patch_data[offset2];
}
};
..
.. index:: RTreeClassifier
.. _RTreeClassifier:
RTreeClassifier
---------------
`id=0.477872539921 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier>`__
.. ctype:: RTreeClassifier
The class contains
``RTreeClassifier``
. It represents calonder descriptor which was originally introduced by Michael Calonder
::
class CV_EXPORTS RTreeClassifier
{
public:
static const int DEFAULT_TREES = 48;
static const size_t DEFAULT_NUM_QUANT_BITS = 4;
RTreeClassifier();
void train(std::vector<BaseKeypoint> const& base_set,
cv::RNG &rng,
int num_trees = RTreeClassifier::DEFAULT_TREES,
int depth = DEFAULT_DEPTH,
int views = DEFAULT_VIEWS,
size_t reduced_num_dim = DEFAULT_REDUCED_NUM_DIM,
int num_quant_bits = DEFAULT_NUM_QUANT_BITS,
bool print_status = true);
void train(std::vector<BaseKeypoint> const& base_set,
cv::RNG &rng,
PatchGenerator &make_patch,
int num_trees = RTreeClassifier::DEFAULT_TREES,
int depth = DEFAULT_DEPTH,
int views = DEFAULT_VIEWS,
size_t reduced_num_dim = DEFAULT_REDUCED_NUM_DIM,
int num_quant_bits = DEFAULT_NUM_QUANT_BITS,
bool print_status = true);
// sig must point to a memory block of at least
//classes()*sizeof(float|uchar) bytes
void getSignature(IplImage *patch, uchar *sig);
void getSignature(IplImage *patch, float *sig);
void getSparseSignature(IplImage *patch, float *sig,
float thresh);
static int countNonZeroElements(float *vec, int n, double tol=1e-10);
static inline void safeSignatureAlloc(uchar **sig, int num_sig=1,
int sig_len=176);
static inline uchar* safeSignatureAlloc(int num_sig=1,
int sig_len=176);
inline int classes() { return classes_; }
inline int original_num_classes()
{ return original_num_classes_; }
void setQuantization(int num_quant_bits);
void discardFloatPosteriors();
void read(const char* file_name);
void read(std::istream &is);
void write(const char* file_name) const;
void write(std::ostream &os) const;
std::vector<RandomizedTree> trees_;
private:
int classes_;
int num_quant_bits_;
uchar **posteriors_;
ushort *ptemp_;
int original_num_classes_;
bool keep_floats_;
};
..
.. index:: RTreeClassifier::train
cv::RTreeClassifier::train
--------------------------
`id=0.173927228061 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3Atrain>`__
.. cfunction:: void train(std::vector<BaseKeypoint> const\& base_set, cv::RNG \&rng, int num_trees = RTreeClassifier::DEFAULT_TREES, int depth = DEFAULT_DEPTH, int views = DEFAULT_VIEWS, size_t reduced_num_dim = DEFAULT_REDUCED_NUM_DIM, int num_quant_bits = DEFAULT_NUM_QUANT_BITS, bool print_status = true)
Trains a randomized tree classificator using input set of keypoints
.. cfunction:: void train(std::vector<BaseKeypoint> const\& base_set, cv::RNG \&rng, PatchGenerator \&make_patch, int num_trees = RTreeClassifier::DEFAULT_TREES, int depth = DEFAULT_DEPTH, int views = DEFAULT_VIEWS, size_t reduced_num_dim = DEFAULT_REDUCED_NUM_DIM, int num_quant_bits = DEFAULT_NUM_QUANT_BITS, bool print_status = true)
{Vector of
``BaseKeypoint``
type. Contains keypoints from the image are used for training}
{Random numbers generator is used for training}
{Patch generator is used for training}
{Number of randomized trees used in RTreeClassificator}
{Maximum tree depth}
{Number of dimensions are used in compressed signature}
{Number of bits are used for quantization}
{Print current status of training on the console}
.. index:: RTreeClassifier::getSignature
cv::RTreeClassifier::getSignature
---------------------------------
`id=0.90043980708 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3AgetSignature>`__
.. cfunction:: void getSignature(IplImage *patch, uchar *sig)
Returns signature for image patch
.. cfunction:: void getSignature(IplImage *patch, float *sig)
{Image patch to calculate signature for}
{Output signature (array dimension is
``reduced_num_dim)``
}
.. index:: RTreeClassifier::getSparseSignature
cv::RTreeClassifier::getSparseSignature
---------------------------------------
`id=0.692099737961 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3AgetSparseSignature>`__
````
.. cfunction:: void getSparseSignature(IplImage *patch, float *sig, float thresh)
The function is simular to getSignaturebut uses the threshold for removing all signature elements less than the threshold. So that the signature is compressed
{Image patch to calculate signature for}
{Output signature (array dimension is
``reduced_num_dim)``
}
{The threshold that is used for compressing the signature}
.. index:: RTreeClassifier::countNonZeroElements
cv::RTreeClassifier::countNonZeroElements
-----------------------------------------
`id=0.553226961988 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3AcountNonZeroElements>`__
.. cfunction:: static int countNonZeroElements(float *vec, int n, double tol=1e-10)
The function returns the number of non-zero elements in the input array.
:param vec: Input vector contains float elements
:param n: Input vector size
{The threshold used for elements counting. We take all elements are less than
``tol``
as zero elements}
.. index:: RTreeClassifier::read
cv::RTreeClassifier::read
-------------------------
`id=0.648907224792 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3Aread>`__
.. cfunction:: read(const char* file_name)
Reads pre-saved RTreeClassifier from file or stream
.. cfunction:: read(std::istream \&is)
:param file_name: Filename of file contains randomized tree data
:param is: Input stream associated with file contains randomized tree data
.. index:: RTreeClassifier::write
cv::RTreeClassifier::write
--------------------------
`id=0.340545032412 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3Awrite>`__
.. cfunction:: void write(const char* file_name) const
Writes current RTreeClassifier to a file or stream
.. cfunction:: void write(std::ostream \&os) const
:param file_name: Filename of file where randomized tree data will be stored
:param is: Output stream associated with file where randomized tree data will be stored
.. index:: RTreeClassifier::setQuantization
cv::RTreeClassifier::setQuantization
------------------------------------
`id=0.788175788924 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/RTreeClassifier%3A%3AsetQuantization>`__
.. cfunction:: void setQuantization(int num_quant_bits)
Applies quantization to the current randomized tree
{Number of bits are used for quantization}
Below there is an example of
``RTreeClassifier``
usage for feature matching. There are test and train images and we extract features from both with SURF. Output is
:math:`best\_corr`
and
:math:`best\_corr\_idx`
arrays which keep the best probabilities and corresponding features indexes for every train feature.
::
CvMemStorage* storage = cvCreateMemStorage(0);
CvSeq *objectKeypoints = 0, *objectDescriptors = 0;
CvSeq *imageKeypoints = 0, *imageDescriptors = 0;
CvSURFParams params = cvSURFParams(500, 1);
cvExtractSURF( test_image, 0, &imageKeypoints, &imageDescriptors,
storage, params );
cvExtractSURF( train_image, 0, &objectKeypoints, &objectDescriptors,
storage, params );
cv::RTreeClassifier detector;
int patch_width = cv::PATCH_SIZE;
iint patch_height = cv::PATCH_SIZE;
vector<cv::BaseKeypoint> base_set;
int i=0;
CvSURFPoint* point;
for (i=0;i<(n_points > 0 ? n_points : objectKeypoints->total);i++)
{
point=(CvSURFPoint*)cvGetSeqElem(objectKeypoints,i);
base_set.push_back(
cv::BaseKeypoint(point->pt.x,point->pt.y,train_image));
}
//Detector training
cv::RNG rng( cvGetTickCount() );
cv::PatchGenerator gen(0,255,2,false,0.7,1.3,-CV_PI/3,CV_PI/3,
-CV_PI/3,CV_PI/3);
printf("RTree Classifier training...n");
detector.train(base_set,rng,gen,24,cv::DEFAULT_DEPTH,2000,
(int)base_set.size(), detector.DEFAULT_NUM_QUANT_BITS);
printf("Donen");
float* signature = new float[detector.original_num_classes()];
float* best_corr;
int* best_corr_idx;
if (imageKeypoints->total > 0)
{
best_corr = new float[imageKeypoints->total];
best_corr_idx = new int[imageKeypoints->total];
}
for(i=0; i < imageKeypoints->total; i++)
{
point=(CvSURFPoint*)cvGetSeqElem(imageKeypoints,i);
int part_idx = -1;
float prob = 0.0f;
CvRect roi = cvRect((int)(point->pt.x) - patch_width/2,
(int)(point->pt.y) - patch_height/2,
patch_width, patch_height);
cvSetImageROI(test_image, roi);
roi = cvGetImageROI(test_image);
if(roi.width != patch_width || roi.height != patch_height)
{
best_corr_idx[i] = part_idx;
best_corr[i] = prob;
}
else
{
cvSetImageROI(test_image, roi);
IplImage* roi_image =
cvCreateImage(cvSize(roi.width, roi.height),
test_image->depth, test_image->nChannels);
cvCopy(test_image,roi_image);
detector.getSignature(roi_image, signature);
for (int j = 0; j< detector.original_num_classes();j++)
{
if (prob < signature[j])
{
part_idx = j;
prob = signature[j];
}
}
best_corr_idx[i] = part_idx;
best_corr[i] = prob;
if (roi_image)
cvReleaseImage(&roi_image);
}
cvResetImageROI(test_image);
}
..

14
modules/features2d/doc/features2d.rst Normal file
View File

@ -0,0 +1,14 @@
*********************
2D Features Framework
*********************
.. toctree::
:maxdepth: 2
feature_detection_and_description
common_interfaces_of_feature_detectors
common_interfaces_of_descriptor_extractors
common_interfaces_of_descriptor_matchers
common_interfaces_of_generic_descriptor_matchers
drawing_function_of_keypoints_and_matches
object_categorization

408
modules/features2d/doc/object_categorization.rst Normal file
View File

@ -0,0 +1,408 @@
Object Categorization
=====================
.. highlight:: cpp
Some approaches based on local 2D features and used to object categorization
are described in this section.
.. index:: BOWTrainer
.. _BOWTrainer:
BOWTrainer
----------
`id=0.926370937775 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWTrainer>`__
.. ctype:: BOWTrainer
Abstract base class for training ''bag of visual words'' vocabulary from a set of descriptors.
See e.g. ''Visual Categorization with Bags of Keypoints'' of Gabriella Csurka, Christopher R. Dance,
Lixin Fan, Jutta Willamowski, Cedric Bray, 2004.
::
class BOWTrainer
{
public:
BOWTrainer(){}
virtual ~BOWTrainer(){}
void add( const Mat& descriptors );
const vector<Mat>& getDescriptors() const;
int descripotorsCount() const;
virtual void clear();
virtual Mat cluster() const = 0;
virtual Mat cluster( const Mat& descriptors ) const = 0;
protected:
...
};
..
.. index:: BOWTrainer::add
cv::BOWTrainer::add
-------------------
`id=0.849162389183 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWTrainer%3A%3Aadd>`__
````
.. cfunction:: void BOWTrainer::add( const Mat\& descriptors )
Add descriptors to training set. The training set will be clustered using clustermethod to construct vocabulary.
:param descriptors: Descriptors to add to training set. Each row of ``descriptors``
matrix is a one descriptor.
.. index:: BOWTrainer::getDescriptors
cv::BOWTrainer::getDescriptors
------------------------------
`id=0.999824242082 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWTrainer%3A%3AgetDescriptors>`__
.. cfunction:: const vector<Mat>\& BOWTrainer::getDescriptors() const
Returns training set of descriptors.
.. index:: BOWTrainer::descripotorsCount
cv::BOWTrainer::descripotorsCount
---------------------------------
`id=0.497913292449 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWTrainer%3A%3AdescripotorsCount>`__
.. cfunction:: const vector<Mat>\& BOWTrainer::descripotorsCount() const
Returns count of all descriptors stored in the training set.
.. index:: BOWTrainer::cluster
cv::BOWTrainer::cluster
-----------------------
`id=0.560094315089 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWTrainer%3A%3Acluster>`__
.. cfunction:: Mat BOWTrainer::cluster() const
Cluster train descriptors. Vocabulary consists from cluster centers. So this method
returns vocabulary. In first method variant the stored in object train descriptors will be
clustered, in second variant -- input descriptors will be clustered.
.. cfunction:: Mat BOWTrainer::cluster( const Mat\& descriptors ) const
:param descriptors: Descriptors to cluster. Each row of ``descriptors``
matrix is a one descriptor. Descriptors will not be added
to the inner train descriptor set.
.. index:: BOWKMeansTrainer
.. _BOWKMeansTrainer:
BOWKMeansTrainer
----------------
`id=0.588500098443 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWKMeansTrainer>`__
.. ctype:: BOWKMeansTrainer
:func:`kmeans`
based class to train visual vocabulary using the ''bag of visual words'' approach.
::
class BOWKMeansTrainer : public BOWTrainer
{
public:
BOWKMeansTrainer( int clusterCount, const TermCriteria& termcrit=TermCriteria(),
int attempts=3, int flags=KMEANS_PP_CENTERS );
virtual ~BOWKMeansTrainer(){}
// Returns trained vocabulary (i.e. cluster centers).
virtual Mat cluster() const;
virtual Mat cluster( const Mat& descriptors ) const;
protected:
...
};
..
To gain an understanding of constructor parameters see
:func:`kmeans`
function
arguments.
.. index:: BOWImgDescriptorExtractor
.. _BOWImgDescriptorExtractor:
BOWImgDescriptorExtractor
-------------------------
`id=0.166378792557 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor>`__
.. ctype:: BOWImgDescriptorExtractor
Class to compute image descriptor using ''bad of visual words''. In few,
such computing consists from the following steps:
1. Compute descriptors for given image and it's keypoints set,
\
2. Find nearest visual words from vocabulary for each keypoint descriptor,
\
3. Image descriptor is a normalized histogram of vocabulary words encountered in the image. I.e.
``i``
-bin of the histogram is a frequency of
``i``
-word of vocabulary in the given image.
::
class BOWImgDescriptorExtractor
{
public:
BOWImgDescriptorExtractor( const Ptr<DescriptorExtractor>& dextractor,
const Ptr<DescriptorMatcher>& dmatcher );
virtual ~BOWImgDescriptorExtractor(){}
void setVocabulary( const Mat& vocabulary );
const Mat& getVocabulary() const;
void compute( const Mat& image, vector<KeyPoint>& keypoints,
Mat& imgDescriptor,
vector<vector<int> >* pointIdxsOfClusters=0,
Mat* descriptors=0 );
int descriptorSize() const;
int descriptorType() const;
protected:
...
};
..
.. index:: BOWImgDescriptorExtractor::BOWImgDescriptorExtractor
cv::BOWImgDescriptorExtractor::BOWImgDescriptorExtractor
--------------------------------------------------------
`id=0.355574799377 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3ABOWImgDescriptorExtractor>`__
.. cfunction:: BOWImgDescriptorExtractor::BOWImgDescriptorExtractor( const Ptr<DescriptorExtractor>\& dextractor, const Ptr<DescriptorMatcher>\& dmatcher )
Constructor.
:param dextractor: Descriptor extractor that will be used to compute descriptors
for input image and it's keypoints.
:param dmatcher: Descriptor matcher that will be used to find nearest word of trained vocabulary to
each keupoints descriptor of the image.
.. index:: BOWImgDescriptorExtractor::setVocabulary
cv::BOWImgDescriptorExtractor::setVocabulary
--------------------------------------------
`id=0.592484692408 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3AsetVocabulary>`__
.. cfunction:: void BOWImgDescriptorExtractor::setVocabulary( const Mat\& vocabulary )
Method to set visual vocabulary.
:param vocabulary: Vocabulary (can be trained using inheritor of :func:`BOWTrainer` ).
Each row of vocabulary is a one visual word (cluster center).
.. index:: BOWImgDescriptorExtractor::getVocabulary
cv::BOWImgDescriptorExtractor::getVocabulary
--------------------------------------------
`id=0.0185667539631 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3AgetVocabulary>`__
.. cfunction:: const Mat\& BOWImgDescriptorExtractor::getVocabulary() const
Returns set vocabulary.
.. index:: BOWImgDescriptorExtractor::compute
cv::BOWImgDescriptorExtractor::compute
--------------------------------------
`id=0.558308680471 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3Acompute>`__
.. cfunction:: void BOWImgDescriptorExtractor::compute( const Mat\& image, vector<KeyPoint>\& keypoints, Mat\& imgDescriptor, vector<vector<int> >* pointIdxsOfClusters=0, Mat* descriptors=0 )
Compute image descriptor using set visual vocabulary.
:param image: The image. Image descriptor will be computed for this.
:param keypoints: Keypoints detected in the input image.
:param imgDescriptor: This is output, i.e. computed image descriptor.
:param pointIdxsOfClusters: Indices of keypoints which belong to the cluster, i.e.
``pointIdxsOfClusters[i]`` is keypoint indices which belong
to the ``i-`` cluster (word of vocabulary) (returned if it is not 0.)
:param descriptors: Descriptors of the image keypoints (returned if it is not 0.)
.. index:: BOWImgDescriptorExtractor::descriptorSize
cv::BOWImgDescriptorExtractor::descriptorSize
---------------------------------------------
`id=0.758326749957 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3AdescriptorSize>`__
.. cfunction:: int BOWImgDescriptorExtractor::descriptorSize() const
Returns image discriptor size, if vocabulary was set, and 0 otherwise.
.. index:: BOWImgDescriptorExtractor::descriptorType
cv::BOWImgDescriptorExtractor::descriptorType
---------------------------------------------
`id=0.940227909801 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/features2d/BOWImgDescriptorExtractor%3A%3AdescriptorType>`__
.. cfunction:: int BOWImgDescriptorExtractor::descriptorType() const
Returns image descriptor type.

903
modules/gpu/doc/camera_calibration_and_3d_reconstruction.rst Normal file
View File

@ -0,0 +1,903 @@
Camera Calibration and 3d Reconstruction
========================================
.. highlight:: cpp
.. index:: gpu::StereoBM_GPU
.. _gpu::StereoBM_GPU:
gpu::StereoBM_GPU
-----------------
`id=0.818546624063 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoBM_GPU>`__
.. ctype:: gpu::StereoBM_GPU
The class for computing stereo correspondence using block matching algorithm.
::
class StereoBM_GPU
{
public:
enum { BASIC_PRESET = 0, PREFILTER_XSOBEL = 1 };
enum { DEFAULT_NDISP = 64, DEFAULT_WINSZ = 19 };
StereoBM_GPU();
StereoBM_GPU(int preset, int ndisparities = DEFAULT_NDISP,
int winSize = DEFAULT_WINSZ);
void operator() (const GpuMat& left, const GpuMat& right,
GpuMat& disparity);
void operator() (const GpuMat& left, const GpuMat& right,
GpuMat& disparity, const Stream & stream);
static bool checkIfGpuCallReasonable();
int preset;
int ndisp;
int winSize;
float avergeTexThreshold;
...
};
..
This class computes the disparity map using block matching algorithm. The class also performs pre- and post- filtering steps: sobel prefiltering (if PREFILTER
_
XSOBEL flag is set) and low textureness filtering (if averageTexThreshols
:math:`>`
0). If
``avergeTexThreshold = 0``
low textureness filtering is disabled, otherwise disparity is set to 0 in each point
``(x, y)``
where for left image
:math:`\sum HorizontalGradiensInWindow(x, y, winSize) < (winSize \cdot winSize) \cdot avergeTexThreshold`
i.e. input left image is low textured.
.. index:: cv::gpu::StereoBM_GPU::StereoBM_GPU
.. _cv::gpu::StereoBM_GPU::StereoBM_GPU:
cv::gpu::StereoBM_GPU::StereoBM_GPU
-----------------------------------
`id=0.487412502312 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3AStereoBM_GPU%3A%3AStereoBM_GPU>`__
_
.. cfunction:: StereoBM_GPU::StereoBM_GPU()
.. cfunction:: StereoBM_GPU::StereoBM_GPU(int preset, int ndisparities = DEFAULT_NDISP, int winSize = DEFAULT_WINSZ)
StereoBMGPU constructors.
:param preset: Preset:
* **BASIC_PRESET** Without preprocessing.
* **PREFILTER_XSOBEL** Sobel prefilter.
:param ndisparities: Number of disparities. Must be a multiple of 8 and less or equal then 256.
:param winSize: Block size.
.. index:: cv::gpu::StereoBM_GPU::operator ()
.. _cv::gpu::StereoBM_GPU::operator ():
cv::gpu::StereoBM_GPU::operator ()
----------------------------------
`id=0.568109898904 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3AStereoBM_GPU%3A%3Aoperator%20%28%29>`__
.. cfunction:: void StereoBM_GPU::operator() (const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity)
.. cfunction:: void StereoBM_GPU::operator() (const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity, const Stream\& stream)
The stereo correspondence operator. Finds the disparity for the specified rectified stereo pair.
:param left: Left image; supports only ``CV_8UC1`` type.
:param right: Right image with the same size and the same type as the left one.
:param disparity: Output disparity map. It will be ``CV_8UC1`` image with the same size as the input images.
:param stream: Stream for the asynchronous version.
.. index:: cv::gpu::StereoBM_GPU::checkIfGpuCallReasonable
.. _cv::gpu::StereoBM_GPU::checkIfGpuCallReasonable:
cv::gpu::StereoBM_GPU::checkIfGpuCallReasonable
-----------------------------------------------
`id=0.0777071732975 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3AStereoBM_GPU%3A%3AcheckIfGpuCallReasonable>`__
.. cfunction:: bool StereoBM_GPU::checkIfGpuCallReasonable()
Some heuristics that tries to estmate if the current GPU will be faster then CPU in this algorithm. It queries current active device.
.. index:: gpu::StereoBeliefPropagation
.. _gpu::StereoBeliefPropagation:
gpu::StereoBeliefPropagation
----------------------------
`id=0.0927694778121 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoBeliefPropagation>`__
.. ctype:: gpu::StereoBeliefPropagation
The class for computing stereo correspondence using belief propagation algorithm.
::
class StereoBeliefPropagation
{
public:
enum { DEFAULT_NDISP = 64 };
enum { DEFAULT_ITERS = 5 };
enum { DEFAULT_LEVELS = 5 };
static void estimateRecommendedParams(int width, int height,
int& ndisp, int& iters, int& levels);
explicit StereoBeliefPropagation(int ndisp = DEFAULT_NDISP,
int iters = DEFAULT_ITERS,
int levels = DEFAULT_LEVELS,
int msg_type = CV_32F);
StereoBeliefPropagation(int ndisp, int iters, int levels,
float max_data_term, float data_weight,
float max_disc_term, float disc_single_jump,
int msg_type = CV_32F);
void operator()(const GpuMat& left, const GpuMat& right,
GpuMat& disparity);
void operator()(const GpuMat& left, const GpuMat& right,
GpuMat& disparity, Stream& stream);
void operator()(const GpuMat& data, GpuMat& disparity);
void operator()(const GpuMat& data, GpuMat& disparity, Stream& stream);
int ndisp;
int iters;
int levels;
float max_data_term;
float data_weight;
float max_disc_term;
float disc_single_jump;
int msg_type;
...
};
..
The class implements Pedro F. Felzenszwalb algorithm
felzenszwalb_bp
. It can compute own data cost (using truncated linear model) or use user-provided data cost.
**Please note:**
``StereoBeliefPropagation``
requires a lot of memory:
.. math::
width \_ step \cdot height \cdot ndisp \cdot 4 \cdot (1 + 0.25)
for message storage and
.. math::
width \_ step \cdot height \cdot ndisp \cdot (1 + 0.25 + 0.0625 + \dotsm + \frac{1}{4^{levels}}
for data cost storage.
``width_step``
is the number of bytes in a line including the padding.
.. index:: gpu::StereoBeliefPropagation::StereoBeliefPropagation
cv::gpu::StereoBeliefPropagation::StereoBeliefPropagation
---------------------------------------------------------
`id=0.271407166254 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoBeliefPropagation%3A%3AStereoBeliefPropagation>`__
.. cfunction:: StereoBeliefPropagation::StereoBeliefPropagation( int ndisp = DEFAULT_NDISP, int iters = DEFAULT_ITERS, int levels = DEFAULT_LEVELS, int msg_type = CV_32F)
.. cfunction:: StereoBeliefPropagation::StereoBeliefPropagation( int ndisp, int iters, int levels, float max_data_term, float data_weight, float max_disc_term, float disc_single_jump, int msg_type = CV_32F)
StereoBeliefPropagation constructors.
:param ndisp: Number of disparities.
:param iters: Number of BP iterations on each level.
:param levels: Number of levels.
:param max_data_term: Threshold for data cost truncation.
:param data_weight: Data weight.
:param max_disc_term: Threshold for discontinuity truncation.
:param disc_single_jump: Discontinuity single jump.
:param msg_type: Type for messages. Supports ``CV_16SC1`` and ``CV_32FC1`` .
``StereoBeliefPropagation``
uses truncated linear model for the data cost and discontinuity term:
.. math::
DataCost = data \_ weight \cdot \min ( \lvert I_2-I_1 \rvert , max \_ data \_ term)
.. math::
DiscTerm = \min (disc \_ single \_ jump \cdot \lvert f_1-f_2 \rvert , max \_ disc \_ term)
For more details please see
felzenszwalb_bp
.
By default
``StereoBeliefPropagation``
uses floating-point arithmetics and
``CV_32FC1``
type for messages. But also it can use fixed-point arithmetics and
``CV_16SC1``
type for messages for better perfomance. To avoid overflow in this case, the parameters must satisfy
.. math::
10 \cdot 2^{levels-1} \cdot max \_ data \_ term < SHRT \_ MAX
.. index:: gpu::StereoBeliefPropagation::estimateRecommendedParams
cv::gpu::StereoBeliefPropagation::estimateRecommendedParams
-----------------------------------------------------------
`id=0.673949423374 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoBeliefPropagation%3A%3AestimateRecommendedParams>`__
````
````
````
````
````
.. cfunction:: void StereoBeliefPropagation::estimateRecommendedParams( int width, int height, int\& ndisp, int\& iters, int\& levels)
Some heuristics that tries to compute recommended parameters (ndisp, itersand levels) for specified image size (widthand height).
.. index:: gpu::StereoBeliefPropagation::operator ()
cv::gpu::StereoBeliefPropagation::operator ()
---------------------------------------------
`id=0.719591752468 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoBeliefPropagation%3A%3Aoperator%20%28%29>`__
.. cfunction:: void StereoBeliefPropagation::operator()( const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity)
.. cfunction:: void StereoBeliefPropagation::operator()( const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity, Stream\& stream)
The stereo correspondence operator. Finds the disparity for the specified rectified stereo pair or data cost.
:param left: Left image; supports ``CV_8UC1`` , ``CV_8UC3`` and ``CV_8UC4`` types.
:param right: Right image with the same size and the same type as the left one.
:param disparity: Output disparity map. If ``disparity`` is empty output type will be ``CV_16SC1`` , otherwise output type will be ``disparity.type()`` .
:param stream: Stream for the asynchronous version.
.. cfunction:: void StereoBeliefPropagation::operator()( const GpuMat\& data, GpuMat\& disparity)
.. cfunction:: void StereoBeliefPropagation::operator()( const GpuMat\& data, GpuMat\& disparity, Stream\& stream)
* **data** The user specified data cost. It must have ``msg_type`` type and :math:`\texttt{imgRows} \cdot \texttt{ndisp} \times \texttt{imgCols}` size.
* **disparity** Output disparity map. If ``disparity`` is empty output type will be ``CV_16SC1`` , otherwise output type will be ``disparity.type()`` .
* **stream** Stream for the asynchronous version.
.. index:: gpu::StereoConstantSpaceBP
.. _gpu::StereoConstantSpaceBP:
gpu::StereoConstantSpaceBP
--------------------------
`id=0.357913399086 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoConstantSpaceBP>`__
.. ctype:: gpu::StereoConstantSpaceBP
The class for computing stereo correspondence using constant space belief propagation algorithm.
::
class StereoConstantSpaceBP
{
public:
enum { DEFAULT_NDISP = 128 };
enum { DEFAULT_ITERS = 8 };
enum { DEFAULT_LEVELS = 4 };
enum { DEFAULT_NR_PLANE = 4 };
static void estimateRecommendedParams(int width, int height,
int& ndisp, int& iters, int& levels, int& nr_plane);
explicit StereoConstantSpaceBP(int ndisp = DEFAULT_NDISP,
int iters = DEFAULT_ITERS,
int levels = DEFAULT_LEVELS,
int nr_plane = DEFAULT_NR_PLANE,
int msg_type = CV_32F);
StereoConstantSpaceBP(int ndisp, int iters, int levels, int nr_plane,
float max_data_term, float data_weight,
float max_disc_term, float disc_single_jump,
int min_disp_th = 0,
int msg_type = CV_32F);
void operator()(const GpuMat& left, const GpuMat& right,
GpuMat& disparity);
void operator()(const GpuMat& left, const GpuMat& right,
GpuMat& disparity, Stream& stream);
int ndisp;
int iters;
int levels;
int nr_plane;
float max_data_term;
float data_weight;
float max_disc_term;
float disc_single_jump;
int min_disp_th;
int msg_type;
bool use_local_init_data_cost;
...
};
..
The class implements Q. Yang algorithm
qx_csbp
.
``StereoConstantSpaceBP``
supports both local minimum and global minimum data cost initialization algortihms. For more details please see the paper. By default local algorithm is used, and to enable global algorithm set
``use_local_init_data_cost``
to false.
.. index:: gpu::StereoConstantSpaceBP::StereoConstantSpaceBP
cv::gpu::StereoConstantSpaceBP::StereoConstantSpaceBP
-----------------------------------------------------
`id=0.540144508025 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoConstantSpaceBP%3A%3AStereoConstantSpaceBP>`__
.. cfunction:: StereoConstantSpaceBP::StereoConstantSpaceBP(int ndisp = DEFAULT_NDISP, int iters = DEFAULT_ITERS, int levels = DEFAULT_LEVELS, int nr_plane = DEFAULT_NR_PLANE, int msg_type = CV_32F)
.. cfunction:: StereoConstantSpaceBP::StereoConstantSpaceBP(int ndisp, int iters, int levels, int nr_plane, float max_data_term, float data_weight, float max_disc_term, float disc_single_jump, int min_disp_th = 0, int msg_type = CV_32F)
StereoConstantSpaceBP constructors.
:param ndisp: Number of disparities.
:param iters: Number of BP iterations on each level.
:param levels: Number of levels.
:param nr_plane: Number of disparity levels on the first level
:param max_data_term: Truncation of data cost.
:param data_weight: Data weight.
:param max_disc_term: Truncation of discontinuity.
:param disc_single_jump: Discontinuity single jump.
:param min_disp_th: Minimal disparity threshold.
:param msg_type: Type for messages. Supports ``CV_16SC1`` and ``CV_32FC1`` .
``StereoConstantSpaceBP``
uses truncated linear model for the data cost and discontinuity term:
.. math::
DataCost = data \_ weight \cdot \min ( \lvert I_2-I_1 \rvert , max \_ data \_ term)
.. math::
DiscTerm = \min (disc \_ single \_ jump \cdot \lvert f_1-f_2 \rvert , max \_ disc \_ term)
For more details please see
qx_csbp
.
By default
``StereoConstantSpaceBP``
uses floating-point arithmetics and
``CV_32FC1``
type for messages. But also it can use fixed-point arithmetics and
``CV_16SC1``
type for messages for better perfomance. To avoid overflow in this case, the parameters must satisfy
.. math::
10 \cdot 2^{levels-1} \cdot max \_ data \_ term < SHRT \_ MAX
.. index:: gpu::StereoConstantSpaceBP::estimateRecommendedParams
cv::gpu::StereoConstantSpaceBP::estimateRecommendedParams
---------------------------------------------------------
`id=0.693436585596 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoConstantSpaceBP%3A%3AestimateRecommendedParams>`__
````
````
````
``_``
````
````
.. cfunction:: void StereoConstantSpaceBP::estimateRecommendedParams( int width, int height, int\& ndisp, int\& iters, int\& levels, int\& nr_plane)
Some heuristics that tries to compute parameters (ndisp, iters, levelsand nrplane) for specified image size (widthand height).
.. index:: gpu::StereoConstantSpaceBP::operator ()
cv::gpu::StereoConstantSpaceBP::operator ()
-------------------------------------------
`id=0.0775494401011 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStereoConstantSpaceBP%3A%3Aoperator%20%28%29>`__
.. cfunction:: void StereoConstantSpaceBP::operator()( const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity)
.. cfunction:: void StereoConstantSpaceBP::operator()( const GpuMat\& left, const GpuMat\& right, GpuMat\& disparity, Stream\& stream)
The stereo correspondence operator. Finds the disparity for the specified rectified stereo pair.
:param left: Left image; supports ``CV_8UC1`` , ``CV_8UC3`` and ``CV_8UC4`` types.
:param right: Right image with the same size and the same type as the left one.
:param disparity: Output disparity map. If ``disparity`` is empty output type will be ``CV_16SC1`` , otherwise output type will be ``disparity.type()`` .
:param stream: Stream for the asynchronous version.
.. index:: gpu::DisparityBilateralFilter
.. _gpu::DisparityBilateralFilter:
gpu::DisparityBilateralFilter
-----------------------------
`id=0.649410057275 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADisparityBilateralFilter>`__
.. ctype:: gpu::DisparityBilateralFilter
The class for disparity map refinement using joint bilateral filtering.
::
class CV_EXPORTS DisparityBilateralFilter
{
public:
enum { DEFAULT_NDISP = 64 };
enum { DEFAULT_RADIUS = 3 };
enum { DEFAULT_ITERS = 1 };
explicit DisparityBilateralFilter(int ndisp = DEFAULT_NDISP,
int radius = DEFAULT_RADIUS, int iters = DEFAULT_ITERS);
DisparityBilateralFilter(int ndisp, int radius, int iters,
float edge_threshold, float max_disc_threshold,
float sigma_range);
void operator()(const GpuMat& disparity, const GpuMat& image,
GpuMat& dst);
void operator()(const GpuMat& disparity, const GpuMat& image,
GpuMat& dst, Stream& stream);
...
};
..
The class implements Q. Yang algorithm
qx_csbp
.
.. index:: gpu::DisparityBilateralFilter::DisparityBilateralFilter
cv::gpu::DisparityBilateralFilter::DisparityBilateralFilter
-----------------------------------------------------------
`id=0.896263433112 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADisparityBilateralFilter%3A%3ADisparityBilateralFilter>`__
.. cfunction:: DisparityBilateralFilter::DisparityBilateralFilter( int ndisp = DEFAULT_NDISP, int radius = DEFAULT_RADIUS, int iters = DEFAULT_ITERS)
.. cfunction:: DisparityBilateralFilter::DisparityBilateralFilter( int ndisp, int radius, int iters, float edge_threshold, float max_disc_threshold, float sigma_range)
DisparityBilateralFilter constructors.
:param ndisp: Number of disparities.
:param radius: Filter radius.
:param iters: Number of iterations.
:param edge_threshold: Threshold for edges.
:param max_disc_threshold: Constant to reject outliers.
:param sigma_range: Filter range.
.. index:: gpu::DisparityBilateralFilter::operator ()
cv::gpu::DisparityBilateralFilter::operator ()
----------------------------------------------
`id=0.42982970504 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADisparityBilateralFilter%3A%3Aoperator%20%28%29>`__
.. cfunction:: void DisparityBilateralFilter::operator()( const GpuMat\& disparity, const GpuMat\& image, GpuMat\& dst)
.. cfunction:: void DisparityBilateralFilter::operator()( const GpuMat\& disparity, const GpuMat\& image, GpuMat\& dst, Stream\& stream)
Refines disparity map using joint bilateral filtering.
:param disparity: Input disparity map; supports ``CV_8UC1`` and ``CV_16SC1`` types.
:param image: Input image; supports ``CV_8UC1`` and ``CV_8UC3`` types.
:param dst: Destination disparity map; will have the same size and type as ``disparity`` .
:param stream: Stream for the asynchronous version.
.. index:: gpu::drawColorDisp
cv::gpu::drawColorDisp
----------------------
`id=0.876300277953 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AdrawColorDisp>`__
.. cfunction:: void drawColorDisp(const GpuMat\& src_disp, GpuMat\& dst_disp, int ndisp)
.. cfunction:: void drawColorDisp(const GpuMat\& src_disp, GpuMat\& dst_disp, int ndisp, const Stream\& stream)
Does coloring of disparity image.
:param src_disp: Source disparity image. Supports ``CV_8UC1`` and ``CV_16SC1`` types.
:param dst_disp: Output disparity image. Will have the same size as ``src_disp`` and ``CV_8UC4`` type in ``BGRA`` format (alpha = 255).
:param ndisp: Number of disparities.
:param stream: Stream for the asynchronous version.
This function converts
:math:`[0..ndisp)`
interval to
:math:`[0..240, 1, 1]`
in
``HSV``
color space, than convert
``HSV``
color space to
``RGB``
.
.. index:: gpu::reprojectImageTo3D
cv::gpu::reprojectImageTo3D
---------------------------
`id=0.230278526904 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AreprojectImageTo3D>`__
.. cfunction:: void reprojectImageTo3D(const GpuMat\& disp, GpuMat\& xyzw, const Mat\& Q)
.. cfunction:: void reprojectImageTo3D(const GpuMat\& disp, GpuMat\& xyzw, const Mat\& Q, const Stream\& stream)
Reprojects disparity image to 3D space.
:param disp: Input disparity image; supports ``CV_8U`` and ``CV_16S`` types.
:param xyzw: Output 4-channel floating-point image of the same size as ``disp`` . Each element of ``xyzw(x,y)`` will contain the 3D coordinates ``(x,y,z,1)`` of the point ``(x,y)`` , computed from the disparity map.
:param Q: :math:`4 \times 4` perspective transformation matrix that can be obtained via :ref:`StereoRectify` .
:param stream: Stream for the asynchronous version.
See also:
:func:`reprojectImageTo3D`
.

597
modules/gpu/doc/data_structures.rst Normal file
View File

@ -0,0 +1,597 @@
Data Structures
===============
.. highlight:: cpp
.. index:: gpu::DevMem2D_
.. _gpu::DevMem2D_:
gpu::DevMem2D_
--------------
`id=0.542572017346 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADevMem2D_>`__
.. ctype:: gpu::DevMem2D_
This is a simple lightweight class that encapsulate pitched memory on GPU. It is intended to pass to nvcc-compiled code, i.e. CUDA kernels. So it is used internally by OpenCV and by users writes own device code. Its members can be called both from host and from device code.
::
template <typename T> struct DevMem2D_
{
int cols;
int rows;
T* data;
size_t step;
DevMem2D_() : cols(0), rows(0), data(0), step(0){};
DevMem2D_(int rows_, int cols_, T *data_, size_t step_);
template <typename U>
explicit DevMem2D_(const DevMem2D_<U>& d);
typedef T elem_type;
enum { elem_size = sizeof(elem_type) };
__CV_GPU_HOST_DEVICE__ size_t elemSize() const;
/* returns pointer to the beggining of given image row */
__CV_GPU_HOST_DEVICE__ T* ptr(int y = 0);
__CV_GPU_HOST_DEVICE__ const T* ptr(int y = 0) const;
};
..
.. index:: gpu::PtrStep_
.. _gpu::PtrStep_:
gpu::PtrStep_
-------------
`id=0.130599760293 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3APtrStep_>`__
.. ctype:: gpu::PtrStep_
This is structure is similar to DevMem2D
_
but contains only pointer and row step. Width and height fields are excluded due to performance reasons. The structure is for internal use or for users who write own device code.
::
template<typename T> struct PtrStep_
{
T* data;
size_t step;
PtrStep_();
PtrStep_(const DevMem2D_<T>& mem);
typedef T elem_type;
enum { elem_size = sizeof(elem_type) };
__CV_GPU_HOST_DEVICE__ size_t elemSize() const;
__CV_GPU_HOST_DEVICE__ T* ptr(int y = 0);
__CV_GPU_HOST_DEVICE__ const T* ptr(int y = 0) const;
};
..
.. index:: gpu::PtrElemStrp_
.. _gpu::PtrElemStrp_:
gpu::PtrElemStrp_
-----------------
`id=0.837109179392 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3APtrElemStrp_>`__
.. ctype:: gpu::PtrElemStrp_
This is structure is similar to DevMem2D
_
but contains only pointer and row step in elements. Width and height fields are excluded due to performance reasons. This class is can only be constructed if sizeof(T) is a multiple of 256. The structure is for internal use or for users who write own device code.
::
template<typename T> struct PtrElemStep_ : public PtrStep_<T>
{
PtrElemStep_(const DevMem2D_<T>& mem);
__CV_GPU_HOST_DEVICE__ T* ptr(int y = 0);
__CV_GPU_HOST_DEVICE__ const T* ptr(int y = 0) const;
};
..
.. index:: gpu::GpuMat
.. _gpu::GpuMat:
gpu::GpuMat
-----------
`id=0.816128758115 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AGpuMat>`__
.. ctype:: gpu::GpuMat
The base storage class for GPU memory with reference counting. Its interface is almost
:func:`Mat`
interface with some limitations, so using it won't be a problem. The limitations are no arbitrary dimensions support (only 2D), no functions that returns references to its data (because references on GPU are not valid for CPU), no expression templates technique support. Because of last limitation please take care with overloaded matrix operators - they cause memory allocations. The GpuMat class is convertible to
and
so it can be passed to directly to kernel.
**Please note:**
In contrast with
:func:`Mat`
, In most cases
``GpuMat::isContinuous() == false``
, i.e. rows are aligned to size depending on hardware. Also single row GpuMat is always a continuous matrix.
::
class CV_EXPORTS GpuMat
{
public:
//! default constructor
GpuMat();
GpuMat(int rows, int cols, int type);
GpuMat(Size size, int type);
.....
//! builds GpuMat from Mat. Perfom blocking upload to device.
explicit GpuMat (const Mat& m);
//! returns lightweight DevMem2D_ structure for passing
//to nvcc-compiled code. Contains size, data ptr and step.
template <class T> operator DevMem2D_<T>() const;
template <class T> operator PtrStep_<T>() const;
//! pefroms blocking upload data to GpuMat.
void upload(const cv::Mat& m);
void upload(const CudaMem& m, Stream& stream);
//! downloads data from device to host memory. Blocking calls.
operator Mat() const;
void download(cv::Mat& m) const;
//! download async
void download(CudaMem& m, Stream& stream) const;
};
..
**Please note:**
Is it a bad practice to leave static or global GpuMat variables allocated, i.e. to rely on its destructor. That is because destruction order of such variables and CUDA context is undefined and GPU memory release function returns error if CUDA context has been destroyed before.
See also:
:func:`Mat`
.. index:: gpu::CudaMem
.. _gpu::CudaMem:
gpu::CudaMem
------------
`id=0.762477139905 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ACudaMem>`__
.. ctype:: gpu::CudaMem
This is a class with reference counting that wraps special memory type allocation functions from CUDA. Its interface is also
:func:`Mat`
-like but with additional memory type parameter:
*
``ALLOC_PAGE_LOCKED``
Set page locked memory type, used commonly for fast and asynchronous upload/download data from/to GPU.
*
``ALLOC_ZEROCOPY``
Specifies zero copy memory allocation, i.e. with possibility to map host memory to GPU address space if supported.
*
``ALLOC_WRITE_COMBINED``
Sets write combined buffer which is not cached by CPU. Such buffers are used to supply GPU with data when GPU only reads it. The advantage is better CPU cache utilization.
Please note that allocation size of such memory types is usually limited. For more details please see "CUDA 2.2 Pinned Memory APIs" document or "CUDA
_
C Programming Guide".
::
class CV_EXPORTS CudaMem
{
public:
enum { ALLOC_PAGE_LOCKED = 1, ALLOC_ZEROCOPY = 2,
ALLOC_WRITE_COMBINED = 4 };
CudaMem(Size size, int type, int alloc_type = ALLOC_PAGE_LOCKED);
//! creates from cv::Mat with coping data
explicit CudaMem(const Mat& m, int alloc_type = ALLOC_PAGE_LOCKED);
......
void create(Size size, int type, int alloc_type = ALLOC_PAGE_LOCKED);
//! returns matrix header with disabled ref. counting for CudaMem data.
Mat createMatHeader() const;
operator Mat() const;
//! maps host memory into device address space
GpuMat createGpuMatHeader() const;
operator GpuMat() const;
//if host memory can be mapperd to gpu address space;
static bool canMapHostMemory();
int alloc_type;
};
..
.. index:: gpu::CudaMem::createMatHeader
cv::gpu::CudaMem::createMatHeader
---------------------------------
`id=0.772787893445 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ACudaMem%3A%3AcreateMatHeader>`__
:func:`Mat`
.. cfunction:: Mat CudaMem::createMatHeader() const
.. cfunction:: CudaMem::operator Mat() const
Creates header without reference counting to CudaMem data.
.. index:: gpu::CudaMem::createGpuMatHeader
cv::gpu::CudaMem::createGpuMatHeader
------------------------------------
`id=0.759677323147 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ACudaMem%3A%3AcreateGpuMatHeader>`__
:func:`gpu::GpuMat`
``_``
.. cfunction:: GpuMat CudaMem::createGpuMatHeader() const
.. cfunction:: CudaMem::operator GpuMat() const
Maps CPU memory to GPU address space and creates header without reference counting for it. This can be done only if memory was allocated with ALLOCZEROCOPYflag and if it is supported by hardware (laptops often share video and CPU memory, so address spaces can be mapped, and that eliminates extra copy).
.. index:: gpu::CudaMem::canMapHostMemory
cv::gpu::CudaMem::canMapHostMemory
----------------------------------
`id=0.317724503486 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ACudaMem%3A%3AcanMapHostMemory>`__
``_``
.. cfunction:: static bool CudaMem::canMapHostMemory()
Returns true if the current hardware supports address space mapping and ALLOCZEROCOPYmemory allocation
.. index:: gpu::Stream
.. _gpu::Stream:
gpu::Stream
-----------
`id=0.153849663278 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStream>`__
.. ctype:: gpu::Stream
This class encapsulated queue of the asynchronous calls. Some functions have overloads with additional
:func:`gpu::Stream`
parameter. The overloads do initialization work (allocate output buffers, upload constants, etc.), start GPU kernel and return before results are ready. A check if all operation are complete can be performed via
:func:`gpu::Stream::queryIfComplete()`
. Asynchronous upload/download have to be performed from/to page-locked buffers, i.e. using
:func:`gpu::CudaMem`
or
:func:`Mat`
header that points to a region of
:func:`gpu::CudaMem`
.
**Please note the limitation**
: currently it is not guaranteed that all will work properly if one operation will be enqueued twice with different data. Some functions use constant GPU memory and next call may update the memory before previous has been finished. But calling asynchronously different operations is safe because each operation has own constant buffer. Memory copy/upload/download/set operations to buffers hold by user are also safe.
::
class CV_EXPORTS Stream
{
public:
Stream();
~Stream();
Stream(const Stream&);
Stream& operator=(const Stream&);
bool queryIfComplete();
void waitForCompletion();
//! downloads asynchronously.
// Warning! cv::Mat must point to page locked memory
(i.e. to CudaMem data or to its subMat)
void enqueueDownload(const GpuMat& src, CudaMem& dst);
void enqueueDownload(const GpuMat& src, Mat& dst);
//! uploads asynchronously.
// Warning! cv::Mat must point to page locked memory
(i.e. to CudaMem data or to its ROI)
void enqueueUpload(const CudaMem& src, GpuMat& dst);
void enqueueUpload(const Mat& src, GpuMat& dst);
void enqueueCopy(const GpuMat& src, GpuMat& dst);
void enqueueMemSet(const GpuMat& src, Scalar val);
void enqueueMemSet(const GpuMat& src, Scalar val, const GpuMat& mask);
// converts matrix type, ex from float to uchar depending on type
void enqueueConvert(const GpuMat& src, GpuMat& dst, int type,
double a = 1, double b = 0);
};
..
.. index:: gpu::Stream::queryIfComplete
cv::gpu::Stream::queryIfComplete
--------------------------------
`id=0.136699172621 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStream%3A%3AqueryIfComplete>`__
.. cfunction:: bool Stream::queryIfComplete()
Returns true if the current stream queue is finished, otherwise false.
.. index:: gpu::Stream::waitForCompletion
cv::gpu::Stream::waitForCompletion
----------------------------------
`id=0.870172270785 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStream%3A%3AwaitForCompletion>`__
.. cfunction:: void Stream::waitForCompletion()
Blocks until all operations in the stream are complete.
.. index:: gpu::StreamAccessor
.. _gpu::StreamAccessor:
gpu::StreamAccessor
-------------------
`id=0.312772323299 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AStreamAccessor>`__
.. ctype:: gpu::StreamAccessor
This class provides possibility to get
``cudaStream_t``
from
:func:`gpu::Stream`
. This class is declared in
``stream_accessor.hpp``
because that is only public header that depend on Cuda Runtime API. Including it will bring the dependency to your code.
::
struct StreamAccessor
{
CV_EXPORTS static cudaStream_t getStream(const Stream& stream);
};
..
.. index:: gpu::createContinuous
cv::gpu::createContinuous
-------------------------
`id=0.638242088099 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AcreateContinuous>`__
.. cfunction:: void createContinuous(int rows, int cols, int type, GpuMat\& m)
Creates continuous matrix in GPU memory.
:param rows: Row count.
:param cols: Column count.
:param type: Type of the matrix.
:param m: Destination matrix. Will be only reshaped if it has proper type and area ( ``rows`` :math:`\times` ``cols`` ).
Also the following wrappers are available:
.. cfunction:: GpuMat createContinuous(int rows, int cols, int type)
.. cfunction:: void createContinuous(Size size, int type, GpuMat\& m)
.. cfunction:: GpuMat createContinuous(Size size, int type)
Matrix is called continuous if its elements are stored continuously, i.e. wuthout gaps in the end of each row.
.. index:: gpu::ensureSizeIsEnough
cv::gpu::ensureSizeIsEnough
---------------------------
`id=0.0969536734629 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AensureSizeIsEnough>`__
.. cfunction:: void ensureSizeIsEnough(int rows, int cols, int type, GpuMat\& m)
Ensures that size of matrix is big enough and matrix has proper type. The function doesn't reallocate memory if the matrix has proper attributes already.
:param rows: Minimum desired number of rows.
:param cols: Minimum desired number of cols.
:param type: Desired matrix type.
:param m: Destination matrix.
Also the following wrapper is available:
.. cfunction:: void ensureSizeIsEnough(Size size, int type, GpuMat\& m)

661
modules/gpu/doc/feature_detection_and_description.rst Normal file
View File

@ -0,0 +1,661 @@
Feature Detection and Description
=================================
.. highlight:: cpp
.. index:: gpu::SURF_GPU
.. _gpu::SURF_GPU:
gpu::SURF_GPU
-------------
`id=0.87802428318 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ASURF_GPU>`__
.. ctype:: gpu::SURF_GPU
Class for extracting Speeded Up Robust Features from an image.
::
class SURF_GPU : public SURFParams_GPU
{
public:
//! returns the descriptor size in float's (64 or 128)
int descriptorSize() const;
//! upload host keypoints to device memory
static void uploadKeypoints(const vector<KeyPoint>& keypoints,
GpuMat& keypointsGPU);
//! download keypoints from device to host memory
static void downloadKeypoints(const GpuMat& keypointsGPU,
vector<KeyPoint>& keypoints);
//! download descriptors from device to host memory
static void downloadDescriptors(const GpuMat& descriptorsGPU,
vector<float>& descriptors);
void operator()(const GpuMat& img, const GpuMat& mask,
GpuMat& keypoints);
void operator()(const GpuMat& img, const GpuMat& mask,
GpuMat& keypoints, GpuMat& descriptors,
bool useProvidedKeypoints = false,
bool calcOrientation = true);
void operator()(const GpuMat& img, const GpuMat& mask,
std::vector<KeyPoint>& keypoints);
void operator()(const GpuMat& img, const GpuMat& mask,
std::vector<KeyPoint>& keypoints, GpuMat& descriptors,
bool useProvidedKeypoints = false,
bool calcOrientation = true);
void operator()(const GpuMat& img, const GpuMat& mask,
std::vector<KeyPoint>& keypoints,
std::vector<float>& descriptors,
bool useProvidedKeypoints = false,
bool calcOrientation = true);
GpuMat sum;
GpuMat sumf;
GpuMat mask1;
GpuMat maskSum;
GpuMat hessianBuffer;
GpuMat maxPosBuffer;
GpuMat featuresBuffer;
};
..
The class
``SURF_GPU``
implements Speeded Up Robust Features descriptor. There is fast multi-scale Hessian keypoint detector that can be used to find the keypoints (which is the default option), but the descriptors can be also computed for the user-specified keypoints. Supports only 8 bit grayscale images.
The class
``SURF_GPU``
can store results to GPU and CPU memory and provides static functions to convert results between CPU and GPU version (
``uploadKeypoints``
,
``downloadKeypoints``
,
``downloadDescriptors``
). CPU results has the same format as
results. GPU results are stored to
``GpuMat``
.
``keypoints``
matrix is one row matrix with
``CV_32FC6``
type. It contains 6 float values per feature:
``x, y, size, response, angle, octave``
.
``descriptors``
matrix is
:math:`\texttt{nFeatures} \times \texttt{descriptorSize}`
matrix with
``CV_32FC1``
type.
The class
``SURF_GPU``
uses some buffers and provides access to it. All buffers can be safely released between function calls.
See also:
.
.. index:: gpu::BruteForceMatcher_GPU
.. _gpu::BruteForceMatcher_GPU:
gpu::BruteForceMatcher_GPU
--------------------------
`id=0.776429775465 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ABruteForceMatcher_GPU>`__
.. ctype:: gpu::BruteForceMatcher_GPU
Brute-force descriptor matcher. For each descriptor in the first set, this matcher finds the closest descriptor in the second set by trying each one. This descriptor matcher supports masking permissible matches between descriptor sets.
::
template<class Distance>
class BruteForceMatcher_GPU
{
public:
// Add descriptors to train descriptor collection.
void add(const std::vector<GpuMat>& descCollection);
// Get train descriptors collection.
const std::vector<GpuMat>& getTrainDescriptors() const;
// Clear train descriptors collection.
void clear();
// Return true if there are not train descriptors in collection.
bool empty() const;
// Return true if the matcher supports mask in match methods.
bool isMaskSupported() const;
void matchSingle(const GpuMat& queryDescs, const GpuMat& trainDescs,
GpuMat& trainIdx, GpuMat& distance,
const GpuMat& mask = GpuMat());
static void matchDownload(const GpuMat& trainIdx,
const GpuMat& distance, std::vector<DMatch>& matches);
void match(const GpuMat& queryDescs, const GpuMat& trainDescs,
std::vector<DMatch>& matches, const GpuMat& mask = GpuMat());
void makeGpuCollection(GpuMat& trainCollection, GpuMat& maskCollection,
const vector<GpuMat>& masks = std::vector<GpuMat>());
void matchCollection(const GpuMat& queryDescs,
const GpuMat& trainCollection,
GpuMat& trainIdx, GpuMat& imgIdx, GpuMat& distance,
const GpuMat& maskCollection);
static void matchDownload(const GpuMat& trainIdx, GpuMat& imgIdx,
const GpuMat& distance, std::vector<DMatch>& matches);
void match(const GpuMat& queryDescs, std::vector<DMatch>& matches,
const std::vector<GpuMat>& masks = std::vector<GpuMat>());
void knnMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
GpuMat& trainIdx, GpuMat& distance, GpuMat& allDist, int k,
const GpuMat& mask = GpuMat());
static void knnMatchDownload(const GpuMat& trainIdx,
const GpuMat& distance, std::vector< std::vector<DMatch> >& matches,
bool compactResult = false);
void knnMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
std::vector< std::vector<DMatch> >& matches, int k,
const GpuMat& mask = GpuMat(), bool compactResult = false);
void knnMatch(const GpuMat& queryDescs,
std::vector< std::vector<DMatch> >& matches, int knn,
const std::vector<GpuMat>& masks = std::vector<GpuMat>(),
bool compactResult = false );
void radiusMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
GpuMat& trainIdx, GpuMat& nMatches, GpuMat& distance,
float maxDistance, const GpuMat& mask = GpuMat());
static void radiusMatchDownload(const GpuMat& trainIdx,
const GpuMat& nMatches, const GpuMat& distance,
std::vector< std::vector<DMatch> >& matches,
bool compactResult = false);
void radiusMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
std::vector< std::vector<DMatch> >& matches, float maxDistance,
const GpuMat& mask = GpuMat(), bool compactResult = false);
void radiusMatch(const GpuMat& queryDescs,
std::vector< std::vector<DMatch> >& matches, float maxDistance,
const std::vector<GpuMat>& masks = std::vector<GpuMat>(),
bool compactResult = false);
private:
std::vector<GpuMat> trainDescCollection;
};
..
The class
``BruteForceMatcher_GPU``
has the similar interface to class
. It has two groups of match methods: for matching descriptors of one image with other image or with image set. Also all functions have alternative: save results to GPU memory or to CPU memory.
``Distance``
template parameter is kept for CPU/GPU interfaces similarity.
``BruteForceMatcher_GPU``
supports only
``L1<float>``
and
``L2<float>``
distance types.
See also:
,
.
.. index:: cv::gpu::BruteForceMatcher_GPU::match
.. _cv::gpu::BruteForceMatcher_GPU::match:
cv::gpu::BruteForceMatcher_GPU::match
-------------------------------------
`id=0.164151048457 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3Amatch>`__
.. cfunction:: void match(const GpuMat\& queryDescs, const GpuMat\& trainDescs, std::vector<DMatch>\& matches, const GpuMat\& mask = GpuMat())
.. cfunction:: void match(const GpuMat\& queryDescs, std::vector<DMatch>\& matches, const std::vector<GpuMat>\& masks = std::vector<GpuMat>())
Finds the best match for each descriptor from a query set with train descriptors.
See also:
:func:`DescriptorMatcher::match`
.
.. index:: cv::gpu::BruteForceMatcher_GPU::matchSingle
.. _cv::gpu::BruteForceMatcher_GPU::matchSingle:
cv::gpu::BruteForceMatcher_GPU::matchSingle
-------------------------------------------
`id=0.230978706047 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AmatchSingle>`__
.. cfunction:: void matchSingle(const GpuMat\& queryDescs, const GpuMat\& trainDescs, GpuMat\& trainIdx, GpuMat\& distance, const GpuMat\& mask = GpuMat())
Finds the best match for each query descriptor. Results will be stored to GPU memory.
{Query set of descriptors.}
{Train set of descriptors. This will not be added to train descriptors collection stored in class object.}
{One row
``CV_32SC1``
matrix. Will contain the best train index for each query. If some query descriptors are masked out in
``mask``
it will contain -1.}
{One row
``CV_32FC1``
matrix. Will contain the best distance for each query. If some query descriptors are masked out in
``mask``
it will contain
``FLT_MAX``
.}
:param mask: Mask specifying permissible matches between input query and train matrices of descriptors.
.. index:: cv::gpu::BruteForceMatcher_GPU::matchCollection
.. _cv::gpu::BruteForceMatcher_GPU::matchCollection:
cv::gpu::BruteForceMatcher_GPU::matchCollection
-----------------------------------------------
`id=0.934341769456 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AmatchCollection>`__
.. cfunction:: void matchCollection(const GpuMat\& queryDescs, const GpuMat\& trainCollection, GpuMat\& trainIdx, GpuMat\& imgIdx, GpuMat\& distance, const GpuMat\& maskCollection)
Find the best match for each query descriptor from train collection. Results will be stored to GPU memory.
{Query set of descriptors.}
{
``GpuMat``
containing train collection. It can be obtained from train descriptors collection that was set using
``add``
method by
. Or it can contain user defined collection. It must be one row matrix, each element is a
``DevMem2D``
that points to one train descriptors matrix.}
{One row
``CV_32SC1``
matrix. Will contain the best train index for each query. If some query descriptors are masked out in
``maskCollection``
it will contain -1.}
{One row
``CV_32SC1``
matrix. Will contain image train index for each query. If some query descriptors are masked out in
``maskCollection``
it will contain -1.}
{One row
``CV_32FC1``
matrix. Will contain the best distance for each query. If some query descriptors are masked out in
``maskCollection``
it will contain
``FLT_MAX``
.}
:param maskCollection: ``GpuMat`` containing set of masks. It can be obtained from ``std::vector<GpuMat>`` by . Or it can contain user defined mask set. It must be empty matrix or one row matrix, each element is a ``PtrStep`` that points to one mask.
.. index:: cv::gpu::BruteForceMatcher_GPU::makeGpuCollection
.. _cv::gpu::BruteForceMatcher_GPU::makeGpuCollection:
cv::gpu::BruteForceMatcher_GPU::makeGpuCollection
-------------------------------------------------
`id=0.285830043662 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AmakeGpuCollection>`__
.. cfunction:: void makeGpuCollection(GpuMat\& trainCollection, GpuMat\& maskCollection, const vector<GpuMat>\& masks = std::vector<GpuMat>())
Makes gpu collection of train descriptors and masks in suitable format for function.
.. index:: cv::gpu::BruteForceMatcher_GPU::matchDownload
.. _cv::gpu::BruteForceMatcher_GPU::matchDownload:
cv::gpu::BruteForceMatcher_GPU::matchDownload
---------------------------------------------
`id=0.171611509706 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AmatchDownload>`__
````
````
````
.. cfunction:: void matchDownload(const GpuMat\& trainIdx, const GpuMat\& distance, std::vector<DMatch>\& matches)
.. cfunction:: void matchDownload(const GpuMat\& trainIdx, GpuMat\& imgIdx, const GpuMat\& distance, std::vector<DMatch>\& matches)
Downloads trainIdx, imgIdxand distancematrices obtained via or to CPU vector with .
.. index:: cv::gpu::BruteForceMatcher_GPU::knnMatch
.. _cv::gpu::BruteForceMatcher_GPU::knnMatch:
cv::gpu::BruteForceMatcher_GPU::knnMatch
----------------------------------------
`id=0.619005099272 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AknnMatch>`__
.. cfunction:: void knnMatch(const GpuMat\& queryDescs, const GpuMat\& trainDescs, std::vector< std::vector<DMatch> >\& matches, int k, const GpuMat\& mask = GpuMat(), bool compactResult = false)
Finds the k best matches for each descriptor from a query set with train descriptors. Found k (or less if not possible) matches are returned in distance increasing order.
.. cfunction:: void knnMatch(const GpuMat\& queryDescs, std::vector< std::vector<DMatch> >\& matches, int k, const std::vector<GpuMat>\& masks = std::vector<GpuMat>(), bool compactResult = false )
See also:
:func:`DescriptorMatcher::knnMatch`
.
.. index:: cv::gpu::BruteForceMatcher_GPU::knnMatch
.. _cv::gpu::BruteForceMatcher_GPU::knnMatch:
cv::gpu::BruteForceMatcher_GPU::knnMatch
----------------------------------------
`id=0.852761934257 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AknnMatch>`__
.. cfunction:: void knnMatch(const GpuMat\& queryDescs, const GpuMat\& trainDescs, GpuMat\& trainIdx, GpuMat\& distance, GpuMat\& allDist, int k, const GpuMat\& mask = GpuMat())
Finds the k best matches for each descriptor from a query set with train descriptors. Found k (or less if not possible) matches are returned in distance increasing order. Results will be stored to GPU memory.
{Query set of descriptors.}
{Train set of descriptors. This will not be added to train descriptors collection stored in class object.}
{Matrix with
:math:`\texttt{nQueries} \times \texttt{k}`
size and
``CV_32SC1``
type.
``trainIdx.at<int>(queryIdx, i)``
will contain index of the i'th best trains. If some query descriptors are masked out in
``mask``
it will contain -1.}
{Matrix with
:math:`\texttt{nQuery} \times \texttt{k}`
and
``CV_32FC1``
type. Will contain distance for each query and the i'th best trains. If some query descriptors are masked out in
``mask``
it will contain
``FLT_MAX``
.}
{Buffer to store all distances between query descriptors and train descriptors. It will have
:math:`\texttt{nQuery} \times \texttt{nTrain}`
size and
``CV_32FC1``
type.
``allDist.at<float>(queryIdx, trainIdx)``
will contain
``FLT_MAX``
, if
``trainIdx``
is one from k best, otherwise it will contain distance between
``queryIdx``
and
``trainIdx``
descriptors.}
:param k: Number of the best matches will be found per each query descriptor (or less if it's not possible).
:param mask: Mask specifying permissible matches between input query and train matrices of descriptors.
.. index:: cv::gpu::BruteForceMatcher_GPU::knnMatchDownload
.. _cv::gpu::BruteForceMatcher_GPU::knnMatchDownload:
cv::gpu::BruteForceMatcher_GPU::knnMatchDownload
------------------------------------------------
`id=0.735745722087 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AknnMatchDownload>`__
````
````
````
````
.. cfunction:: void knnMatchDownload(const GpuMat\& trainIdx, const GpuMat\& distance, std::vector< std::vector<DMatch> >\& matches, bool compactResult = false)
Downloads trainIdxand distancematrices obtained via to CPU vector with . If compactResultis true matchesvector will not contain matches for fully masked out query descriptors.
.. index:: cv::gpu::BruteForceMatcher_GPU::radiusMatch
.. _cv::gpu::BruteForceMatcher_GPU::radiusMatch:
cv::gpu::BruteForceMatcher_GPU::radiusMatch
-------------------------------------------
`id=0.964758287221 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AradiusMatch>`__
.. cfunction:: void radiusMatch(const GpuMat\& queryDescs, const GpuMat\& trainDescs, std::vector< std::vector<DMatch> >\& matches, float maxDistance, const GpuMat\& mask = GpuMat(), bool compactResult = false)
Finds the best matches for each query descriptor which have distance less than given threshold. Found matches are returned in distance increasing order.
.. cfunction:: void radiusMatch(const GpuMat\& queryDescs, std::vector< std::vector<DMatch> >\& matches, float maxDistance, const std::vector<GpuMat>\& masks = std::vector<GpuMat>(), bool compactResult = false)
This function works only on devices with Compute Capability
:math:`>=`
1.1.
See also:
:func:`DescriptorMatcher::radiusMatch`
.
.. index:: cv::gpu::BruteForceMatcher_GPU::radiusMatch
.. _cv::gpu::BruteForceMatcher_GPU::radiusMatch:
cv::gpu::BruteForceMatcher_GPU::radiusMatch
-------------------------------------------
`id=0.499772925784 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AradiusMatch>`__
.. cfunction:: void radiusMatch(const GpuMat\& queryDescs, const GpuMat\& trainDescs, GpuMat\& trainIdx, GpuMat\& nMatches, GpuMat\& distance, float maxDistance, const GpuMat\& mask = GpuMat())
Finds the best matches for each query descriptor which have distance less than given threshold. Results will be stored to GPU memory.
{Query set of descriptors.}
{Train set of descriptors. This will not be added to train descriptors collection stored in class object.}
{
``trainIdx.at<int>(queryIdx, i)``
will contain i'th train index
``(i < min(nMatches.at<unsigned int>(0, queryIdx), trainIdx.cols)``
. If
``trainIdx``
is empty, it will be created with size
:math:`\texttt{nQuery} \times \texttt{nTrain}`
. Or it can be allocated by user (it must have
``nQuery``
rows and
``CV_32SC1``
type). Cols can be less than
``nTrain``
, but it can be that matcher won't find all matches, because it haven't enough memory to store results.}
{
``nMatches.at<unsigned int>(0, queryIdx)``
will contain matches count for
``queryIdx``
. Carefully,
``nMatches``
can be greater than
``trainIdx.cols``
- it means that matcher didn't find all matches, because it didn't have enough memory.}
{
``distance.at<int>(queryIdx, i)``
will contain i'th distance
``(i < min(nMatches.at<unsigned int>(0, queryIdx), trainIdx.cols)``
. If
``trainIdx``
is empty, it will be created with size
:math:`\texttt{nQuery} \times \texttt{nTrain}`
. Otherwise it must be also allocated by user (it must have the same size as
``trainIdx``
and
``CV_32FC1``
type).}
:param maxDistance: Distance threshold.
:param mask: Mask specifying permissible matches between input query and train matrices of descriptors.
In contrast to
results are not sorted by distance increasing order.
This function works only on devices with Compute Capability
:math:`>=`
1.1.
.. index:: cv::gpu::BruteForceMatcher_GPU::radiusMatchDownload
.. _cv::gpu::BruteForceMatcher_GPU::radiusMatchDownload:
cv::gpu::BruteForceMatcher_GPU::radiusMatchDownload
---------------------------------------------------
`id=0.627360663551 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ABruteForceMatcher_GPU%3A%3AradiusMatchDownload>`__
````
````
````
````
````
.. cfunction:: void radiusMatchDownload(const GpuMat\& trainIdx, const GpuMat\& nMatches, const GpuMat\& distance, std::vector< std::vector<DMatch> >\& matches, bool compactResult = false)
Downloads trainIdx, nMatchesand distancematrices obtained via to CPU vector with . If compactResultis true matchesvector will not contain matches for fully masked out query descriptors.

18
modules/gpu/doc/gpu.rst Normal file
View File

@ -0,0 +1,18 @@
*******************************
GPU-accelerated Computer Vision
*******************************
.. toctree::
:maxdepth: 2
gpu_gpu_module_introduction
gpu_initalization_and_information
gpu_data_structures
gpu_operations_on_matrices
gpu_per-element_operations.
gpu_image_processing
gpu_matrix_reductions
gpu_object_detection
gpu_feature_detection_and_description
gpu_image_filtering
gpu_camera_calibration_and_3d_reconstruction

1400
modules/gpu/doc/image_filtering.rst Normal file
View File

File diff suppressed because it is too large Load Diff

1254
modules/gpu/doc/image_processing.rst Normal file
View File

File diff suppressed because it is too large Load Diff

402
modules/gpu/doc/initalization_and_information.rst Normal file
View File

@ -0,0 +1,402 @@
Initalization and Information
=============================
.. highlight:: cpp
.. index:: gpu::getCudaEnabledDeviceCount
cv::gpu::getCudaEnabledDeviceCount
----------------------------------
`id=0.541856697999 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AgetCudaEnabledDeviceCount>`__
.. cfunction:: int getCudaEnabledDeviceCount()
Returns number of CUDA-enabled devices installed. It is to be used before any other GPU functions calls. If OpenCV is compiled without GPU support this function returns 0.
.. index:: gpu::setDevice
cv::gpu::setDevice
------------------
`id=0.817295536445 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AsetDevice>`__
.. cfunction:: void setDevice(int device)
Sets device and initializes it for the current thread. Call of this function can be omitted, but in this case a default device will be initialized on fist GPU usage.
:param device: index of GPU device in system starting with 0.
.. index:: gpu::getDevice
cv::gpu::getDevice
------------------
`id=0.908782607162 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AgetDevice>`__
.. cfunction:: int getDevice()
Returns the current device index, which was set by {gpu::getDevice} or initialized by default.
.. index:: gpu::GpuFeature
.. _gpu::GpuFeature:
gpu::GpuFeature
---------------
`id=0.185426029041 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AGpuFeature>`__
.. ctype:: gpu::GpuFeature
GPU compute features.
::
enum GpuFeature
{
COMPUTE_10, COMPUTE_11,
COMPUTE_12, COMPUTE_13,
COMPUTE_20, COMPUTE_21,
ATOMICS, NATIVE_DOUBLE
};
..
.. index:: gpu::DeviceInfo
.. _gpu::DeviceInfo:
gpu::DeviceInfo
---------------
`id=0.91098225386 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo>`__
.. ctype:: gpu::DeviceInfo
This class provides functionality for querying the specified GPU properties.
::
class CV_EXPORTS DeviceInfo
{
public:
DeviceInfo();
DeviceInfo(int device_id);
string name() const;
int majorVersion() const;
int minorVersion() const;
int multiProcessorCount() const;
size_t freeMemory() const;
size_t totalMemory() const;
bool supports(GpuFeature feature) const;
bool isCompatible() const;
};
..
.. index:: gpu::DeviceInfo::DeviceInfo
cv::gpu::DeviceInfo::DeviceInfo
-------------------------------
`id=0.971366637207 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3ADeviceInfo>`__
``_``
.. cfunction:: DeviceInfo::DeviceInfo()
.. cfunction:: DeviceInfo::DeviceInfo(int device_id)
Constructs DeviceInfo object for the specified device. If deviceidparameter is missed it constructs object for the current device.
:param device_id: Index of the GPU device in system starting with 0.
.. index:: gpu::DeviceInfo::name
cv::gpu::DeviceInfo::name
-------------------------
`id=0.472941921148 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3Aname>`__
.. cfunction:: string DeviceInfo::name()
Returns the device name.
.. index:: gpu::DeviceInfo::majorVersion
cv::gpu::DeviceInfo::majorVersion
---------------------------------
`id=0.982334984119 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AmajorVersion>`__
.. cfunction:: int DeviceInfo::majorVersion()
Returns the major compute capability version.
.. index:: gpu::DeviceInfo::minorVersion
cv::gpu::DeviceInfo::minorVersion
---------------------------------
`id=0.309433581176 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AminorVersion>`__
.. cfunction:: int DeviceInfo::minorVersion()
Returns the minor compute capability version.
.. index:: gpu::DeviceInfo::multiProcessorCount
cv::gpu::DeviceInfo::multiProcessorCount
----------------------------------------
`id=0.417609601388 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AmultiProcessorCount>`__
.. cfunction:: int DeviceInfo::multiProcessorCount()
Returns the number of streaming multiprocessors.
.. index:: gpu::DeviceInfo::freeMemory
cv::gpu::DeviceInfo::freeMemory
-------------------------------
`id=0.961189453269 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AfreeMemory>`__
.. cfunction:: size_t DeviceInfo::freeMemory()
Returns the amount of free memory in bytes.
.. index:: gpu::DeviceInfo::totalMemory
cv::gpu::DeviceInfo::totalMemory
--------------------------------
`id=0.884488673579 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AtotalMemory>`__
.. cfunction:: size_t DeviceInfo::totalMemory()
Returns the amount of total memory in bytes.
.. index:: gpu::DeviceInfo::supports
cv::gpu::DeviceInfo::supports
-----------------------------
`id=0.141435828088 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3Asupports>`__
.. cfunction:: bool DeviceInfo::supports(GpuFeature feature)
Returns true if the device has the given GPU feature, otherwise false.
:param feature: Feature to be checked. See .
.. index:: gpu::DeviceInfo::isCompatible
cv::gpu::DeviceInfo::isCompatible
---------------------------------
`id=0.564690282768 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ADeviceInfo%3A%3AisCompatible>`__
.. cfunction:: bool DeviceInfo::isCompatible()
Returns true if the GPU module can be run on the specified device, otherwise false.
.. index:: gpu::TargetArchs
.. _gpu::TargetArchs:
gpu::TargetArchs
----------------
`id=0.200853353999 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ATargetArchs>`__
.. ctype:: gpu::TargetArchs
This class provides functionality (as set of static methods) for checking which NVIDIA card architectures the GPU module was built for.
bigskip
The following method checks whether the module was built with the support of the given feature:
.. cfunction:: static bool builtWith(GpuFeature feature)
:param feature: Feature to be checked. See .
There are a set of methods for checking whether the module contains intermediate (PTX) or binary GPU code for the given architecture(s):
.. cfunction:: static bool has(int major, int minor)
.. cfunction:: static bool hasPtx(int major, int minor)
.. cfunction:: static bool hasBin(int major, int minor)
.. cfunction:: static bool hasEqualOrLessPtx(int major, int minor)
.. cfunction:: static bool hasEqualOrGreater(int major, int minor)
.. cfunction:: static bool hasEqualOrGreaterPtx(int major, int minor)
.. cfunction:: static bool hasEqualOrGreaterBin(int major, int minor)
* **major** Major compute capability version.
* **minor** Minor compute capability version.
According to the CUDA C Programming Guide Version 3.2: "PTX code produced for some specific compute capability can always be compiled to binary code of greater or equal compute capability".

122
modules/gpu/doc/introduction.rst Normal file
View File

@ -0,0 +1,122 @@
GPU module introduction
=======================
.. highlight:: cpp
General information
-------------------
The OpenCV GPU module is a set of classes and functions to utilize GPU computational capabilities. It is implemented using NVidia CUDA Runtime API, so only the NVidia GPUs are supported. It includes utility functions, low-level vision primitives as well as high-level algorithms. The utility functions and low-level primitives provide a powerful infrastructure for developing fast vision algorithms taking advantage of GPU. Whereas the high-level functionality includes some state-of-the-art algorithms (such as stereo correspondence, face and people detectors etc.), ready to be used by the application developers.
The GPU module is designed as host-level API, i.e. if a user has pre-compiled OpenCV GPU binaries, it is not necessary to have Cuda Toolkit installed or write any extra code to make use of the GPU.
The GPU module depends on the Cuda Toolkit and NVidia Performance Primitives library (NPP). Make sure you have the latest versions of those. The two libraries can be downloaded from NVidia site for all supported platforms. To compile OpenCV GPU module you will need a compiler compatible with Cuda Runtime Toolkit.
OpenCV GPU module is designed for ease of use and does not require any knowledge of Cuda. Though, such a knowledge will certainly be useful in non-trivial cases, or when you want to get the highest performance. It is helpful to have understanding of the costs of various operations, what the GPU does, what are the preferred data formats etc. The GPU module is an effective instrument for quick implementation of GPU-accelerated computer vision algorithms. However, if you algorithm involves many simple operations, then for the best possible performance you may still need to write your own kernels, to avoid extra write and read operations on the intermediate results.
To enable CUDA support, configure OpenCV using CMake with
``WITH_CUDA=ON``
. When the flag is set and if CUDA is installed, the full-featured OpenCV GPU module will be built. Otherwise, the module will still be built, but at runtime all functions from the module will throw
:func:`Exception`
with
``CV_GpuNotSupported``
error code, except for
:func:`gpu::getCudaEnabledDeviceCount()`
. The latter function will return zero GPU count in this case. Building OpenCV without CUDA support does not perform device code compilation, so it does not require Cuda Toolkit installed. Therefore, using
:func:`gpu::getCudaEnabledDeviceCount()`
function it is possible to implement a high-level algorithm that will detect GPU presence at runtime and choose the appropriate implementation (CPU or GPU) accordingly.
Compilation for different NVidia platforms.
-------------------------------------------
NVidia compiler allows generating binary code (cubin and fatbin) and intermediate code (PTX). Binary code often implies a specific GPU architecture and generation, so the compatibility with other GPUs is not guaranteed. PTX is targeted for a virtual platform, which is defined entirely by the set of capabilities, or features. Depending on the virtual platform chosen, some of the instructions will be emulated or disabled, even if the real hardware supports all the features.
On first call, the PTX code is compiled to binary code for the particular GPU using JIT compiler. When the target GPU has lower "compute capability" (CC) than the PTX code, JIT fails.
By default, the OpenCV GPU module includes:
*
Binaries for compute capabilities 1.3 and 2.0 (controlled by
``CUDA_ARCH_BIN``
in CMake)
*
PTX code for compute capabilities 1.1 and 1.3 (controlled by
``CUDA_ARCH_PTX``
in CMake)
That means for devices with CC 1.3 and 2.0 binary images are ready to run. For all newer platforms the PTX code for 1.3 is JIT'ed to a binary image. For devices with 1.1 and 1.2 the PTX for 1.1 is JIT'ed. For devices with CC 1.0 no code is available and the functions will throw
:func:`Exception`
. For platforms where JIT compilation is performed first run will be slow.
If you happen to have GPU with CC 1.0, the GPU module can still be compiled on it and most of the functions will run just fine on such card. Simply add "1.0" to the list of binaries, for example,
``CUDA_ARCH_BIN="1.0 1.3 2.0"``
. The functions that can not be run on CC 1.0 GPUs will throw an exception.
You can always determine at runtime whether OpenCV GPU built binaries (or PTX code) are compatible with your GPU. The function
:func:`gpu::DeviceInfo::isCompatible`
return the compatibility status (true/false).
Threading and multi-threading.
------------------------------
OpenCV GPU module follows Cuda Runtime API conventions regarding the multi-threaded programming. That is, on first the API call a Cuda context is created implicitly, attached to the current CPU thread and then is used as the thread's "current" context. All further operations, such as memory allocation, GPU code compilation, will be associated with the context and the thread. Because any other thread is not attached to the context, memory (and other resources) allocated in the first thread can not be accessed by the other thread. Instead, for this other thread Cuda will create another context associated with it. In short, by default different threads do not share resources.
But such limitation can be removed using Cuda Driver API (version 3.1 or later). User can retrieve context reference for one thread, attach it to another thread and make it "current" for that thread. Then the threads can share memory and other resources. It is also possible to create a context explicitly before calling any GPU code and attach it to all the threads that you want to share the resources.
Also it is possible to create context explicitly using Cuda Driver API, attach and make "current" for all necessary threads. Cuda Runtime API (and OpenCV functions respectively) will pick up it.
Multi-GPU
---------
In the current version each of the OpenCV GPU algorithms can use only a single GPU. So, to utilize multiple GPUs, user has to manually distribute the work between the GPUs. Here are the two ways of utilizing multiple GPUs:
*
If you only use synchronous functions, first, create several CPU threads (one per each GPU) and from within each thread create CUDA context for the corresponding GPU using
:func:`gpu::setDevice()`
or Driver API. That's it. Now each of the threads will use the associated GPU.
*
In case of asynchronous functions, it is possible to create several Cuda contexts associated with different GPUs but attached to one CPU thread. This can be done only by Driver API. Within the thread you can switch from one GPU to another by making the corresponding context "current". With non-blocking GPU calls managing algorithm is clear.
While developing algorithms for multiple GPUs a data passing overhead have to be taken into consideration. For primitive functions and for small images it can be significant and eliminate all the advantages of having multiple GPUs. But for high level algorithms Multi-GPU acceleration may be suitable. For example, Stereo Block Matching algorithm has been successfully parallelized using the following algorithm:
*
Each image of the stereo pair is split into two horizontal overlapping stripes.
*
Each pair of stripes (from the left and the right images) has been processed on a separate Fermi GPU
*
The results are merged into the single disparity map.
With this scheme dual GPU gave 180
%
performance increase comparing to the single Fermi GPU. The source code of the example is available at
https://code.ros.org/svn/opencv/trunk/opencv/examples/gpu/

366
modules/gpu/doc/matrix_reductions.rst Normal file
View File

@ -0,0 +1,366 @@
Matrix Reductions
=================
.. highlight:: cpp
.. index:: gpu::meanStdDev
cv::gpu::meanStdDev
-------------------
`id=0.607789005794 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AmeanStdDev>`__
.. cfunction:: void meanStdDev(const GpuMat\& mtx, Scalar\& mean, Scalar\& stddev)
Computes mean value and standard deviation of matrix elements.
:param mtx: Source matrix. ``CV_8UC1`` matrices are supported for now.
:param mean: Mean value.
:param stddev: Standard deviation value.
See also:
:func:`meanStdDev`
.
.. index:: gpu::norm
cv::gpu::norm
-------------
`id=0.423726153071 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Anorm>`__
.. cfunction:: double norm(const GpuMat\& src, int normType=NORM_L2)
Returns norm of matrix (or of two matrices difference).
:param src: Source matrix. Any matrices except 64F are supported.
:param normType: Norm type. ``NORM_L1`` , ``NORM_L2`` and ``NORM_INF`` are supported for now.
.. cfunction:: double norm(const GpuMat\& src, int normType, GpuMat\& buf)
* **src** Source matrix. Any matrices except 64F are supported.
* **normType** Norm type. ``NORM_L1`` , ``NORM_L2`` and ``NORM_INF`` are supported for now.
* **buf** Optional buffer to avoid extra memory allocations. It's resized automatically.
.. cfunction:: double norm(const GpuMat\& src1, const GpuMat\& src2, int normType=NORM_L2)
* **src1** First source matrix. ``CV_8UC1`` matrices are supported for now.
* **src2** Second source matrix. Must have the same size and type as ``src1``
.
* **normType** Norm type. ``NORM_L1`` , ``NORM_L2`` and ``NORM_INF`` are supported for now.
See also:
:func:`norm`
.
.. index:: gpu::sum
cv::gpu::sum
------------
`id=0.979123982078 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Asum>`__
.. cfunction:: Scalar sum(const GpuMat\& src)
.. cfunction:: Scalar sum(const GpuMat\& src, GpuMat\& buf)
Returns sum of matrix elements.
:param src: Source image of any depth except ``CV_64F`` .
:param buf: Optional buffer to avoid extra memory allocations. It's resized automatically.
See also:
:func:`sum`
.
.. index:: gpu::absSum
cv::gpu::absSum
---------------
`id=0.607738316178 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AabsSum>`__
.. cfunction:: Scalar absSum(const GpuMat\& src)
.. cfunction:: Scalar absSum(const GpuMat\& src, GpuMat\& buf)
Returns sum of matrix elements absolute values.
:param src: Source image of any depth except ``CV_64F`` .
:param buf: Optional buffer to avoid extra memory allocations. It's resized automatically.
.. index:: gpu::sqrSum
cv::gpu::sqrSum
---------------
`id=0.470934615291 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AsqrSum>`__
.. cfunction:: Scalar sqrSum(const GpuMat\& src)
.. cfunction:: Scalar sqrSum(const GpuMat\& src, GpuMat\& buf)
Returns squared sum of matrix elements.
:param src: Source image of any depth except ``CV_64F`` .
:param buf: Optional buffer to avoid extra memory allocations. It's resized automatically.
.. index:: gpu::minMax
cv::gpu::minMax
---------------
`id=0.0207742957447 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AminMax>`__
.. cfunction:: void minMax(const GpuMat\& src, double* minVal, double* maxVal=0, const GpuMat\& mask=GpuMat())
.. cfunction:: void minMax(const GpuMat\& src, double* minVal, double* maxVal, const GpuMat\& mask, GpuMat\& buf)
Finds global minimum and maximum matrix elements and returns their values.
:param src: Single-channel source image.
:param minVal: Pointer to returned minimum value. ``NULL`` if not required.
:param maxVal: Pointer to returned maximum value. ``NULL`` if not required.
:param mask: Optional mask to select a sub-matrix.
:param buf: Optional buffer to avoid extra memory allocations. It's resized automatically.
Function doesn't work with
``CV_64F``
images on GPU with compute capability
:math:`<`
1.3.
See also:
:func:`minMaxLoc`
.
.. index:: gpu::minMaxLoc
cv::gpu::minMaxLoc
------------------
`id=0.985111829483 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AminMaxLoc>`__
.. cfunction:: void minMaxLoc(const GpuMat\& src, double\* minVal, double* maxVal=0, Point* minLoc=0, Point* maxLoc=0, const GpuMat\& mask=GpuMat())
.. cfunction:: void minMaxLoc(const GpuMat\& src, double* minVal, double* maxVal, Point* minLoc, Point* maxLoc, const GpuMat\& mask, GpuMat\& valbuf, GpuMat\& locbuf)
Finds global minimum and maximum matrix elements and returns their values with locations.
:param src: Single-channel source image.
:param minVal: Pointer to returned minimum value. ``NULL`` if not required.
:param maxVal: Pointer to returned maximum value. ``NULL`` if not required.
:param minValLoc: Pointer to returned minimum location. ``NULL`` if not required.
:param maxValLoc: Pointer to returned maximum location. ``NULL`` if not required.
:param mask: Optional mask to select a sub-matrix.
:param valbuf: Optional values buffer to avoid extra memory allocations. It's resized automatically.
:param locbuf: Optional locations buffer to avoid extra memory allocations. It's resized automatically.
Function doesn't work with
``CV_64F``
images on GPU with compute capability
:math:`<`
1.3.
See also:
:func:`minMaxLoc`
.
.. index:: gpu::countNonZero
cv::gpu::countNonZero
---------------------
`id=0.904273321304 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AcountNonZero>`__
.. cfunction:: int countNonZero(const GpuMat\& src)
.. cfunction:: int countNonZero(const GpuMat\& src, GpuMat\& buf)
Counts non-zero matrix elements.
:param src: Single-channel source image.
:param buf: Optional buffer to avoid extra memory allocations. It's resized automatically.
Function doesn't work with
``CV_64F``
images on GPU with compute capability
:math:`<`
1.3.
See also:
:func:`countNonZero`
.

575
modules/gpu/doc/object_detection.rst Normal file
View File

@ -0,0 +1,575 @@
Object Detection
================
.. highlight:: cpp
.. index:: gpu::HOGDescriptor
.. _gpu::HOGDescriptor:
gpu::HOGDescriptor
------------------
`id=0.263285034412 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor>`__
.. ctype:: gpu::HOGDescriptor
Histogram of Oriented Gradients
dalal_hog
descriptor and detector.
::
struct CV_EXPORTS HOGDescriptor
{
enum { DEFAULT_WIN_SIGMA = -1 };
enum { DEFAULT_NLEVELS = 64 };
enum { DESCR_FORMAT_ROW_BY_ROW, DESCR_FORMAT_COL_BY_COL };
HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16),
Size block_stride=Size(8, 8), Size cell_size=Size(8, 8),
int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA,
double threshold_L2hys=0.2, bool gamma_correction=true,
int nlevels=DEFAULT_NLEVELS);
size_t getDescriptorSize() const;
size_t getBlockHistogramSize() const;
void setSVMDetector(const vector<float>& detector);
static vector<float> getDefaultPeopleDetector();
static vector<float> getPeopleDetector48x96();
static vector<float> getPeopleDetector64x128();
void detect(const GpuMat& img, vector<Point>& found_locations,
double hit_threshold=0, Size win_stride=Size(),
Size padding=Size());
void detectMultiScale(const GpuMat& img, vector<Rect>& found_locations,
double hit_threshold=0, Size win_stride=Size(),
Size padding=Size(), double scale0=1.05,
int group_threshold=2);
void getDescriptors(const GpuMat& img, Size win_stride,
GpuMat& descriptors,
int descr_format=DESCR_FORMAT_COL_BY_COL);
Size win_size;
Size block_size;
Size block_stride;
Size cell_size;
int nbins;
double win_sigma;
double threshold_L2hys;
bool gamma_correction;
int nlevels;
private:
// Hidden
}
..
Interfaces of all methods are kept similar to CPU HOG descriptor and detector analogues as much as possible.
.. index:: gpu::HOGDescriptor::HOGDescriptor
cv::gpu::HOGDescriptor::HOGDescriptor
-------------------------------------
`id=0.377426649644 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AHOGDescriptor>`__
.. cfunction:: HOGDescriptor::HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16), Size block_stride=Size(8, 8), Size cell_size=Size(8, 8), int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA, double threshold_L2hys=0.2, bool gamma_correction=true, int nlevels=DEFAULT_NLEVELS)
Creates HOG descriptor and detector.
:param win_size: Detection window size. Must be aligned to block size and block stride.
:param block_size: Block size in pixels. Must be aligned to cell size. Only (16,16) is supported for now.
:param block_stride: Block stride. Must be a multiple of cell size.
:param cell_size: Cell size. Only (8, 8) is supported for now.
:param nbins: Number of bins. Only 9 bins per cell is supported for now.
:param win_sigma: Gaussian smoothing window parameter.
:param threshold_L2Hys: L2-Hys normalization method shrinkage.
:param gamma_correction: Do gamma correction preprocessing or not.
:param nlevels: Maximum number of detection window increases.
.. index:: gpu::HOGDescriptor::getDescriptorSize
cv::gpu::HOGDescriptor::getDescriptorSize
-----------------------------------------
`id=0.25703536307 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetDescriptorSize>`__
.. cfunction:: size_t HOGDescriptor::getDescriptorSize() const
Returns number of coefficients required for the classification.
.. index:: gpu::HOGDescriptor::getBlockHistogramSize
cv::gpu::HOGDescriptor::getBlockHistogramSize
---------------------------------------------
`id=0.91431196569 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetBlockHistogramSize>`__
.. cfunction:: size_t HOGDescriptor::getBlockHistogramSize() const
Returns block histogram size.
.. index:: gpu::HOGDescriptor::setSVMDetector
cv::gpu::HOGDescriptor::setSVMDetector
--------------------------------------
`id=0.719708439759 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AsetSVMDetector>`__
.. cfunction:: void HOGDescriptor::setSVMDetector(const vector<float>\& detector)
Sets coefficients for the linear SVM classifier.
.. index:: gpu::HOGDescriptor::getDefaultPeopleDetector
cv::gpu::HOGDescriptor::getDefaultPeopleDetector
------------------------------------------------
`id=0.941470897866 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetDefaultPeopleDetector>`__
.. cfunction:: static vector<float> HOGDescriptor::getDefaultPeopleDetector()
Returns coefficients of the classifier trained for people detection (for default window size).
.. index:: gpu::HOGDescriptor::getPeopleDetector48x96
cv::gpu::HOGDescriptor::getPeopleDetector48x96
----------------------------------------------
`id=0.600273723778 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetPeopleDetector48x96>`__
.. cfunction:: static vector<float> HOGDescriptor::getPeopleDetector48x96()
Returns coefficients of the classifier trained for people detection (for 48x96 windows).
.. index:: gpu::HOGDescriptor::getPeopleDetector64x128
cv::gpu::HOGDescriptor::getPeopleDetector64x128
-----------------------------------------------
`id=0.583356812364 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetPeopleDetector64x128>`__
.. cfunction:: static vector<float> HOGDescriptor::getPeopleDetector64x128()
Returns coefficients of the classifier trained for people detection (for 64x128 windows).
.. index:: gpu::HOGDescriptor::detect
cv::gpu::HOGDescriptor::detect
------------------------------
`id=0.0364241115122 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3Adetect>`__
.. cfunction:: void HOGDescriptor::detect(const GpuMat\& img, vector<Point>\& found_locations, double hit_threshold=0, Size win_stride=Size(), Size padding=Size())
Perfroms object detection without multiscale window.
:param img: Source image. ``CV_8UC1`` and ``CV_8UC4`` types are supported for now.
:param found_locations: Will contain left-top corner points of detected objects boundaries.
:param hit_threshold: Threshold for the distance between features and SVM classifying plane. Usually it's 0 and should be specfied in the detector coefficients (as the last free coefficient), but if the free coefficient is omitted (it's allowed) you can specify it manually here.
:param win_stride: Window stride. Must be a multiple of block stride.
:param padding: Mock parameter to keep CPU interface compatibility. Must be (0,0).
.. index:: gpu::HOGDescriptor::detectMultiScale
cv::gpu::HOGDescriptor::detectMultiScale
----------------------------------------
`id=0.125190830083 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AdetectMultiScale>`__
.. cfunction:: void HOGDescriptor::detectMultiScale(const GpuMat\& img, vector<Rect>\& found_locations, double hit_threshold=0, Size win_stride=Size(), Size padding=Size(), double scale0=1.05, int group_threshold=2)
Perfroms object detection with multiscale window.
:param img: Source image. See :func:`gpu::HOGDescriptor::detect` for type limitations.
:param found_locations: Will contain detected objects boundaries.
:param hit_threshold: The threshold for the distance between features and SVM classifying plane. See :func:`gpu::HOGDescriptor::detect` for details.
:param win_stride: Window stride. Must be a multiple of block stride.
:param padding: Mock parameter to keep CPU interface compatibility. Must be (0,0).
:param scale0: Coefficient of the detection window increase.
:param group_threshold: After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping.
See :func:`groupRectangles` .
.. index:: gpu::HOGDescriptor::getDescriptors
cv::gpu::HOGDescriptor::getDescriptors
--------------------------------------
`id=0.128234884479 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AHOGDescriptor%3A%3AgetDescriptors>`__
.. cfunction:: void HOGDescriptor::getDescriptors(const GpuMat\& img, Size win_stride, GpuMat\& descriptors, int descr_format=DESCR_FORMAT_COL_BY_COL)
Returns block descriptors computed for the whole image. It's mainly used for classifier learning purposes.
:param img: Source image. See :func:`gpu::HOGDescriptor::detect` for type limitations.
:param win_stride: Window stride. Must be a multiple of block stride.
:param descriptors: 2D array of descriptors.
:param descr_format: Descriptor storage format:
* **DESCR_FORMAT_ROW_BY_ROW** Row-major order.
* **DESCR_FORMAT_COL_BY_COL** Column-major order.
.. index:: gpu::CascadeClassifier_GPU
.. _gpu::CascadeClassifier_GPU:
gpu::CascadeClassifier_GPU
--------------------------
`id=0.362290729184 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ACascadeClassifier_GPU>`__
.. ctype:: gpu::CascadeClassifier_GPU
The cascade classifier class for object detection.
::
class CV_EXPORTS CascadeClassifier_GPU
{
public:
CascadeClassifier_GPU();
CascadeClassifier_GPU(const string& filename);
~CascadeClassifier_GPU();
bool empty() const;
bool load(const string& filename);
void release();
/* returns number of detected objects */
int detectMultiScale( const GpuMat& image, GpuMat& objectsBuf, double scaleFactor=1.2, int minNeighbors=4, Size minSize=Size());
/* Finds only the largest object. Special mode for need to training*/
bool findLargestObject;
/* Draws rectangles in input image */
bool visualizeInPlace;
Size getClassifierSize() const;
};
..
.. index:: cv::gpu::CascadeClassifier_GPU::CascadeClassifier_GPU
.. _cv::gpu::CascadeClassifier_GPU::CascadeClassifier_GPU:
cv::gpu::CascadeClassifier_GPU::CascadeClassifier_GPU
-----------------------------------------------------
`id=0.502164537388 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ACascadeClassifier_GPU%3A%3ACascadeClassifier_GPU>`__
.. cfunction:: cv::CascadeClassifier_GPU(const string\& filename)
Loads the classifier from file.
:param filename: Name of file from which classifier will be load. Only old haar classifier (trained by haartraining application) and NVidia's nvbin are supported.
.. index:: cv::gpu::CascadeClassifier_GPU::empty
.. _cv::gpu::CascadeClassifier_GPU::empty:
cv::gpu::CascadeClassifier_GPU::empty
-------------------------------------
`id=0.00879679914574 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ACascadeClassifier_GPU%3A%3Aempty>`__
.. cfunction:: bool CascadeClassifier_GPU::empty() const
Checks if the classifier has been loaded or not.
.. index:: cv::gpu::CascadeClassifier_GPU::load
.. _cv::gpu::CascadeClassifier_GPU::load:
cv::gpu::CascadeClassifier_GPU::load
------------------------------------
`id=0.831994730738 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ACascadeClassifier_GPU%3A%3Aload>`__
.. cfunction:: bool CascadeClassifier_GPU::load(const string\& filename)
Loads the classifier from file. The previous content is destroyed.
:param filename: Name of file from which classifier will be load. Only old haar classifier (trained by haartraining application) and NVidia's nvbin are supported.
.. index:: cv::gpu::CascadeClassifier_GPU::release
.. _cv::gpu::CascadeClassifier_GPU::release:
cv::gpu::CascadeClassifier_GPU::release
---------------------------------------
`id=0.524456582811 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ACascadeClassifier_GPU%3A%3Arelease>`__
.. cfunction:: void CascadeClassifier_GPU::release()
Destroys loaded classifier.
.. index:: cv::gpu::CascadeClassifier_GPU::detectMultiScale
.. _cv::gpu::CascadeClassifier_GPU::detectMultiScale:
cv::gpu::CascadeClassifier_GPU::detectMultiScale
------------------------------------------------
`id=0.0605957110589 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3ACascadeClassifier_GPU%3A%3AdetectMultiScale>`__
.. cfunction:: int CascadeClassifier_GPU::detectMultiScale(const GpuMat\& image, GpuMat\& objectsBuf, double scaleFactor=1.2, int minNeighbors=4, Size minSize=Size())
Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.
:param image: Matrix of type ``CV_8U`` containing the image in which to detect objects.
:param objects: Buffer to store detected objects (rectangles). If it is empty, it will be allocated with default size. If not empty, function will search not more than N objects, where N = sizeof(objectsBufer's data)/sizeof(cv::Rect).
:param scaleFactor: Specifies how much the image size is reduced at each image scale.
:param minNeighbors: Specifies how many neighbors should each candidate rectangle have to retain it.
:param minSize: The minimum possible object size. Objects smaller than that are ignored.
The function returns number of detected objects, so you can retrieve them as in following example:
::
cv::gpu::CascadeClassifier_GPU cascade_gpu(...);
Mat image_cpu = imread(...)
GpuMat image_gpu(image_cpu);
GpuMat objbuf;
int detections_number = cascade_gpu.detectMultiScale( image_gpu,
objbuf, 1.2, minNeighbors);
Mat obj_host;
// download only detected number of rectangles
objbuf.colRange(0, detections_number).download(obj_host);
Rect* faces = obj_host.ptr<Rect>();
for(int i = 0; i < detections_num; ++i)
cv::rectangle(image_cpu, faces[i], Scalar(255));
imshow("Faces", image_cpu);
..
See also:
:func:`CascadeClassifier::detectMultiScale`
.

509
modules/gpu/doc/operations_on_matrices.rst Normal file
View File

@ -0,0 +1,509 @@
Operations on Matrices
======================
.. highlight:: cpp
.. index:: gpu::transpose
cv::gpu::transpose
------------------
`id=0.581518039061 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Atranspose>`__
.. cfunction:: void transpose(const GpuMat\& src, GpuMat\& dst)
Transposes a matrix.
:param src: Source matrix. 1, 4, 8 bytes element sizes are supported for now.
:param dst: Destination matrix.
See also:
:func:`transpose`
.
.. index:: gpu::flip
cv::gpu::flip
-------------
`id=0.29725445638 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Aflip>`__
.. cfunction:: void flip(const GpuMat\& a, GpuMat\& b, int flipCode)
Flips a 2D matrix around vertical, horizontal or both axes.
:param a: Source matrix. Only ``CV_8UC1`` and ``CV_8UC4`` matrices are supported for now.
:param b: Destination matrix.
:param flipCode: Specifies how to flip the source:
* **0** Flip around x-axis.
* **:math:`>`0** Flip around y-axis.
* **:math:`<`0** Flip around both axes.
See also:
:func:`flip`
.
.. index:: gpu::LUT
cv::gpu::LUT
------------
`id=0.279602538414 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ALUT>`__
.. math::
dst(I) = lut(src(I))
.. cfunction:: void LUT(const GpuMat\& src, const Mat\& lut, GpuMat\& dst)
Transforms the source matrix into the destination matrix using given look-up table:
:param src: Source matrix. ``CV_8UC1`` and ``CV_8UC3`` matrixes are supported for now.
:param lut: Look-up table. Must be continuous, ``CV_8U`` depth matrix. Its area must satisfy to ``lut.rows`` :math:`\times` ``lut.cols`` = 256 condition.
:param dst: Destination matrix. Will have the same depth as ``lut`` and the same number of channels as ``src`` .
See also:
:func:`LUT`
.
.. index:: gpu::merge
cv::gpu::merge
--------------
`id=0.568969773318 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Amerge>`__
.. cfunction:: void merge(const GpuMat* src, size_t n, GpuMat\& dst)
.. cfunction:: void merge(const GpuMat* src, size_t n, GpuMat\& dst, const Stream\& stream)
Makes a multi-channel matrix out of several single-channel matrices.
:param src: Pointer to array of the source matrices.
:param n: Number of source matrices.
:param dst: Destination matrix.
:param stream: Stream for the asynchronous version.
.. cfunction:: void merge(const vector$<$GpuMat$>$\& src, GpuMat\& dst)
.. cfunction:: void merge(const vector$<$GpuMat$>$\& src, GpuMat\& dst, const Stream\& stream)
* **src** Vector of the source matrices.
* **dst** Destination matrix.
* **stream** Stream for the asynchronous version.
See also:
:func:`merge`
.
.. index:: gpu::split
cv::gpu::split
--------------
`id=0.117653518739 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Asplit>`__
.. cfunction:: void split(const GpuMat\& src, GpuMat* dst)
.. cfunction:: void split(const GpuMat\& src, GpuMat* dst, const Stream\& stream)
Copies each plane of a multi-channel matrix into an array.
:param src: Source matrix.
:param dst: Pointer to array of single-channel matrices.
:param stream: Stream for the asynchronous version.
.. cfunction:: void split(const GpuMat\& src, vector$<$GpuMat$>$\& dst)
.. cfunction:: void split(const GpuMat\& src, vector$<$GpuMat$>$\& dst, const Stream\& stream)
* **src** Source matrix.
* **dst** Destination vector of single-channel matrices.
* **stream** Stream for the asynchronous version.
See also:
:func:`split`
.
.. index:: gpu::magnitude
cv::gpu::magnitude
------------------
`id=0.0879492693083 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Amagnitude>`__
.. cfunction:: void magnitude(const GpuMat\& x, GpuMat\& magnitude)
Computes magnitudes of complex matrix elements.
:param x: Source complex matrix in the interleaved format ( ``CV_32FC2`` ).
:param magnitude: Destination matrix of float magnitudes ( ``CV_32FC1`` ).
.. cfunction:: void magnitude(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude)
.. cfunction:: void magnitude(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude, const Stream\& stream)
* **x** Source matrix, containing real components ( ``CV_32FC1`` ).
* **y** Source matrix, containing imaginary components ( ``CV_32FC1`` ).
* **magnitude** Destination matrix of float magnitudes ( ``CV_32FC1`` ).
* **stream** Stream for the asynchronous version.
See also:
:func:`magnitude`
.
.. index:: gpu::magnitudeSqr
cv::gpu::magnitudeSqr
---------------------
`id=0.0350196817871 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AmagnitudeSqr>`__
.. cfunction:: void magnitudeSqr(const GpuMat\& x, GpuMat\& magnitude)
Computes squared magnitudes of complex matrix elements.
:param x: Source complex matrix in the interleaved format ( ``CV_32FC2`` ).
:param magnitude: Destination matrix of float magnitude squares ( ``CV_32FC1`` ).
.. cfunction:: void magnitudeSqr(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude)
.. cfunction:: void magnitudeSqr(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude, const Stream\& stream)
* **x** Source matrix, containing real components ( ``CV_32FC1`` ).
* **y** Source matrix, containing imaginary components ( ``CV_32FC1`` ).
* **magnitude** Destination matrix of float magnitude squares ( ``CV_32FC1`` ).
* **stream** Stream for the asynchronous version.
.. index:: gpu::phase
cv::gpu::phase
--------------
`id=0.274224468378 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Aphase>`__
.. cfunction:: void phase(const GpuMat\& x, const GpuMat\& y, GpuMat\& angle, bool angleInDegrees=false)
.. cfunction:: void phase(const GpuMat\& x, const GpuMat\& y, GpuMat\& angle, bool angleInDegrees, const Stream\& stream)
Computes polar angles of complex matrix elements.
:param x: Source matrix, containing real components ( ``CV_32FC1`` ).
:param y: Source matrix, containing imaginary components ( ``CV_32FC1`` ).
:param angle: Destionation matrix of angles ( ``CV_32FC1`` ).
:param angleInDegress: Flag which indicates angles must be evaluated in degress.
:param stream: Stream for the asynchronous version.
See also:
:func:`phase`
.
.. index:: gpu::cartToPolar
cv::gpu::cartToPolar
--------------------
`id=0.813292348151 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3AcartToPolar>`__
.. cfunction:: void cartToPolar(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude, GpuMat\& angle, bool angleInDegrees=false)
.. cfunction:: void cartToPolar(const GpuMat\& x, const GpuMat\& y, GpuMat\& magnitude, GpuMat\& angle, bool angleInDegrees, const Stream\& stream)
Converts Cartesian coordinates into polar.
:param x: Source matrix, containing real components ( ``CV_32FC1`` ).
:param y: Source matrix, containing imaginary components ( ``CV_32FC1`` ).
:param magnitude: Destination matrix of float magnituds ( ``CV_32FC1`` ).
:param angle: Destionation matrix of angles ( ``CV_32FC1`` ).
:param angleInDegress: Flag which indicates angles must be evaluated in degress.
:param stream: Stream for the asynchronous version.
See also:
:func:`cartToPolar`
.
.. index:: gpu::polarToCart
cv::gpu::polarToCart
--------------------
`id=0.108746506092 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3ApolarToCart>`__
.. cfunction:: void polarToCart(const GpuMat\& magnitude, const GpuMat\& angle, GpuMat\& x, GpuMat\& y, bool angleInDegrees=false)
.. cfunction:: void polarToCart(const GpuMat\& magnitude, const GpuMat\& angle, GpuMat\& x, GpuMat\& y, bool angleInDegrees, const Stream\& stream)
Converts polar coordinates into Cartesian.
:param magnitude: Source matrix, containing magnitudes ( ``CV_32FC1`` ).
:param angle: Source matrix, containing angles ( ``CV_32FC1`` ).
:param x: Destination matrix of real components ( ``CV_32FC1`` ).
:param y: Destination matrix of imaginary components ( ``CV_32FC1`` ).
:param angleInDegress: Flag which indicates angles are in degress.
:param stream: Stream for the asynchronous version.
See also:
:func:`polarToCart`
.

721
modules/gpu/doc/per_element_operations..rst Normal file
View File

@ -0,0 +1,721 @@
Per-element Operations.
=======================
.. highlight:: cpp
.. index:: gpu::add
cv::gpu::add
------------
`id=0.387694196113 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Aadd>`__
.. cfunction:: void add(const GpuMat\& a, const GpuMat\& b, GpuMat\& c)
Computes matrix-matrix or matrix-scalar sum.
:param a: First source matrix. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destination matrix. Will have the same size and type as ``a`` .
.. cfunction:: void add(const GpuMat\& a, const Scalar\& sc, GpuMat\& c)
* **a** Source matrix. ``CV_32FC1`` and ``CV_32FC2`` matrixes are supported for now.
* **b** Source scalar to be added to the source matrix.
* **c** Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`add`
.
.. index:: gpu::subtract
cv::gpu::subtract
-----------------
`id=0.316386979537 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Asubtract>`__
.. cfunction:: void subtract(const GpuMat\& a, const GpuMat\& b, GpuMat\& c)
Subtracts matrix from another matrix (or scalar from matrix).
:param a: First source matrix. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destination matrix. Will have the same size and type as ``a`` .
.. cfunction:: void subtract(const GpuMat\& a, const Scalar\& sc, GpuMat\& c)
* **a** Source matrix. ``CV_32FC1`` and ``CV_32FC2`` matrixes are supported for now.
* **b** Scalar to be subtracted from the source matrix elements.
* **c** Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`subtract`
.
.. index:: gpu::multiply
cv::gpu::multiply
-----------------
`id=0.12843407457 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Amultiply>`__
.. cfunction:: void multiply(const GpuMat\& a, const GpuMat\& b, GpuMat\& c)
Computes per-element product of two matrices (or of matrix and scalar).
:param a: First source matrix. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destionation matrix. Will have the same size and type as ``a`` .
.. cfunction:: void multiply(const GpuMat\& a, const Scalar\& sc, GpuMat\& c)
* **a** Source matrix. ``CV_32FC1`` and ``CV_32FC2`` matrixes are supported for now.
* **b** Scalar to be multiplied by.
* **c** Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`multiply`
.
.. index:: gpu::divide
cv::gpu::divide
---------------
`id=0.178699823123 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Adivide>`__
.. cfunction:: void divide(const GpuMat\& a, const GpuMat\& b, GpuMat\& c)
Performs per-element division of two matrices (or division of matrix by scalar).
:param a: First source matrix. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destionation matrix. Will have the same size and type as ``a`` .
.. cfunction:: void divide(const GpuMat\& a, const Scalar\& sc, GpuMat\& c)
* **a** Source matrix. ``CV_32FC1`` and ``CV_32FC2`` matrixes are supported for now.
* **b** Scalar to be divided by.
* **c** Destination matrix. Will have the same size and type as ``a`` .
This function in contrast to
:func:`divide`
uses round-down rounding mode.
See also:
:func:`divide`
.
.. index:: gpu::exp
cv::gpu::exp
------------
`id=0.0437158645609 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Aexp>`__
.. cfunction:: void exp(const GpuMat\& a, GpuMat\& b)
Computes exponent of each matrix element.
:param a: Source matrix. ``CV_32FC1`` matrixes are supported for now.
:param b: Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`exp`
.
.. index:: gpu::log
cv::gpu::log
------------
`id=0.726514219732 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Alog>`__
.. cfunction:: void log(const GpuMat\& a, GpuMat\& b)
Computes natural logarithm of absolute value of each matrix element.
:param a: Source matrix. ``CV_32FC1`` matrixes are supported for now.
:param b: Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`log`
.
.. index:: gpu::absdiff
cv::gpu::absdiff
----------------
`id=0.0449517502969 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Aabsdiff>`__
.. cfunction:: void absdiff(const GpuMat\& a, const GpuMat\& b, GpuMat\& c)
Computes per-element absolute difference of two matrices (or of matrix and scalar).
:param a: First source matrix. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destionation matrix. Will have the same size and type as ``a`` .
.. cfunction:: void absdiff(const GpuMat\& a, const Scalar\& s, GpuMat\& c)
* **a** Source matrix. ``CV_32FC1`` matrixes are supported for now.
* **b** Scalar to be subtracted from the source matrix elements.
* **c** Destination matrix. Will have the same size and type as ``a`` .
See also:
:func:`absdiff`
.
.. index:: gpu::compare
cv::gpu::compare
----------------
`id=0.346307736999 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Acompare>`__
.. cfunction:: void compare(const GpuMat\& a, const GpuMat\& b, GpuMat\& c, int cmpop)
Compares elements of two matrices.
:param a: First source matrix. ``CV_8UC4`` and ``CV_32FC1`` matrices are supported for now.
:param b: Second source matrix. Must have the same size and type as ``a`` .
:param c: Destination matrix. Will have the same size as ``a`` and be ``CV_8UC1`` type.
:param cmpop: Flag specifying the relation between the elements to be checked:
* **CMP_EQ** :math:`=`
* **CMP_GT** :math:`>`
* **CMP_GE** :math:`\ge`
* **CMP_LT** :math:`<`
* **CMP_LE** :math:`\le`
* **CMP_NE** :math:`\ne`
See also:
:func:`compare`
.
.. index:: cv::gpu::bitwise_not
.. _cv::gpu::bitwise_not:
cv::gpu::bitwise_not
--------------------
`id=0.242780097451 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3Abitwise_not>`__
.. cfunction:: void bitwise_not(const GpuMat\& src, GpuMat\& dst, const GpuMat\& mask=GpuMat())
.. cfunction:: void bitwise_not(const GpuMat\& src, GpuMat\& dst, const GpuMat\& mask, const Stream\& stream)
Performs per-element bitwise inversion.
:param src: Source matrix.
:param dst: Destination matrix. Will have the same size and type as ``src`` .
:param mask: Optional operation mask. 8-bit single channel image.
:param stream: Stream for the asynchronous version.
See also:
.
.. index:: cv::gpu::bitwise_or
.. _cv::gpu::bitwise_or:
cv::gpu::bitwise_or
-------------------
`id=0.762303417062 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3Abitwise_or>`__
.. cfunction:: void bitwise_or(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask=GpuMat())
.. cfunction:: void bitwise_or(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask, const Stream\& stream)
Performs per-element bitwise disjunction of two matrices.
:param src1: First source matrix.
:param src2: Second source matrix. It must have the same size and type as ``src1`` .
:param dst: Destination matrix. Will have the same size and type as ``src1`` .
:param mask: Optional operation mask. 8-bit single channel image.
:param stream: Stream for the asynchronous version.
See also:
.
.. index:: cv::gpu::bitwise_and
.. _cv::gpu::bitwise_and:
cv::gpu::bitwise_and
--------------------
`id=0.621591376205 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3Abitwise_and>`__
.. cfunction:: void bitwise_and(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask=GpuMat())
.. cfunction:: void bitwise_and(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask, const Stream\& stream)
Performs per-element bitwise conjunction of two matrices.
:param src1: First source matrix.
:param src2: Second source matrix. It must have the same size and type as ``src1`` .
:param dst: Destination matrix. Will have the same size and type as ``src1`` .
:param mask: Optional operation mask. 8-bit single channel image.
:param stream: Stream for the asynchronous version.
See also:
.
.. index:: cv::gpu::bitwise_xor
.. _cv::gpu::bitwise_xor:
cv::gpu::bitwise_xor
--------------------
`id=0.684217951074 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/cv%3A%3Agpu%3A%3Abitwise_xor>`__
.. cfunction:: void bitwise_xor(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask=GpuMat())
.. cfunction:: void bitwise_xor(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const GpuMat\& mask, const Stream\& stream)
Performs per-element bitwise "exclusive or" of two matrices.
:param src1: First source matrix.
:param src2: Second source matrix. It must have the same size and type as ``src1`` .
:param dst: Destination matrix. Will have the same size and type as ``src1`` .
:param mask: Optional operation mask. 8-bit single channel image.
:param stream: Stream for the asynchronous version.
See also:
.
.. index:: gpu::min
cv::gpu::min
------------
`id=0.276176266158 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Amin>`__
.. cfunction:: void min(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst)
.. cfunction:: void min(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const Stream\& stream)
Computes per-element minimum of two matrices (or of matrix and scalar).
:param src1: First source matrix.
:param src2: Second source matrix.
:param dst: Destination matrix. Will have the same size and type as ``src1`` .
:param stream: Stream for the asynchronous version.
.. cfunction:: void min(const GpuMat\& src1, double src2, GpuMat\& dst)
.. cfunction:: void min(const GpuMat\& src1, double src2, GpuMat\& dst, const Stream\& stream)
* **src1** Source matrix.
* **src2** Scalar to be compared with.
* **dst** Destination matrix. Will have the same size and type as ``src1`` .
* **stream** Stream for the asynchronous version.
See also:
:func:`min`
.
.. index:: gpu::max
cv::gpu::max
------------
`id=0.175554622377 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/gpu/gpu%3A%3Amax>`__
.. cfunction:: void max(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst)
.. cfunction:: void max(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst, const Stream\& stream)
Computes per-element maximum of two matrices (or of matrix and scalar).
:param src1: First source matrix.
:param src2: Second source matrix.
:param dst: Destination matrix. Will have the same size and type as ``src1`` .
:param stream: Stream for the asynchronous version.
.. cfunction:: void max(const GpuMat\& src1, double src2, GpuMat\& dst)
.. cfunction:: void max(const GpuMat\& src1, double src2, GpuMat\& dst, const Stream\& stream)
* **src1** Source matrix.
* **src2** Scalar to be compared with.
* **dst** Destination matrix. Will have the same size and type as ``src1`` .
* **stream** Stream for the asynchronous version.
See also:
:func:`max`
.

3
modules/highgui/doc/highgui.rst Normal file
View File

@ -0,0 +1,3 @@
****************************
High-level GUI and Media I/O
****************************

39
modules/highgui/doc/highgui__high-level_gui_and_media_i_o.rst Normal file
View File

@ -0,0 +1,39 @@
*************************************
highgui. High-level GUI and Media I/O
*************************************
While OpenCV was designed for use in full-scale
applications and can be used within functionally rich UI frameworks (such as Qt, WinForms or Cocoa) or without any UI at all, sometimes there is a need to try some functionality quickly and visualize the results. This is what the HighGUI module has been designed for.
It provides easy interface to:
*
create and manipulate windows that can display images and "remember" their content (no need to handle repaint events from OS)
*
add trackbars to the windows, handle simple mouse events as well as keyboard commmands
*
read and write images to/from disk or memory.
*
read video from camera or file and write video to a file.
.. toctree::
:maxdepth: 2
highgui_user_interface
highgui_reading_and_writing_images_and_video
highgui_qt_new_functions

607
modules/highgui/doc/qt_new_functions.rst Normal file
View File

@ -0,0 +1,607 @@
Qt new functions
================
.. highlight:: cpp
.. image:: ../../pics/Qt_GUI.png
This figure explains the new functionalities implemented with Qt GUI. As we can see, the new GUI provides a statusbar, a toolbar, and a control panel. The control panel can have trackbars and buttonbars attached to it.
*
To attach a trackbar, the window
_
name parameter must be NULL.
*
To attach a buttonbar, a button must be created.
If the last bar attached to the control panel is a buttonbar, the new button is added on the right of the last button.
If the last bar attached to the control panel is a trackbar, or the control panel is empty, a new buttonbar is created. Then a new button is attached to it.
The following code is an example used to generate the figure.
::
int main(int argc, char *argv[])
int value = 50;
int value2 = 0;
cvNamedWindow("main1",CV_WINDOW_NORMAL);
cvNamedWindow("main2",CV_WINDOW_AUTOSIZE | CV_GUI_NORMAL);
cvCreateTrackbar( "track1", "main1", &value, 255, NULL);//OK tested
char* nameb1 = "button1";
char* nameb2 = "button2";
cvCreateButton(nameb1,callbackButton,nameb1,CV_CHECKBOX,1);
cvCreateButton(nameb2,callbackButton,nameb2,CV_CHECKBOX,0);
cvCreateTrackbar( "track2", NULL, &value2, 255, NULL);
cvCreateButton("button5",callbackButton1,NULL,CV_RADIOBOX,0);
cvCreateButton("button6",callbackButton2,NULL,CV_RADIOBOX,1);
cvSetMouseCallback( "main2",on_mouse,NULL );
IplImage* img1 = cvLoadImage("files/flower.jpg");
IplImage* img2 = cvCreateImage(cvGetSize(img1),8,3);
CvCapture* video = cvCaptureFromFile("files/hockey.avi");
IplImage* img3 = cvCreateImage(cvGetSize(cvQueryFrame(video)),8,3);
while(cvWaitKey(33) != 27)
{
cvAddS(img1,cvScalarAll(value),img2);
cvAddS(cvQueryFrame(video),cvScalarAll(value2),img3);
cvShowImage("main1",img2);
cvShowImage("main2",img3);
}
cvDestroyAllWindows();
cvReleaseImage(&img1);
cvReleaseImage(&img2);
cvReleaseImage(&img3);
cvReleaseCapture(&video);
return 0;
}
..
.. index:: setWindowProperty
cv::setWindowProperty
---------------------
`id=0.202216555435 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/setWindowProperty>`__
.. cfunction:: void setWindowProperty(const string\& name, int prop_id, double prop_value)
Change the parameters of the window dynamically.
:param name: Name of the window.
:param prop_id: Window's property to edit. The operation flags:
* **CV_WND_PROP_FULLSCREEN** Change if the window is fullscreen ( ``CV_WINDOW_NORMAL`` or ``CV_WINDOW_FULLSCREEN`` ).
* **CV_WND_PROP_AUTOSIZE** Change if the user can resize the window (texttt {CV\_WINDOW\_NORMAL} or ``CV_WINDOW_AUTOSIZE`` ).
* **CV_WND_PROP_ASPECTRATIO** Change if the image's aspect ratio is preserved (texttt {CV\_WINDOW\_FREERATIO} or ``CV_WINDOW_KEEPRATIO`` ).
:param prop_value: New value of the Window's property. The operation flags:
* **CV_WINDOW_NORMAL** Change the window in normal size, or allows the user to resize the window.
* **CV_WINDOW_AUTOSIZE** The user cannot resize the window, the size is constrainted by the image displayed.
* **CV_WINDOW_FULLSCREEN** Change the window to fullscreen.
* **CV_WINDOW_FREERATIO** The image expends as much as it can (no ratio constraint)
* **CV_WINDOW_KEEPRATIO** The ration image is respected.
The function
`` setWindowProperty``
allows to change the window's properties.
.. index:: getWindowProperty
cv::getWindowProperty
---------------------
`id=0.467280795493 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/getWindowProperty>`__
.. cfunction:: void getWindowProperty(const char* name, int prop_id)
Get the parameters of the window.
:param name: Name of the window.
:param prop_id: Window's property to retrive. The operation flags:
* **CV_WND_PROP_FULLSCREEN** Change if the window is fullscreen ( ``CV_WINDOW_NORMAL`` or ``CV_WINDOW_FULLSCREEN`` ).
* **CV_WND_PROP_AUTOSIZE** Change if the user can resize the window (texttt {CV\_WINDOW\_NORMAL} or ``CV_WINDOW_AUTOSIZE`` ).
* **CV_WND_PROP_ASPECTRATIO** Change if the image's aspect ratio is preserved (texttt {CV\_WINDOW\_FREERATIO} or ``CV_WINDOW_KEEPRATIO`` ).
See
:ref:`setWindowProperty`
to know the meaning of the returned values.
The function
`` getWindowProperty``
return window's properties.
.. index:: fontQt
cv::fontQt
----------
`id=0.680350496921 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/fontQt>`__
.. cfunction:: CvFont fontQt(const string\& nameFont, int pointSize = -1, Scalar color = Scalar::all(0), int weight = CV_FONT_NORMAL, int style = CV_STYLE_NORMAL, int spacing = 0)
Create the font to be used to draw text on an image.
:param nameFont: Name of the font. The name should match the name of a system font (such as ``Times''). If the font is not found, a default one will be used.
:param pointSize: Size of the font. If not specified, equal zero or negative, the point size of the font is set to a system-dependent default value. Generally, this is 12 points.
:param color: Color of the font in BGRA -- A = 255 is fully transparent. Use the macro CV _ RGB for simplicity.
:param weight: The operation flags:
* **CV_FONT_LIGHT** Weight of 25
* **CV_FONT_NORMAL** Weight of 50
* **CV_FONT_DEMIBOLD** Weight of 63
* **CV_FONT_BOLD** Weight of 75
* **CV_FONT_BLACK** Weight of 87
You can also specify a positive integer for more control.
:param style: The operation flags:
* **CV_STYLE_NORMAL** Font is normal
* **CV_STYLE_ITALIC** Font is in italic
* **CV_STYLE_OBLIQUE** Font is oblique
:param spacing: Spacing between characters. Can be negative or positive
The function
``fontQt``
creates a CvFont object. This CvFont is not compatible with putText.
A basic usage of this function is:
::
CvFont font = fontQt(''Times'');
addText( img1, ``Hello World !'', Point(50,50), font);
..
.. index:: addText
cv::addText
-----------
`id=0.0425492674947 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/addText>`__
.. cfunction:: void addText(const Mat\& img, const string\& text, Point location, CvFont *font)
Create the font to be used to draw text on an image
:param img: Image where the text should be drawn
:param text: Text to write on the image
:param location: Point(x,y) where the text should start on the image
:param font: Font to use to draw the text
The function
``addText``
draw
*text*
on the image
*img*
using a specific font
*font*
(see example
:ref:`fontQt`
)
.. index:: displayOverlay
cv::displayOverlay
------------------
`id=0.969508597197 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/displayOverlay>`__
.. cfunction:: void displayOverlay(const string\& name, const string\& text, int delay)
Display text on the window's image as an overlay for delay milliseconds. This is not editing the image's data. The text is display on the top of the image.
:param name: Name of the window
:param text: Overlay text to write on the window's image
:param delay: Delay to display the overlay text. If this function is called before the previous overlay text time out, the timer is restarted and the text updated. . If this value is zero, the text never disapers.
The function
``displayOverlay``
aims at displaying useful information/tips on the window for a certain amount of time
*delay*
. This information is display on the top of the window.
.. index:: displayStatusBar
cv::displayStatusBar
--------------------
`id=0.132014751496 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/displayStatusBar>`__
.. cfunction:: void displayStatusBar(const string\& name, const string\& text, int delayms)
Display text on the window's statusbar as for delay milliseconds.
:param name: Name of the window
:param text: Text to write on the window's statusbar
:param delay: Delay to display the text. If this function is called before the previous text time out, the timer is restarted and the text updated. If this value is zero, the text never disapers.
The function
``displayOverlay``
aims at displaying useful information/tips on the window for a certain amount of time
*delay*
. This information is displayed on the window's statubar (the window must be created with
``CV_GUI_EXPANDED``
flags).
.. index:: createOpenGLCallback
cv::createOpenGLCallback
------------------------
`id=0.0486773148219 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/createOpenGLCallback>`__
*_*
.. cfunction:: void createOpenGLCallback( const string\& window_name, OpenGLCallback callbackOpenGL, void* userdata CV_DEFAULT(NULL), double angle CV_DEFAULT(-1), double zmin CV_DEFAULT(-1), double zmax CV_DEFAULT(-1)
Create a callback function called to draw OpenGL on top the the image display by windowname.
:param window_name: Name of the window
:param callbackOpenGL:
Pointer to the function to be called every frame.
This function should be prototyped as ``void Foo(*void);`` .
:param userdata: pointer passed to the callback function. *(Optional)*
:param angle: Specifies the field of view angle, in degrees, in the y direction.. *(Optional - Default 45 degree)*
:param zmin: Specifies the distance from the viewer to the near clipping plane (always positive). *(Optional - Default 0.01)*
:param zmax: Specifies the distance from the viewer to the far clipping plane (always positive). *(Optional - Default 1000)*
The function
``createOpenGLCallback``
can be used to draw 3D data on the window. An example of callback could be:
::
void on_opengl(void* param)
{
glLoadIdentity();
glTranslated(0.0, 0.0, -1.0);
glRotatef( 55, 1, 0, 0 );
glRotatef( 45, 0, 1, 0 );
glRotatef( 0, 0, 0, 1 );
static const int coords[6][4][3] = {
{ { +1, -1, -1 }, { -1, -1, -1 }, { -1, +1, -1 }, { +1, +1, -1 } },
{ { +1, +1, -1 }, { -1, +1, -1 }, { -1, +1, +1 }, { +1, +1, +1 } },
{ { +1, -1, +1 }, { +1, -1, -1 }, { +1, +1, -1 }, { +1, +1, +1 } },
{ { -1, -1, -1 }, { -1, -1, +1 }, { -1, +1, +1 }, { -1, +1, -1 } },
{ { +1, -1, +1 }, { -1, -1, +1 }, { -1, -1, -1 }, { +1, -1, -1 } },
{ { -1, -1, +1 }, { +1, -1, +1 }, { +1, +1, +1 }, { -1, +1, +1 } }
};
for (int i = 0; i < 6; ++i) {
glColor3ub( i*20, 100+i*10, i*42 );
glBegin(GL_QUADS);
for (int j = 0; j < 4; ++j) {
glVertex3d(0.2 * coords[i][j][0], 0.2 * coords[i][j][1], 0.2 * coords[i][j][2]);
}
glEnd();
}
}
..
.. index:: saveWindowParameters
cv::saveWindowParameters
------------------------
`id=0.189887022151 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/saveWindowParameters>`__
*_*
.. cfunction:: void saveWindowParameters(const string\& name)
Save parameters of the window windowname.
:param name: Name of the window
The function
``saveWindowParameters``
saves size, location, flags, trackbars' value, zoom and panning location of the window
*window_name*
.. index:: loadWindowParameters
cv::loadWindowParameters
------------------------
`id=0.922344403304 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/loadWindowParameters>`__
*_*
.. cfunction:: void loadWindowParameters(const string\& name)
Load parameters of the window windowname.
:param name: Name of the window
The function
``loadWindowParameters``
load size, location, flags, trackbars' value, zoom and panning location of the window
*window_name*
.. index:: createButton
cv::createButton
----------------
`id=0.367650849719 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/createButton>`__
*_*
.. cfunction:: createButton( const string\& button_name CV_DEFAULT(NULL),ButtonCallback on_change CV_DEFAULT(NULL), void* userdata CV_DEFAULT(NULL) , int button_type CV_DEFAULT(CV_PUSH_BUTTON), int initial_button_state CV_DEFAULT(0)
Create a callback function called to draw OpenGL on top the the image display by windowname.
:param button_name: Name of the button *( if NULL, the name will be "button <number of boutton>")*
:param on_change:
Pointer to the function to be called every time the button changed its state.
This function should be prototyped as ``void Foo(int state,*void);`` . *state* is the current state of the button. It could be -1 for a push button, 0 or 1 for a check/radio box button.
:param userdata: pointer passed to the callback function. *(Optional)*
The
``button_type``
parameter can be :
*(Optional -- Will be a push button by default.)
* **CV_PUSH_BUTTON** The button will be a push button.
* **CV_CHECKBOX** The button will be a checkbox button.
* **CV_RADIOBOX** The button will be a radiobox button. The radiobox on the same buttonbar (same line) are exclusive; one on can be select at the time.
*
* **initial_button_state** Default state of the button. Use for checkbox and radiobox, its value could be 0 or 1. *(Optional)*
The function
``createButton``
attach a button to the control panel. Each button is added to a buttonbar on the right of the last button.
A new buttonbar is create if nothing was attached to the control panel before, or if the last element attached to the control panel was a trackbar.
Here are various example of
``createButton``
function call:
::
createButton(NULL,callbackButton);//create a push button "button 0", that will call callbackButton.
createButton("button2",callbackButton,NULL,CV_CHECKBOX,0);
createButton("button3",callbackButton,&value);
createButton("button5",callbackButton1,NULL,CV_RADIOBOX);
createButton("button6",callbackButton2,NULL,CV_PUSH_BUTTON,1);
..

624
modules/highgui/doc/reading_and_writing_images_and_video.rst Normal file
View File

@ -0,0 +1,624 @@
Reading and Writing Images and Video
====================================
.. highlight:: cpp
.. index:: imdecode
cv::imdecode
------------
`id=0.524391584247 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/imdecode>`__
.. cfunction:: Mat imdecode( const Mat\& buf, int flags )
Reads an image from a buffer in memory.
:param buf: The input array of vector of bytes
:param flags: The same flags as in :ref:`imread`
The function reads image from the specified buffer in memory.
If the buffer is too short or contains invalid data, the empty matrix will be returned.
See
:ref:`imread`
for the list of supported formats and the flags description.
.. index:: imencode
cv::imencode
------------
`id=0.960190095821 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/imencode>`__
.. cfunction:: bool imencode( const string\& ext, const Mat\& img, vector<uchar>\& buf, const vector<int>\& params=vector<int>())
Encode an image into a memory buffer.
:param ext: The file extension that defines the output format
:param img: The image to be written
:param buf: The output buffer; resized to fit the compressed image
:param params: The format-specific parameters; see :ref:`imwrite`
The function compresses the image and stores it in the memory buffer, which is resized to fit the result.
See
:ref:`imwrite`
for the list of supported formats and the flags description.
.. index:: imread
cv::imread
----------
`id=0.16110153292 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/imread>`__
.. cfunction:: Mat imread( const string\& filename, int flags=1 )
Loads an image from a file.
:param filename: Name of file to be loaded.
:param flags: Specifies color type of the loaded image:
* **>0** the loaded image is forced to be a 3-channel color image
* **=0** the loaded image is forced to be grayscale
* **<0** the loaded image will be loaded as-is (note that in the current implementation the alpha channel, if any, is stripped from the output image, e.g. 4-channel RGBA image will be loaded as RGB if :math:`flags\ge0` ).
The function
``imread``
loads an image from the specified file and returns it. If the image can not be read (because of missing file, improper permissions, unsupported or invalid format), the function returns empty matrix (
``Mat::data==NULL``
).Currently, the following file formats are supported:
*
Windows bitmaps -
``*.bmp, *.dib``
(always supported)
*
JPEG files -
``*.jpeg, *.jpg, *.jpe``
(see
**Note2**
)
*
JPEG 2000 files -
``*.jp2``
(see
**Note2**
)
*
Portable Network Graphics -
``*.png``
(see
**Note2**
)
*
Portable image format -
``*.pbm, *.pgm, *.ppm``
(always supported)
*
Sun rasters -
``*.sr, *.ras``
(always supported)
*
TIFF files -
``*.tiff, *.tif``
(see
**Note2**
)
**Note1**
: The function determines type of the image by the content, not by the file extension.
**Note2**
: On Windows and MacOSX the shipped with OpenCV image codecs (libjpeg, libpng, libtiff and libjasper) are used by default; so OpenCV can always read JPEGs, PNGs and TIFFs. On MacOSX there is also the option to use native MacOSX image readers. But beware that currently these native image loaders give images with somewhat different pixel values, because of the embedded into MacOSX color management.
On Linux, BSD flavors and other Unix-like open-source operating systems OpenCV looks for the supplied with OS image codecs. Please, install the relevant packages (do not forget the development files, e.g. "libjpeg-dev" etc. in Debian and Ubuntu) in order to get the codec support, or turn on
``OPENCV_BUILD_3RDPARTY_LIBS``
flag in CMake.
.. index:: imwrite
cv::imwrite
-----------
`id=0.00846497387051 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/imwrite>`__
.. cfunction:: bool imwrite( const string\& filename, const Mat\& img, const vector<int>\& params=vector<int>())
Saves an image to a specified file.
:param filename: Name of the file.
:param img: The image to be saved.
:param params: The format-specific save parameters, encoded as pairs ``paramId_1, paramValue_1, paramId_2, paramValue_2, ...`` . The following parameters are currently supported:
* In the case of JPEG it can be a quality ( ``CV_IMWRITE_JPEG_QUALITY`` ), from 0 to 100 (the higher is the better), 95 by default.
* In the case of PNG it can be the compression level ( ``CV_IMWRITE_PNG_COMPRESSION`` ), from 0 to 9 (the higher value means smaller size and longer compression time), 3 by default.
* In the case of PPM, PGM or PBM it can a binary format flag ( ``CV_IMWRITE_PXM_BINARY`` ), 0 or 1, 1 by default.
The function
``imwrite``
saves the image to the specified file. The image format is chosen based on the
``filename``
extension, see
:ref:`imread`
for the list of extensions. Only 8-bit (or 16-bit in the case of PNG, JPEG 2000 and TIFF) single-channel or 3-channel (with 'BGR' channel order) images can be saved using this function. If the format, depth or channel order is different, use
:ref:`Mat::convertTo`
, and
:ref:`cvtColor`
to convert it before saving, or use the universal XML I/O functions to save the image to XML or YAML format.
.. index:: VideoCapture
.. _VideoCapture:
VideoCapture
------------
`id=0.267295181599 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/VideoCapture>`__
.. ctype:: VideoCapture
Class for video capturing from video files or cameras
::
class VideoCapture
{
public:
// the default constructor
VideoCapture();
// the constructor that opens video file
VideoCapture(const string& filename);
// the constructor that starts streaming from the camera
VideoCapture(int device);
// the destructor
virtual ~VideoCapture();
// opens the specified video file
virtual bool open(const string& filename);
// starts streaming from the specified camera by its id
virtual bool open(int device);
// returns true if the file was open successfully or if the camera
// has been initialized succesfully
virtual bool isOpened() const;
// closes the camera stream or the video file
// (automatically called by the destructor)
virtual void release();
// grab the next frame or a set of frames from a multi-head camera;
// returns false if there are no more frames
virtual bool grab();
// reads the frame from the specified video stream
// (non-zero channel is only valid for multi-head camera live streams)
virtual bool retrieve(Mat& image, int channel=0);
// equivalent to grab() + retrieve(image, 0);
virtual VideoCapture& operator >> (Mat& image);
// sets the specified property propId to the specified value
virtual bool set(int propId, double value);
// retrieves value of the specified property
virtual double get(int propId);
protected:
...
};
..
The class provides C++ video capturing API. Here is how the class can be used:
::
#include "cv.h"
#include "highgui.h"
using namespace cv;
int main(int, char**)
{
VideoCapture cap(0); // open the default camera
if(!cap.isOpened()) // check if we succeeded
return -1;
Mat edges;
namedWindow("edges",1);
for(;;)
{
Mat frame;
cap >> frame; // get a new frame from camera
cvtColor(frame, edges, CV_BGR2GRAY);
GaussianBlur(edges, edges, Size(7,7), 1.5, 1.5);
Canny(edges, edges, 0, 30, 3);
imshow("edges", edges);
if(waitKey(30) >= 0) break;
}
// the camera will be deinitialized automatically in VideoCapture destructor
return 0;
}
..
.. index:: VideoCapture::VideoCapture
cv::VideoCapture::VideoCapture
------------------------------
`id=0.788880569149 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/VideoCapture%3A%3AVideoCapture>`__
.. cfunction:: VideoCapture::VideoCapture()
.. cfunction:: VideoCapture::VideoCapture(const string\& filename)
.. cfunction:: VideoCapture::VideoCapture(int device)
:param filename: TOWRITE
:param device: TOWRITE
VideoCapture constructors.
.. index:: VideoCapture::get
cv::VideoCapture::get
---------------------
`id=0.977076859044 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/VideoCapture%3A%3Aget>`__
.. cfunction:: double VideoCapture::get(int property_id)
:param property_id: Property identifier. Can be one of the following:
* **CV_CAP_PROP_POS_MSEC** Film current position in milliseconds or video capture timestamp
* **CV_CAP_PROP_POS_FRAMES** 0-based index of the frame to be decoded/captured next
* **CV_CAP_PROP_POS_AVI_RATIO** Relative position of the video file (0 - start of the film, 1 - end of the film)
* **CV_CAP_PROP_FRAME_WIDTH** Width of the frames in the video stream
* **CV_CAP_PROP_FRAME_HEIGHT** Height of the frames in the video stream
* **CV_CAP_PROP_FPS** Frame rate
* **CV_CAP_PROP_FOURCC** 4-character code of codec
* **CV_CAP_PROP_FRAME_COUNT** Number of frames in the video file
* **CV_CAP_PROP_FORMAT** The format of the Mat objects returned by retrieve()
* **CV_CAP_PROP_MODE** A backend-specific value indicating the current capture mode
* **CV_CAP_PROP_BRIGHTNESS** Brightness of the image (only for cameras)
* **CV_CAP_PROP_CONTRAST** Contrast of the image (only for cameras)
* **CV_CAP_PROP_SATURATION** Saturation of the image (only for cameras)
* **CV_CAP_PROP_HUE** Hue of the image (only for cameras)
* **CV_CAP_PROP_GAIN** Gain of the image (only for cameras)
* **CV_CAP_PROP_EXPOSURE** Exposure (only for cameras)
* **CV_CAP_PROP_CONVERT_RGB** Boolean flags indicating whether images should be converted to RGB
* **CV_CAP_PROP_WHITE_BALANCE** Currently unsupported
* **CV_CAP_PROP_RECTIFICATION** TOWRITE (note: only supported by DC1394 v 2.x backend currently)
Note that when querying a property which is unsupported by the backend used by the VideoCapture class, the value 0 is returned.
.. index:: VideoCapture::set
cv::VideoCapture::set
---------------------
`id=0.845027627213 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/VideoCapture%3A%3Aset>`__
.. cfunction:: bool VideoCapture::set(int property_id, double value)
:param property_id: Property identifier. Can be one of the following:
* **CV_CAP_PROP_POS_MSEC** Film current position in milliseconds or video capture timestamp
* **CV_CAP_PROP_POS_FRAMES** 0-based index of the frame to be decoded/captured next
* **CV_CAP_PROP_POS_AVI_RATIO** Relative position of the video file (0 - start of the film, 1 - end of the film)
* **CV_CAP_PROP_FRAME_WIDTH** Width of the frames in the video stream
* **CV_CAP_PROP_FRAME_HEIGHT** Height of the frames in the video stream
* **CV_CAP_PROP_FPS** Frame rate
* **CV_CAP_PROP_FOURCC** 4-character code of codec
* **CV_CAP_PROP_FRAME_COUNT** Number of frames in the video file
* **CV_CAP_PROP_FORMAT** The format of the Mat objects returned by retrieve()
* **CV_CAP_PROP_MODE** A backend-specific value indicating the current capture mode
* **CV_CAP_PROP_BRIGHTNESS** Brightness of the image (only for cameras)
* **CV_CAP_PROP_CONTRAST** Contrast of the image (only for cameras)
* **CV_CAP_PROP_SATURATION** Saturation of the image (only for cameras)
* **CV_CAP_PROP_HUE** Hue of the image (only for cameras)
* **CV_CAP_PROP_GAIN** Gain of the image (only for cameras)
* **CV_CAP_PROP_EXPOSURE** Exposure (only for cameras)
* **CV_CAP_PROP_CONVERT_RGB** Boolean flags indicating whether images should be converted to RGB
* **CV_CAP_PROP_WHITE_BALANCE** Currently unsupported
* **CV_CAP_PROP_RECTIFICATION** TOWRITE (note: only supported by DC1394 v 2.x backend currently)
:param value: value of the property.
Sets a property in the VideoCapture backend.
.. index:: VideoWriter
.. _VideoWriter:
VideoWriter
-----------
`id=0.234127975013 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/VideoWriter>`__
.. ctype:: VideoWriter
Video writer class
::
class VideoWriter
{
public:
// default constructor
VideoWriter();
// constructor that calls open
VideoWriter(const string& filename, int fourcc,
double fps, Size frameSize, bool isColor=true);
// the destructor
virtual ~VideoWriter();
// opens the file and initializes the video writer.
// filename - the output file name.
// fourcc - the codec
// fps - the number of frames per second
// frameSize - the video frame size
// isColor - specifies whether the video stream is color or grayscale
virtual bool open(const string& filename, int fourcc,
double fps, Size frameSize, bool isColor=true);
// returns true if the writer has been initialized successfully
virtual bool isOpened() const;
// writes the next video frame to the stream
virtual VideoWriter& operator << (const Mat& image);
protected:
...
};
..

315
modules/highgui/doc/user_interface.rst Normal file
View File

@ -0,0 +1,315 @@
User Interface
==============
.. highlight:: cpp
.. index:: createTrackbar
cv::createTrackbar
------------------
`id=0.122963695249 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/createTrackbar>`__
.. cfunction:: int createTrackbar( const string\& trackbarname, const string\& winname, int* value, int count, TrackbarCallback onChange CV_DEFAULT(0), void* userdata CV_DEFAULT(0))
Creates a trackbar and attaches it to the specified window
:param trackbarname: Name of the created trackbar.
:param winname: Name of the window which will be used as a parent of the created trackbar.
:param value: The optional pointer to an integer variable, whose value will reflect the position of the slider. Upon creation, the slider position is defined by this variable.
:param count: The maximal position of the slider. The minimal position is always 0.
:param onChange: Pointer to the function to be called every time the slider changes position. This function should be prototyped as ``void Foo(int,void*);`` , where the first parameter is the trackbar position and the second parameter is the user data (see the next parameter). If the callback is NULL pointer, then no callbacks is called, but only ``value`` is updated
:param userdata: The user data that is passed as-is to the callback; it can be used to handle trackbar events without using global variables
The function
``createTrackbar``
creates a trackbar (a.k.a. slider or range control) with the specified name and range, assigns a variable
``value``
to be syncronized with trackbar position and specifies a callback function
``onChange``
to be called on the trackbar position change. The created trackbar is displayed on the top of the given window.
\
\
**[Qt Backend Only]**
qt-specific details:
* **winname** Name of the window which will be used as a parent for created trackbar. Can be NULL if the trackbar should be attached to the control panel.
The created trackbar is displayed at the bottom of the given window if
*winname*
is correctly provided, or displayed on the control panel if
*winname*
is NULL.
By clicking on the label of each trackbar, it is possible to edit the trackbar's value manually for a more accurate control of it.
.. index:: getTrackbarPos
cv::getTrackbarPos
------------------
`id=0.51821188779 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/getTrackbarPos>`__
.. cfunction:: int getTrackbarPos( const string\& trackbarname, const string\& winname )
Returns the trackbar position.
:param trackbarname: Name of the trackbar.
:param winname: Name of the window which is the parent of the trackbar.
The function returns the current position of the specified trackbar.
\
\
**[Qt Backend Only]**
qt-specific details:
* **winname** Name of the window which is the parent of the trackbar. Can be NULL if the trackbar is attached to the control panel.
.. index:: imshow
cv::imshow
----------
`id=0.765508098436 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/imshow>`__
.. cfunction:: void imshow( const string\& winname, const Mat\& image )
Displays the image in the specified window
:param winname: Name of the window.
:param image: Image to be shown.
The function
``imshow``
displays the image in the specified window. If the window was created with the
``CV_WINDOW_AUTOSIZE``
flag then the image is shown with its original size, otherwise the image is scaled to fit in the window. The function may scale the image, depending on its depth:
*
If the image is 8-bit unsigned, it is displayed as is.
*
If the image is 16-bit unsigned or 32-bit integer, the pixels are divided by 256. That is, the value range [0,255*256] is mapped to [0,255].
*
If the image is 32-bit floating-point, the pixel values are multiplied by 255. That is, the value range [0,1] is mapped to [0,255].
.. index:: namedWindow
cv::namedWindow
---------------
`id=0.618574996458 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/namedWindow>`__
.. cfunction:: void namedWindow( const string\& winname, int flags )
Creates a window.
:param name: Name of the window in the window caption that may be used as a window identifier.
:param flags: Flags of the window. Currently the only supported flag is ``CV_WINDOW_AUTOSIZE`` . If this is set, the window size is automatically adjusted to fit the displayed image (see :ref:`imshow` ), and the user can not change the window size manually.
The function
``namedWindow``
creates a window which can be used as a placeholder for images and trackbars. Created windows are referred to by their names.
If a window with the same name already exists, the function does nothing.
\
\
**[Qt Backend Only]**
qt-specific details:
* **flags** Flags of the window. Currently the supported flags are:
* **CV_WINDOW_NORMAL or CV_WINDOW_AUTOSIZE:** ``CV_WINDOW_NORMAL`` let the user resize the window, whereas ``CV_WINDOW_AUTOSIZE`` adjusts automatically the window's size to fit the displayed image (see :ref:`ShowImage` ), and the user can not change the window size manually.
* **CV_WINDOW_FREERATIO or CV_WINDOW_KEEPRATIO:** ``CV_WINDOW_FREERATIO`` adjust the image without respect the its ration, whereas ``CV_WINDOW_KEEPRATIO`` keep the image's ratio.
* **CV_GUI_NORMAL or CV_GUI_EXPANDED:** ``CV_GUI_NORMAL`` is the old way to draw the window without statusbar and toolbar, whereas ``CV_GUI_EXPANDED`` is the new enhance GUI.
This parameter is optional. The default flags set for a new window are ``CV_WINDOW_AUTOSIZE`` , ``CV_WINDOW_KEEPRATIO`` , and ``CV_GUI_EXPANDED`` .
However, if you want to modify the flags, you can combine them using OR operator, ie:
::
namedWindow( ``myWindow'', ``CV_WINDOW_NORMAL`` textbar ``CV_GUI_NORMAL`` );
..
.. index:: setTrackbarPos
cv::setTrackbarPos
------------------
`id=0.247665233354 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/setTrackbarPos>`__
.. cfunction:: void setTrackbarPos( const string\& trackbarname, const string\& winname, int pos )
Sets the trackbar position.
:param trackbarname: Name of the trackbar.
:param winname: Name of the window which is the parent of trackbar.
:param pos: The new position.
The function sets the position of the specified trackbar in the specified window.
\
\
**[Qt Backend Only]**
qt-specific details:
* **winname** Name of the window which is the parent of trackbar. Can be NULL if the trackbar is attached to the control panel.
.. index:: waitKey
cv::waitKey
-----------
`id=0.777845991089 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/highgui/waitKey>`__
.. cfunction:: int waitKey(int delay=0)
Waits for a pressed key.
:param delay: Delay in milliseconds. 0 is the special value that means "forever"
The function
``waitKey``
waits for key event infinitely (when
:math:`\texttt{delay}\leq 0`
) or for
``delay``
milliseconds, when it's positive. Returns the code of the pressed key or -1 if no key was pressed before the specified time had elapsed.
**Note:**
This function is the only method in HighGUI that can fetch and handle events, so it needs to be called periodically for normal event processing, unless HighGUI is used within some environment that takes care of event processing.
**Note 2:**
The function only works if there is at least one HighGUI window created and the window is active. If there are several HighGUI windows, any of them can be active.

829
modules/imgproc/doc/feature_detection.rst Normal file
View File

@ -0,0 +1,829 @@
Feature Detection
=================
.. highlight:: cpp
.. index:: Canny
cv::Canny
---------
`id=0.626295418243 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/Canny>`__
.. cfunction:: void Canny( const Mat\& image, Mat\& edges, double threshold1, double threshold2, int apertureSize=3, bool L2gradient=false )
Finds edges in an image using Canny algorithm.
:param image: Single-channel 8-bit input image
:param edges: The output edge map. It will have the same size and the same type as ``image``
:param threshold1: The first threshold for the hysteresis procedure
:param threshold2: The second threshold for the hysteresis procedure
:param apertureSize: Aperture size for the :func:`Sobel` operator
:param L2gradient: Indicates, whether the more accurate :math:`L_2` norm :math:`=\sqrt{(dI/dx)^2 + (dI/dy)^2}` should be used to compute the image gradient magnitude ( ``L2gradient=true`` ), or a faster default :math:`L_1` norm :math:`=|dI/dx|+|dI/dy|` is enough ( ``L2gradient=false`` )
The function finds edges in the input image
``image``
and marks them in the output map
``edges``
using the Canny algorithm. The smallest value between
``threshold1``
and
``threshold2``
is used for edge linking, the largest value is used to find the initial segments of strong edges, see
http://en.wikipedia.org/wiki/Canny_edge_detector
.. index:: cornerEigenValsAndVecs
cv::cornerEigenValsAndVecs
--------------------------
`id=0.211221916008 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/cornerEigenValsAndVecs>`__
.. cfunction:: void cornerEigenValsAndVecs( const Mat\& src, Mat\& dst, int blockSize, int apertureSize, int borderType=BORDER_DEFAULT )
Calculates eigenvalues and eigenvectors of image blocks for corner detection.
:param src: Input single-channel 8-bit or floating-point image
:param dst: Image to store the results. It will have the same size as ``src`` and the type ``CV_32FC(6)``
:param blockSize: Neighborhood size (see discussion)
:param apertureSize: Aperture parameter for the :func:`Sobel` operator
:param boderType: Pixel extrapolation method; see :func:`borderInterpolate`
For every pixel
:math:`p`
, the function
``cornerEigenValsAndVecs``
considers a
``blockSize``
:math:`\times`
``blockSize``
neigborhood
:math:`S(p)`
. It calculates the covariation matrix of derivatives over the neighborhood as:
.. math::
M = \begin{bmatrix} \sum _{S(p)}(dI/dx)^2 & \sum _{S(p)}(dI/dx dI/dy)^2 \\ \sum _{S(p)}(dI/dx dI/dy)^2 & \sum _{S(p)}(dI/dy)^2 \end{bmatrix}
Where the derivatives are computed using
:func:`Sobel`
operator.
After that it finds eigenvectors and eigenvalues of
:math:`M`
and stores them into destination image in the form
:math:`(\lambda_1, \lambda_2, x_1, y_1, x_2, y_2)`
where
* :math:`\lambda_1, \lambda_2`
are the eigenvalues of
:math:`M`
; not sorted
* :math:`x_1, y_1`
are the eigenvectors corresponding to
:math:`\lambda_1`
* :math:`x_2, y_2`
are the eigenvectors corresponding to
:math:`\lambda_2`
The output of the function can be used for robust edge or corner detection.
See also:
:func:`cornerMinEigenVal`
,
:func:`cornerHarris`
,
:func:`preCornerDetect`
.. index:: cornerHarris
cv::cornerHarris
----------------
`id=0.781956530281 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/cornerHarris>`__
.. cfunction:: void cornerHarris( const Mat\& src, Mat\& dst, int blockSize, int apertureSize, double k, int borderType=BORDER_DEFAULT )
Harris edge detector.
:param src: Input single-channel 8-bit or floating-point image
:param dst: Image to store the Harris detector responses; will have type ``CV_32FC1`` and the same size as ``src``
:param blockSize: Neighborhood size (see the discussion of :func:`cornerEigenValsAndVecs` )
:param apertureSize: Aperture parameter for the :func:`Sobel` operator
:param k: Harris detector free parameter. See the formula below
:param boderType: Pixel extrapolation method; see :func:`borderInterpolate`
The function runs the Harris edge detector on the image. Similarly to
:func:`cornerMinEigenVal`
and
:func:`cornerEigenValsAndVecs`
, for each pixel
:math:`(x, y)`
it calculates a
:math:`2\times2`
gradient covariation matrix
:math:`M^{(x,y)}`
over a
:math:`\texttt{blockSize} \times \texttt{blockSize}`
neighborhood. Then, it computes the following characteristic:
.. math::
\texttt{dst} (x,y) = \mathrm{det} M^{(x,y)} - k \cdot \left ( \mathrm{tr} M^{(x,y)} \right )^2
Corners in the image can be found as the local maxima of this response map.
.. index:: cornerMinEigenVal
cv::cornerMinEigenVal
---------------------
`id=0.604155117868 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/cornerMinEigenVal>`__
.. cfunction:: void cornerMinEigenVal( const Mat\& src, Mat\& dst, int blockSize, int apertureSize=3, int borderType=BORDER_DEFAULT )
Calculates the minimal eigenvalue of gradient matrices for corner detection.
:param src: Input single-channel 8-bit or floating-point image
:param dst: Image to store the minimal eigenvalues; will have type ``CV_32FC1`` and the same size as ``src``
:param blockSize: Neighborhood size (see the discussion of :func:`cornerEigenValsAndVecs` )
:param apertureSize: Aperture parameter for the :func:`Sobel` operator
:param boderType: Pixel extrapolation method; see :func:`borderInterpolate`
The function is similar to
:func:`cornerEigenValsAndVecs`
but it calculates and stores only the minimal eigenvalue of the covariation matrix of derivatives, i.e.
:math:`\min(\lambda_1, \lambda_2)`
in terms of the formulae in
:func:`cornerEigenValsAndVecs`
description.
.. index:: cornerSubPix
cv::cornerSubPix
----------------
`id=0.0211213978919 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/cornerSubPix>`__
.. cfunction:: void cornerSubPix( const Mat\& image, vector<Point2f>\& corners, Size winSize, Size zeroZone, TermCriteria criteria )
Refines the corner locations.
:param image: Input image
:param corners: Initial coordinates of the input corners; refined coordinates on output
:param winSize: Half of the side length of the search window. For example, if ``winSize=Size(5,5)`` , then a :math:`5*2+1 \times 5*2+1 = 11 \times 11` search window would be used
:param zeroZone: Half of the size of the dead region in the middle of the search zone over which the summation in the formula below is not done. It is used sometimes to avoid possible singularities of the autocorrelation matrix. The value of (-1,-1) indicates that there is no such size
:param criteria: Criteria for termination of the iterative process of corner refinement. That is, the process of corner position refinement stops either after a certain number of iterations or when a required accuracy is achieved. The ``criteria`` may specify either of or both the maximum number of iteration and the required accuracy
The function iterates to find the sub-pixel accurate location of corners, or radial saddle points, as shown in on the picture below.
.. image:: ../../pics/cornersubpix.png
Sub-pixel accurate corner locator is based on the observation that every vector from the center
:math:`q`
to a point
:math:`p`
located within a neighborhood of
:math:`q`
is orthogonal to the image gradient at
:math:`p`
subject to image and measurement noise. Consider the expression:
.. math::
\epsilon _i = {DI_{p_i}}^T \cdot (q - p_i)
where
:math:`{DI_{p_i}}`
is the image gradient at the one of the points
:math:`p_i`
in a neighborhood of
:math:`q`
. The value of
:math:`q`
is to be found such that
:math:`\epsilon_i`
is minimized. A system of equations may be set up with
:math:`\epsilon_i`
set to zero:
.. math::
\sum _i(DI_{p_i} \cdot {DI_{p_i}}^T) - \sum _i(DI_{p_i} \cdot {DI_{p_i}}^T \cdot p_i)
where the gradients are summed within a neighborhood ("search window") of
:math:`q`
. Calling the first gradient term
:math:`G`
and the second gradient term
:math:`b`
gives:
.. math::
q = G^{-1} \cdot b
The algorithm sets the center of the neighborhood window at this new center
:math:`q`
and then iterates until the center keeps within a set threshold.
.. index:: goodFeaturesToTrack
cv::goodFeaturesToTrack
-----------------------
`id=0.784762708085 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/goodFeaturesToTrack>`__
.. cfunction:: void goodFeaturesToTrack( const Mat\& image, vector<Point2f>\& corners, int maxCorners, double qualityLevel, double minDistance, const Mat\& mask=Mat(), int blockSize=3, bool useHarrisDetector=false, double k=0.04 )
Determines strong corners on an image.
:param image: The input 8-bit or floating-point 32-bit, single-channel image
:param corners: The output vector of detected corners
:param maxCorners: The maximum number of corners to return. If there are more corners than that will be found, the strongest of them will be returned
:param qualityLevel: Characterizes the minimal accepted quality of image corners; the value of the parameter is multiplied by the by the best corner quality measure (which is the min eigenvalue, see :func:`cornerMinEigenVal` , or the Harris function response, see :func:`cornerHarris` ). The corners, which quality measure is less than the product, will be rejected. For example, if the best corner has the quality measure = 1500, and the ``qualityLevel=0.01`` , then all the corners which quality measure is less than 15 will be rejected.
:param minDistance: The minimum possible Euclidean distance between the returned corners
:param mask: The optional region of interest. If the image is not empty (then it needs to have the type ``CV_8UC1`` and the same size as ``image`` ), it will specify the region in which the corners are detected
:param blockSize: Size of the averaging block for computing derivative covariation matrix over each pixel neighborhood, see :func:`cornerEigenValsAndVecs`
:param useHarrisDetector: Indicates, whether to use operator or :func:`cornerMinEigenVal`
:param k: Free parameter of Harris detector
The function finds the most prominent corners in the image or in the specified image region, as described
in
Shi94
:
#.
the function first calculates the corner quality measure at every source image pixel using the
:func:`cornerMinEigenVal`
or
:func:`cornerHarris`
#.
then it performs non-maxima suppression (the local maxima in
:math:`3\times 3`
neighborhood
are retained).
#.
the next step rejects the corners with the minimal eigenvalue less than
:math:`\texttt{qualityLevel} \cdot \max_{x,y} qualityMeasureMap(x,y)`
.
#.
the remaining corners are then sorted by the quality measure in the descending order.
#.
finally, the function throws away each corner
:math:`pt_j`
if there is a stronger corner
:math:`pt_i`
(
:math:`i < j`
) such that the distance between them is less than
``minDistance``
The function can be used to initialize a point-based tracker of an object.
Note that the if the function is called with different values
``A``
and
``B``
of the parameter
``qualityLevel``
, and
``A``
> {B}, the vector of returned corners with
``qualityLevel=A``
will be the prefix of the output vector with
``qualityLevel=B``
.
See also:
:func:`cornerMinEigenVal`
,
:func:`cornerHarris`
,
:func:`calcOpticalFlowPyrLK`
,
:func:`estimateRigidMotion`
,
:func:`PlanarObjectDetector`
,
:func:`OneWayDescriptor`
.. index:: HoughCircles
cv::HoughCircles
----------------
`id=0.474895262744 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/HoughCircles>`__
.. cfunction:: void HoughCircles( Mat\& image, vector<Vec3f>\& circles, int method, double dp, double minDist, double param1=100, double param2=100, int minRadius=0, int maxRadius=0 )
Finds circles in a grayscale image using a Hough transform.
:param image: The 8-bit, single-channel, grayscale input image
:param circles: The output vector of found circles. Each vector is encoded as 3-element floating-point vector :math:`(x, y, radius)`
:param method: Currently, the only implemented method is ``CV_HOUGH_GRADIENT`` , which is basically *21HT* , described in Yuen90 .
:param dp: The inverse ratio of the accumulator resolution to the image resolution. For example, if ``dp=1`` , the accumulator will have the same resolution as the input image, if ``dp=2`` - accumulator will have half as big width and height, etc
:param minDist: Minimum distance between the centers of the detected circles. If the parameter is too small, multiple neighbor circles may be falsely detected in addition to a true one. If it is too large, some circles may be missed
:param param1: The first method-specific parameter. in the case of ``CV_HOUGH_GRADIENT`` it is the higher threshold of the two passed to :func:`Canny` edge detector (the lower one will be twice smaller)
:param param2: The second method-specific parameter. in the case of ``CV_HOUGH_GRADIENT`` it is the accumulator threshold at the center detection stage. The smaller it is, the more false circles may be detected. Circles, corresponding to the larger accumulator values, will be returned first
:param minRadius: Minimum circle radius
:param maxRadius: Maximum circle radius
The function finds circles in a grayscale image using some modification of Hough transform. Here is a short usage example:
::
#include <cv.h>
#include <highgui.h>
#include <math.h>
using namespace cv;
int main(int argc, char** argv)
{
Mat img, gray;
if( argc != 2 && !(img=imread(argv[1], 1)).data)
return -1;
cvtColor(img, gray, CV_BGR2GRAY);
// smooth it, otherwise a lot of false circles may be detected
GaussianBlur( gray, gray, Size(9, 9), 2, 2 );
vector<Vec3f> circles;
HoughCircles(gray, circles, CV_HOUGH_GRADIENT,
2, gray->rows/4, 200, 100 );
for( size_t i = 0; i < circles.size(); i++ )
{
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
// draw the circle center
circle( img, center, 3, Scalar(0,255,0), -1, 8, 0 );
// draw the circle outline
circle( img, center, radius, Scalar(0,0,255), 3, 8, 0 );
}
namedWindow( "circles", 1 );
imshow( "circles", img );
return 0;
}
..
Note that usually the function detects the circles' centers well, however it may fail to find the correct radii. You can assist the function by specifying the radius range (
``minRadius``
and
``maxRadius``
) if you know it, or you may ignore the returned radius, use only the center and find the correct radius using some additional procedure.
See also:
:func:`fitEllipse`
,
:func:`minEnclosingCircle`
.. index:: HoughLines
cv::HoughLines
--------------
`id=0.877791227007 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/HoughLines>`__
.. cfunction:: void HoughLines( Mat\& image, vector<Vec2f>\& lines, double rho, double theta, int threshold, double srn=0, double stn=0 )
Finds lines in a binary image using standard Hough transform.
:param image: The 8-bit, single-channel, binary source image. The image may be modified by the function
:param lines: The output vector of lines. Each line is represented by a two-element vector :math:`(\rho, \theta)` . :math:`\rho` is the distance from the coordinate origin :math:`(0,0)` (top-left corner of the image) and :math:`\theta` is the line rotation angle in radians ( :math:`0 \sim \textrm{vertical line}, \pi/2 \sim \textrm{horizontal line}` )
:param rho: Distance resolution of the accumulator in pixels
:param theta: Angle resolution of the accumulator in radians
:param threshold: The accumulator threshold parameter. Only those lines are returned that get enough votes ( :math:`>\texttt{threshold}` )
:param srn: For the multi-scale Hough transform it is the divisor for the distance resolution ``rho`` . The coarse accumulator distance resolution will be ``rho`` and the accurate accumulator resolution will be ``rho/srn`` . If both ``srn=0`` and ``stn=0`` then the classical Hough transform is used, otherwise both these parameters should be positive.
:param stn: For the multi-scale Hough transform it is the divisor for the distance resolution ``theta``
The function implements standard or standard multi-scale Hough transform algorithm for line detection. See
:func:`HoughLinesP`
for the code example.
.. index:: HoughLinesP
cv::HoughLinesP
---------------
`id=0.855533341526 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/HoughLinesP>`__
.. cfunction:: void HoughLinesP( Mat\& image, vector<Vec4i>\& lines, double rho, double theta, int threshold, double minLineLength=0, double maxLineGap=0 )
Finds lines segments in a binary image using probabilistic Hough transform.
:param image: The 8-bit, single-channel, binary source image. The image may be modified by the function
:param lines: The output vector of lines. Each line is represented by a 4-element vector :math:`(x_1, y_1, x_2, y_2)` , where :math:`(x_1,y_1)` and :math:`(x_2, y_2)` are the ending points of each line segment detected.
:param rho: Distance resolution of the accumulator in pixels
:param theta: Angle resolution of the accumulator in radians
:param threshold: The accumulator threshold parameter. Only those lines are returned that get enough votes ( :math:`>\texttt{threshold}` )
:param minLineLength: The minimum line length. Line segments shorter than that will be rejected
:param maxLineGap: The maximum allowed gap between points on the same line to link them.
The function implements probabilistic Hough transform algorithm for line detection, described in
Matas00
. Below is line detection example:
::
/* This is a standalone program. Pass an image name as a first parameter
of the program. Switch between standard and probabilistic Hough transform
by changing "#if 1" to "#if 0" and back */
#include <cv.h>
#include <highgui.h>
#include <math.h>
using namespace cv;
int main(int argc, char** argv)
{
Mat src, dst, color_dst;
if( argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Canny( src, dst, 50, 200, 3 );
cvtColor( dst, color_dst, CV_GRAY2BGR );
#if 0
vector<Vec2f> lines;
HoughLines( dst, lines, 1, CV_PI/180, 100 );
for( size_t i = 0; i < lines.size(); i++ )
{
float rho = lines[i][0];
float theta = lines[i][1];
double a = cos(theta), b = sin(theta);
double x0 = a*rho, y0 = b*rho;
Point pt1(cvRound(x0 + 1000*(-b)),
cvRound(y0 + 1000*(a)));
Point pt2(cvRound(x0 - 1000*(-b)),
cvRound(y0 - 1000*(a)));
line( color_dst, pt1, pt2, Scalar(0,0,255), 3, 8 );
}
#else
vector<Vec4i> lines;
HoughLinesP( dst, lines, 1, CV_PI/180, 80, 30, 10 );
for( size_t i = 0; i < lines.size(); i++ )
{
line( color_dst, Point(lines[i][0], lines[i][1]),
Point(lines[i][2], lines[i][3]), Scalar(0,0,255), 3, 8 );
}
#endif
namedWindow( "Source", 1 );
imshow( "Source", src );
namedWindow( "Detected Lines", 1 );
imshow( "Detected Lines", color_dst );
waitKey(0);
return 0;
}
..
This is the sample picture the function parameters have been tuned for:
.. image:: ../../pics/building.jpg
And this is the output of the above program in the case of probabilistic Hough transform
.. image:: ../../pics/houghp.png
.. index:: preCornerDetect
cv::preCornerDetect
-------------------
`id=0.828630230352 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/preCornerDetect>`__
.. cfunction:: void preCornerDetect( const Mat\& src, Mat\& dst, int apertureSize, int borderType=BORDER_DEFAULT )
Calculates the feature map for corner detection
:param src: The source single-channel 8-bit of floating-point image
:param dst: The output image; will have type ``CV_32F`` and the same size as ``src``
:param apertureSize: Aperture size of :func:`Sobel`
:param borderType: The pixel extrapolation method; see :func:`borderInterpolate`
The function calculates the complex spatial derivative-based function of the source image
.. math::
\texttt{dst} = (D_x \texttt{src} )^2 \cdot D_{yy} \texttt{src} + (D_y \texttt{src} )^2 \cdot D_{xx} \texttt{src} - 2 D_x \texttt{src} \cdot D_y \texttt{src} \cdot D_{xy} \texttt{src}
where
:math:`D_x`
,
:math:`D_y`
are the first image derivatives,
:math:`D_{xx}`
,
:math:`D_{yy}`
are the second image derivatives and
:math:`D_{xy}`
is the mixed derivative.
The corners can be found as local maximums of the functions, as shown below:
::
Mat corners, dilated_corners;
preCornerDetect(image, corners, 3);
// dilation with 3x3 rectangular structuring element
dilate(corners, dilated_corners, Mat(), 1);
Mat corner_mask = corners == dilated_corners;
..

2447
modules/imgproc/doc/filtering.rst Normal file
View File

File diff suppressed because it is too large Load Diff

774
modules/imgproc/doc/geometric_transformations.rst Normal file
View File

@ -0,0 +1,774 @@
Geometric Image Transformations
===============================
.. highlight:: cpp
The functions in this section perform various geometrical transformations of 2D images. That is, they do not change the image content, but deform the pixel grid, and map this deformed grid to the destination image. In fact, to avoid sampling artifacts, the mapping is done in the reverse order, from destination to the source. That is, for each pixel
:math:`(x, y)`
of the destination image, the functions compute coordinates of the corresponding "donor" pixel in the source image and copy the pixel value, that is:
.. math::
\texttt{dst} (x,y)= \texttt{src} (f_x(x,y), f_y(x,y))
In the case when the user specifies the forward mapping:
:math:`\left<g_x, g_y\right>: \texttt{src} \rightarrow \texttt{dst}`
, the OpenCV functions first compute the corresponding inverse mapping:
:math:`\left<f_x, f_y\right>: \texttt{dst} \rightarrow \texttt{src}`
and then use the above formula.
The actual implementations of the geometrical transformations, from the most generic
:ref:`Remap`
and to the simplest and the fastest
:ref:`Resize`
, need to solve the 2 main problems with the above formula:
#.
extrapolation of non-existing pixels. Similarly to the filtering functions, described in the previous section, for some
:math:`(x,y)`
one of
:math:`f_x(x,y)`
or
:math:`f_y(x,y)`
, or they both, may fall outside of the image, in which case some extrapolation method needs to be used. OpenCV provides the same selection of the extrapolation methods as in the filtering functions, but also an additional method
``BORDER_TRANSPARENT``
, which means that the corresponding pixels in the destination image will not be modified at all.
#.
interpolation of pixel values. Usually
:math:`f_x(x,y)`
and
:math:`f_y(x,y)`
are floating-point numbers (i.e.
:math:`\left<f_x, f_y\right>`
can be an affine or perspective transformation, or radial lens distortion correction etc.), so a pixel values at fractional coordinates needs to be retrieved. In the simplest case the coordinates can be just rounded to the nearest integer coordinates and the corresponding pixel used, which is called nearest-neighbor interpolation. However, a better result can be achieved by using more sophisticated
`interpolation methods <http://en.wikipedia.org/wiki/Multivariate_interpolation>`_
, where a polynomial function is fit into some neighborhood of the computed pixel
:math:`(f_x(x,y), f_y(x,y))`
and then the value of the polynomial at
:math:`(f_x(x,y), f_y(x,y))`
is taken as the interpolated pixel value. In OpenCV you can choose between several interpolation methods, see
:ref:`Resize`
.
.. index:: convertMaps
cv::convertMaps
---------------
`id=0.830076060616 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/convertMaps>`__
.. cfunction:: void convertMaps( const Mat\& map1, const Mat\& map2, Mat\& dstmap1, Mat\& dstmap2, int dstmap1type, bool nninterpolation=false )
Converts image transformation maps from one representation to another
:param map1: The first input map of type ``CV_16SC2`` or ``CV_32FC1`` or ``CV_32FC2``
:param map2: The second input map of type ``CV_16UC1`` or ``CV_32FC1`` or none (empty matrix), respectively
:param dstmap1: The first output map; will have type ``dstmap1type`` and the same size as ``src``
:param dstmap2: The second output map
:param dstmap1type: The type of the first output map; should be ``CV_16SC2`` , ``CV_32FC1`` or ``CV_32FC2``
:param nninterpolation: Indicates whether the fixed-point maps will be used for nearest-neighbor or for more complex interpolation
The function converts a pair of maps for
:func:`remap`
from one representation to another. The following options (
``(map1.type(), map2.type())``
:math:`\rightarrow`
``(dstmap1.type(), dstmap2.type())``
) are supported:
#.
:math:`\texttt{(CV\_32FC1, CV\_32FC1)} \rightarrow \texttt{(CV\_16SC2, CV\_16UC1)}`
. This is the most frequently used conversion operation, in which the original floating-point maps (see
:func:`remap`
) are converted to more compact and much faster fixed-point representation. The first output array will contain the rounded coordinates and the second array (created only when
``nninterpolation=false``
) will contain indices in the interpolation tables.
#.
:math:`\texttt{(CV\_32FC2)} \rightarrow \texttt{(CV\_16SC2, CV\_16UC1)}`
. The same as above, but the original maps are stored in one 2-channel matrix.
#.
the reverse conversion. Obviously, the reconstructed floating-point maps will not be exactly the same as the originals.
See also:
:func:`remap`
,
:func:`undisort`
,
:func:`initUndistortRectifyMap`
.. index:: getAffineTransform
cv::getAffineTransform
----------------------
`id=0.578246613742 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/getAffineTransform>`__
.. cfunction:: Mat getAffineTransform( const Point2f src[], const Point2f dst[] )
Calculates the affine transform from 3 pairs of the corresponding points
:param src: Coordinates of a triangle vertices in the source image
:param dst: Coordinates of the corresponding triangle vertices in the destination image
The function calculates the
:math:`2 \times 3`
matrix of an affine transform such that:
.. math::
\begin{bmatrix} x'_i \\ y'_i \end{bmatrix} = \texttt{map\_matrix} \cdot \begin{bmatrix} x_i \\ y_i \\ 1 \end{bmatrix}
where
.. math::
dst(i)=(x'_i,y'_i),
src(i)=(x_i, y_i),
i=0,1,2
See also:
:func:`warpAffine`
,
:func:`transform`
.. index:: getPerspectiveTransform
cv::getPerspectiveTransform
---------------------------
`id=0.124978390322 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/getPerspectiveTransform>`__
.. cfunction:: Mat getPerspectiveTransform( const Point2f src[], const Point2f dst[] )
Calculates the perspective transform from 4 pairs of the corresponding points
:param src: Coordinates of a quadrange vertices in the source image
:param dst: Coordinates of the corresponding quadrangle vertices in the destination image
The function calculates the
:math:`3 \times 3`
matrix of a perspective transform such that:
.. math::
\begin{bmatrix} t_i x'_i \\ t_i y'_i \\ t_i \end{bmatrix} = \texttt{map\_matrix} \cdot \begin{bmatrix} x_i \\ y_i \\ 1 \end{bmatrix}
where
.. math::
dst(i)=(x'_i,y'_i),
src(i)=(x_i, y_i),
i=0,1,2
See also:
:func:`findHomography`
,
:func:`warpPerspective`
,
:func:`perspectiveTransform`
.. index:: getRectSubPix
cv::getRectSubPix
-----------------
`id=0.0571919909094 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/getRectSubPix>`__
.. cfunction:: void getRectSubPix( const Mat\& image, Size patchSize, Point2f center, Mat\& dst, int patchType=-1 )
Retrieves the pixel rectangle from an image with sub-pixel accuracy
:param src: Source image
:param patchSize: Size of the extracted patch
:param center: Floating point coordinates of the extracted rectangle center within the source image. The center must be inside the image
:param dst: The extracted patch; will have the size ``patchSize`` and the same number of channels as ``src``
:param patchType: The depth of the extracted pixels. By default they will have the same depth as ``src``
The function
``getRectSubPix``
extracts pixels from
``src``
:
.. math::
dst(x, y) = src(x + \texttt{center.x} - ( \texttt{dst.cols} -1)*0.5, y + \texttt{center.y} - ( \texttt{dst.rows} -1)*0.5)
where the values of the pixels at non-integer coordinates are retrieved
using bilinear interpolation. Every channel of multiple-channel
images is processed independently. While the rectangle center
must be inside the image, parts of the rectangle may be
outside. In this case, the replication border mode (see
:func:`borderInterpolate`
) is used to extrapolate
the pixel values outside of the image.
See also:
:func:`warpAffine`
,
:func:`warpPerspective`
.. index:: getRotationMatrix2D
cv::getRotationMatrix2D
-----------------------
`id=0.641646199188 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/getRotationMatrix2D>`__
.. cfunction:: Mat getRotationMatrix2D( Point2f center, double angle, double scale )
Calculates the affine matrix of 2d rotation.
:param center: Center of the rotation in the source image
:param angle: The rotation angle in degrees. Positive values mean counter-clockwise rotation (the coordinate origin is assumed to be the top-left corner)
:param scale: Isotropic scale factor
The function calculates the following matrix:
.. math::
\begin{bmatrix} \alpha & \beta & (1- \alpha ) \cdot \texttt{center.x} - \beta \cdot \texttt{center.y} \\ - \beta & \alpha & \beta \cdot \texttt{center.x} - (1- \alpha ) \cdot \texttt{center.y} \end{bmatrix}
where
.. math::
\begin{array}{l} \alpha = \texttt{scale} \cdot \cos \texttt{angle} , \\ \beta = \texttt{scale} \cdot \sin \texttt{angle} \end{array}
The transformation maps the rotation center to itself. If this is not the purpose, the shift should be adjusted.
See also:
:func:`getAffineTransform`
,
:func:`warpAffine`
,
:func:`transform`
.. index:: invertAffineTransform
cv::invertAffineTransform
-------------------------
`id=0.772575709646 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/invertAffineTransform>`__
.. cfunction:: void invertAffineTransform(const Mat\& M, Mat\& iM)
Inverts an affine transformation
:param M: The original affine transformation
:param iM: The output reverse affine transformation
The function computes inverse affine transformation represented by
:math:`2 \times 3`
matrix
``M``
:
.. math::
\begin{bmatrix} a_{11} & a_{12} & b_1 \\ a_{21} & a_{22} & b_2 \end{bmatrix}
The result will also be a
:math:`2 \times 3`
matrix of the same type as
``M``
.
.. index:: remap
cv::remap
---------
`id=0.948217317394 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/remap>`__
.. cfunction:: void remap( const Mat\& src, Mat\& dst, const Mat\& map1, const Mat\& map2, int interpolation, int borderMode=BORDER_CONSTANT, const Scalar\& borderValue=Scalar())
Applies a generic geometrical transformation to an image.
:param src: Source image
:param dst: Destination image. It will have the same size as ``map1`` and the same type as ``src``
:param map1: The first map of either ``(x,y)`` points or just ``x`` values having type ``CV_16SC2`` , ``CV_32FC1`` or ``CV_32FC2`` . See :func:`convertMaps` for converting floating point representation to fixed-point for speed.
:param map2: The second map of ``y`` values having type ``CV_16UC1`` , ``CV_32FC1`` or none (empty map if map1 is ``(x,y)`` points), respectively
:param interpolation: The interpolation method, see :func:`resize` . The method ``INTER_AREA`` is not supported by this function
:param borderMode: The pixel extrapolation method, see :func:`borderInterpolate` . When the \ ``borderMode=BORDER_TRANSPARENT`` , it means that the pixels in the destination image that corresponds to the "outliers" in the source image are not modified by the function
:param borderValue: A value used in the case of a constant border. By default it is 0
The function
``remap``
transforms the source image using the specified map:
.. math::
\texttt{dst} (x,y) = \texttt{src} (map_x(x,y),map_y(x,y))
Where values of pixels with non-integer coordinates are computed using one of the available interpolation methods.
:math:`map_x`
and
:math:`map_y`
can be encoded as separate floating-point maps in
:math:`map_1`
and
:math:`map_2`
respectively, or interleaved floating-point maps of
:math:`(x,y)`
in
:math:`map_1`
, or
fixed-point maps made by using
:func:`convertMaps`
. The reason you might want to convert from floating to fixed-point
representations of a map is that they can yield much faster (~2x) remapping operations. In the converted case,
:math:`map_1`
contains pairs
``(cvFloor(x), cvFloor(y))``
and
:math:`map_2`
contains indices in a table of interpolation coefficients.
This function can not operate in-place.
.. index:: resize
cv::resize
----------
`id=0.927768028114 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/resize>`__
.. cfunction:: void resize( const Mat\& src, Mat\& dst, Size dsize, double fx=0, double fy=0, int interpolation=INTER_LINEAR )
Resizes an image
:param src: Source image
:param dst: Destination image. It will have size ``dsize`` (when it is non-zero) or the size computed from ``src.size()``
and ``fx`` and ``fy`` . The type of ``dst`` will be the same as of ``src`` .
:param dsize: The destination image size. If it is zero, then it is computed as:
.. math::
\texttt{dsize = Size(round(fx*src.cols), round(fy*src.rows))}
.
Either ``dsize`` or both ``fx`` or ``fy`` must be non-zero.
:param fx: The scale factor along the horizontal axis. When 0, it is computed as
.. math::
\texttt{(double)dsize.width/src.cols}
:param fy: The scale factor along the vertical axis. When 0, it is computed as
.. math::
\texttt{(double)dsize.height/src.rows}
:param interpolation: The interpolation method:
* **INTER_NEAREST** nearest-neighbor interpolation
* **INTER_LINEAR** bilinear interpolation (used by default)
* **INTER_AREA** resampling using pixel area relation. It may be the preferred method for image decimation, as it gives moire-free results. But when the image is zoomed, it is similar to the ``INTER_NEAREST`` method
* **INTER_CUBIC** bicubic interpolation over 4x4 pixel neighborhood
* **INTER_LANCZOS4** Lanczos interpolation over 8x8 pixel neighborhood
The function
``resize``
resizes an image
``src``
down to or up to the specified size.
Note that the initial
``dst``
type or size are not taken into account. Instead the size and type are derived from the
``src``
,
``dsize``
,
``fx``
and
``fy``
. If you want to resize
``src``
so that it fits the pre-created
``dst``
, you may call the function as:
::
// explicitly specify dsize=dst.size(); fx and fy will be computed from that.
resize(src, dst, dst.size(), 0, 0, interpolation);
..
If you want to decimate the image by factor of 2 in each direction, you can call the function this way:
::
// specify fx and fy and let the function to compute the destination image size.
resize(src, dst, Size(), 0.5, 0.5, interpolation);
..
See also:
:func:`warpAffine`
,
:func:`warpPerspective`
,
:func:`remap`
.
.. index:: warpAffine
cv::warpAffine
--------------
`id=0.796627178227 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/warpAffine>`__
.. cfunction:: void warpAffine( const Mat\& src, Mat\& dst, const Mat\& M, Size dsize, int flags=INTER_LINEAR, int borderMode=BORDER_CONSTANT, const Scalar\& borderValue=Scalar())
Applies an affine transformation to an image.
:param src: Source image
:param dst: Destination image; will have size ``dsize`` and the same type as ``src``
:param M: :math:`2\times 3` transformation matrix
:param dsize: Size of the destination image
:param flags: A combination of interpolation methods, see :func:`resize` , and the optional flag ``WARP_INVERSE_MAP`` that means that ``M`` is the inverse transformation ( :math:`\texttt{dst}\rightarrow\texttt{src}` )
:param borderMode: The pixel extrapolation method, see :func:`borderInterpolate` . When the \ ``borderMode=BORDER_TRANSPARENT`` , it means that the pixels in the destination image that corresponds to the "outliers" in the source image are not modified by the function
:param borderValue: A value used in case of a constant border. By default it is 0
The function
``warpAffine``
transforms the source image using the specified matrix:
.. math::
\texttt{dst} (x,y) = \texttt{src} ( \texttt{M} _{11} x + \texttt{M} _{12} y + \texttt{M} _{13}, \texttt{M} _{21} x + \texttt{M} _{22} y + \texttt{M} _{23})
when the flag
``WARP_INVERSE_MAP``
is set. Otherwise, the transformation is first inverted with
:func:`invertAffineTransform`
and then put in the formula above instead of
``M``
.
The function can not operate in-place.
See also:
:func:`warpPerspective`
,
:func:`resize`
,
:func:`remap`
,
:func:`getRectSubPix`
,
:func:`transform`
.. index:: warpPerspective
cv::warpPerspective
-------------------
`id=0.733510667556 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/warpPerspective>`__
.. cfunction:: void warpPerspective( const Mat\& src, Mat\& dst, const Mat\& M, Size dsize, int flags=INTER_LINEAR, int borderMode=BORDER_CONSTANT, const Scalar\& borderValue=Scalar())
Applies a perspective transformation to an image.
:param src: Source image
:param dst: Destination image; will have size ``dsize`` and the same type as ``src``
:param M: :math:`3\times 3` transformation matrix
:param dsize: Size of the destination image
:param flags: A combination of interpolation methods, see :func:`resize` , and the optional flag ``WARP_INVERSE_MAP`` that means that ``M`` is the inverse transformation ( :math:`\texttt{dst}\rightarrow\texttt{src}` )
:param borderMode: The pixel extrapolation method, see :func:`borderInterpolate` . When the \ ``borderMode=BORDER_TRANSPARENT`` , it means that the pixels in the destination image that corresponds to the "outliers" in the source image are not modified by the function
:param borderValue: A value used in case of a constant border. By default it is 0
The function
``warpPerspective``
transforms the source image using the specified matrix:
.. math::
\texttt{dst} (x,y) = \texttt{src} \left ( \frac{M_{11} x + M_{12} y + M_{13}}{M_{31} x + M_{32} y + M_{33}} ,
\frac{M_{21} x + M_{22} y + M_{23}}{M_{31} x + M_{32} y + M_{33}} \right )
when the flag
``WARP_INVERSE_MAP``
is set. Otherwise, the transformation is first inverted with
:func:`invert`
and then put in the formula above instead of
``M``
.
The function can not operate in-place.
See also:
:func:`warpAffine`
,
:func:`resize`
,
:func:`remap`
,
:func:`getRectSubPix`
,
:func:`perspectiveTransform`

404
modules/imgproc/doc/histograms.rst Normal file
View File

@ -0,0 +1,404 @@
Histograms
==========
.. highlight:: cpp
.. index:: calcHist
cv::calcHist
------------
`id=0.023612377096 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/calcHist>`__
.. cfunction:: void calcHist( const Mat* arrays, int narrays, const int* channels, const Mat\& mask, MatND\& hist, int dims, const int* histSize, const float** ranges, bool uniform=true, bool accumulate=false )
.. cfunction:: void calcHist( const Mat* arrays, int narrays, const int* channels, const Mat\& mask, SparseMat\& hist, int dims, const int* histSize, const float** ranges, bool uniform=true, bool accumulate=false )
Calculates histogram of a set of arrays
:param arrays: Source arrays. They all should have the same depth, ``CV_8U`` or ``CV_32F`` , and the same size. Each of them can have an arbitrary number of channels
:param narrays: The number of source arrays
:param channels: The list of ``dims`` channels that are used to compute the histogram. The first array channels are numerated from 0 to ``arrays[0].channels()-1`` , the second array channels are counted from ``arrays[0].channels()`` to ``arrays[0].channels() + arrays[1].channels()-1`` etc.
:param mask: The optional mask. If the matrix is not empty, it must be 8-bit array of the same size as ``arrays[i]`` . The non-zero mask elements mark the array elements that are counted in the histogram
:param hist: The output histogram, a dense or sparse ``dims`` -dimensional array
:param dims: The histogram dimensionality; must be positive and not greater than ``CV_MAX_DIMS`` (=32 in the current OpenCV version)
:param histSize: The array of histogram sizes in each dimension
:param ranges: The array of ``dims`` arrays of the histogram bin boundaries in each dimension. When the histogram is uniform ( ``uniform`` =true), then for each dimension ``i`` it's enough to specify the lower (inclusive) boundary :math:`L_0` of the 0-th histogram bin and the upper (exclusive) boundary :math:`U_{\texttt{histSize}[i]-1}` for the last histogram bin ``histSize[i]-1`` . That is, in the case of uniform histogram each of ``ranges[i]`` is an array of 2 elements. When the histogram is not uniform ( ``uniform=false`` ), then each of ``ranges[i]`` contains ``histSize[i]+1`` elements: :math:`L_0, U_0=L_1, U_1=L_2, ..., U_{\texttt{histSize[i]}-2}=L_{\texttt{histSize[i]}-1}, U_{\texttt{histSize[i]}-1}` . The array elements, which are not between :math:`L_0` and :math:`U_{\texttt{histSize[i]}-1}` , are not counted in the histogram
:param uniform: Indicates whether the histogram is uniform or not, see above
:param accumulate: Accumulation flag. If it is set, the histogram is not cleared in the beginning (when it is allocated). This feature allows user to compute a single histogram from several sets of arrays, or to update the histogram in time
The functions
``calcHist``
calculate the histogram of one or more
arrays. The elements of a tuple that is used to increment
a histogram bin are taken at the same location from the corresponding
input arrays. The sample below shows how to compute 2D Hue-Saturation histogram for a color imag
::
#include <cv.h>
#include <highgui.h>
using namespace cv;
int main( int argc, char** argv )
{
Mat src, hsv;
if( argc != 2 || !(src=imread(argv[1], 1)).data )
return -1;
cvtColor(src, hsv, CV_BGR2HSV);
// let's quantize the hue to 30 levels
// and the saturation to 32 levels
int hbins = 30, sbins = 32;
int histSize[] = {hbins, sbins};
// hue varies from 0 to 179, see cvtColor
float hranges[] = { 0, 180 };
// saturation varies from 0 (black-gray-white) to
// 255 (pure spectrum color)
float sranges[] = { 0, 256 };
const float* ranges[] = { hranges, sranges };
MatND hist;
// we compute the histogram from the 0-th and 1-st channels
int channels[] = {0, 1};
calcHist( &hsv, 1, channels, Mat(), // do not use mask
hist, 2, histSize, ranges,
true, // the histogram is uniform
false );
double maxVal=0;
minMaxLoc(hist, 0, &maxVal, 0, 0);
int scale = 10;
Mat histImg = Mat::zeros(sbins*scale, hbins*10, CV_8UC3);
for( int h = 0; h < hbins; h++ )
for( int s = 0; s < sbins; s++ )
{
float binVal = hist.at<float>(h, s);
int intensity = cvRound(binVal*255/maxVal);
rectangle( histImg, Point(h*scale, s*scale),
Point( (h+1)*scale - 1, (s+1)*scale - 1),
Scalar::all(intensity),
CV_FILLED );
}
namedWindow( "Source", 1 );
imshow( "Source", src );
namedWindow( "H-S Histogram", 1 );
imshow( "H-S Histogram", histImg );
waitKey();
}
..
.. index:: calcBackProject
cv::calcBackProject
-------------------
`id=0.307675677402 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/calcBackProject>`__
.. cfunction:: void calcBackProject( const Mat* arrays, int narrays, const int* channels, const MatND\& hist, Mat\& backProject, const float** ranges, double scale=1, bool uniform=true )
.. cfunction:: void calcBackProject( const Mat* arrays, int narrays, const int* channels, const SparseMat\& hist, Mat\& backProject, const float** ranges, double scale=1, bool uniform=true )
Calculates the back projection of a histogram.
:param arrays: Source arrays. They all should have the same depth, ``CV_8U`` or ``CV_32F`` , and the same size. Each of them can have an arbitrary number of channels
:param narrays: The number of source arrays
:param channels: The list of channels that are used to compute the back projection. The number of channels must match the histogram dimensionality. The first array channels are numerated from 0 to ``arrays[0].channels()-1`` , the second array channels are counted from ``arrays[0].channels()`` to ``arrays[0].channels() + arrays[1].channels()-1`` etc.
:param hist: The input histogram, a dense or sparse
:param backProject: Destination back projection aray; will be a single-channel array of the same size and the same depth as ``arrays[0]``
:param ranges: The array of arrays of the histogram bin boundaries in each dimension. See :func:`calcHist`
:param scale: The optional scale factor for the output back projection
:param uniform: Indicates whether the histogram is uniform or not, see above
The functions
``calcBackProject``
calculate the back project of the histogram. That is, similarly to
``calcHist``
, at each location
``(x, y)``
the function collects the values from the selected channels in the input images and finds the corresponding histogram bin. But instead of incrementing it, the function reads the bin value, scales it by
``scale``
and stores in
``backProject(x,y)``
. In terms of statistics, the function computes probability of each element value in respect with the empirical probability distribution represented by the histogram. Here is how, for example, you can find and track a bright-colored object in a scene:
#.
Before the tracking, show the object to the camera such that covers almost the whole frame. Calculate a hue histogram. The histogram will likely have a strong maximums, corresponding to the dominant colors in the object.
#.
During the tracking, calculate back projection of a hue plane of each input video frame using that pre-computed histogram. Threshold the back projection to suppress weak colors. It may also have sense to suppress pixels with non sufficient color saturation and too dark or too bright pixels.
#.
Find connected components in the resulting picture and choose, for example, the largest component.
That is the approximate algorithm of
:func:`CAMShift`
color object tracker.
See also:
:func:`calcHist`
.. index:: compareHist
cv::compareHist
---------------
`id=0.679842058679 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/compareHist>`__
.. cfunction:: double compareHist( const MatND\& H1, const MatND\& H2, int method )
.. cfunction:: double compareHist( const SparseMat\& H1, const SparseMat\& H2, int method )
Compares two histograms
:param H1: The first compared histogram
:param H2: The second compared histogram of the same size as ``H1``
:param method: The comparison method, one of the following:
* **CV_COMP_CORREL** Correlation
* **CV_COMP_CHISQR** Chi-Square
* **CV_COMP_INTERSECT** Intersection
* **CV_COMP_BHATTACHARYYA** Bhattacharyya distance
The functions
``compareHist``
compare two dense or two sparse histograms using the specified method:
* Correlation (method=CV\_COMP\_CORREL)
.. math::
d(H_1,H_2) = \frac{\sum_I (H_1(I) - \bar{H_1}) (H_2(I) - \bar{H_2})}{\sqrt{\sum_I(H_1(I) - \bar{H_1})^2 \sum_I(H_2(I) - \bar{H_2})^2}}
where
.. math::
\bar{H_k} = \frac{1}{N} \sum _J H_k(J)
and
:math:`N`
is the total number of histogram bins.
* Chi-Square (method=CV\_COMP\_CHISQR)
.. math::
d(H_1,H_2) = \sum _I \frac{\left(H_1(I)-H_2(I)\right)^2}{H_1(I)+H_2(I)}
* Intersection (method=CV\_COMP\_INTERSECT)
.. math::
d(H_1,H_2) = \sum _I \min (H_1(I), H_2(I))
* Bhattacharyya distance (method=CV\_COMP\_BHATTACHARYYA)
.. math::
d(H_1,H_2) = \sqrt{1 - \frac{1}{\sqrt{\bar{H_1} \bar{H_2} N^2}} \sum_I \sqrt{H_1(I) \cdot H_2(I)}}
The function returns
:math:`d(H_1, H_2)`
.
While the function works well with 1-, 2-, 3-dimensional dense histograms, it may not be suitable for high-dimensional sparse histograms, where, because of aliasing and sampling problems the coordinates of non-zero histogram bins can slightly shift. To compare such histograms or more general sparse configurations of weighted points, consider using the
:func:`calcEMD`
function.
.. index:: equalizeHist
cv::equalizeHist
----------------
`id=0.125539341699 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/equalizeHist>`__
.. cfunction:: void equalizeHist( const Mat\& src, Mat\& dst )
Equalizes the histogram of a grayscale image.
:param src: The source 8-bit single channel image
:param dst: The destination image; will have the same size and the same type as ``src``
The function equalizes the histogram of the input image using the following algorithm:
#.
calculate the histogram
:math:`H`
for
``src``
.
#.
normalize the histogram so that the sum of histogram bins is 255.
#.
compute the integral of the histogram:
.. math::
H'_i = \sum _{0 \le j < i} H(j)
#.
transform the image using
:math:`H'`
as a look-up table:
:math:`\texttt{dst}(x,y) = H'(\texttt{src}(x,y))`
The algorithm normalizes the brightness and increases the contrast of the image.

16
modules/imgproc/doc/imgproc.rst Normal file
View File

@ -0,0 +1,16 @@
****************
Image Processing
****************
.. toctree::
:maxdepth: 2
histograms
filtering
geometric_transformations
miscellaneous_transformations
structural_analysis_and_shape_descriptors
planar_subdivisions
motion_analysis_and_object_tracking
feature_detection
object_detection

1440
modules/imgproc/doc/miscellaneous_transformations.rst Normal file
View File

File diff suppressed because it is too large Load Diff

227
modules/imgproc/doc/motion_analysis_and_object_tracking.rst Normal file
View File

@ -0,0 +1,227 @@
Motion Analysis and Object Tracking
===================================
.. highlight:: cpp
.. index:: accumulate
cv::accumulate
--------------
`id=0.681079907994 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/accumulate>`__
.. cfunction:: void accumulate( const Mat\& src, Mat\& dst, const Mat\& mask=Mat() )
Adds image to the accumulator.
:param src: The input image, 1- or 3-channel, 8-bit or 32-bit floating point
:param dst: The accumulator image with the same number of channels as input image, 32-bit or 64-bit floating-point
:param mask: Optional operation mask
The function adds
``src``
, or some of its elements, to
``dst``
:
.. math::
\texttt{dst} (x,y) \leftarrow \texttt{dst} (x,y) + \texttt{src} (x,y) \quad \text{if} \quad \texttt{mask} (x,y) \ne 0
The function supports multi-channel images; each channel is processed independently.
The functions
``accumulate*``
can be used, for example, to collect statistic of background of a scene, viewed by a still camera, for the further foreground-background segmentation.
See also:
:func:`accumulateSquare`
,
:func:`accumulateProduct`
,
:func:`accumulateWeighted`
.. index:: accumulateSquare
cv::accumulateSquare
--------------------
`id=0.655955936814 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/accumulateSquare>`__
.. cfunction:: void accumulateSquare( const Mat\& src, Mat\& dst, const Mat\& mask=Mat() )
Adds the square of the source image to the accumulator.
:param src: The input image, 1- or 3-channel, 8-bit or 32-bit floating point
:param dst: The accumulator image with the same number of channels as input image, 32-bit or 64-bit floating-point
:param mask: Optional operation mask
The function adds the input image
``src``
or its selected region, raised to power 2, to the accumulator
``dst``
:
.. math::
\texttt{dst} (x,y) \leftarrow \texttt{dst} (x,y) + \texttt{src} (x,y)^2 \quad \text{if} \quad \texttt{mask} (x,y) \ne 0
The function supports multi-channel images; each channel is processed independently.
See also:
:func:`accumulateSquare`
,
:func:`accumulateProduct`
,
:func:`accumulateWeighted`
.. index:: accumulateProduct
cv::accumulateProduct
---------------------
`id=0.866927763669 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/accumulateProduct>`__
.. cfunction:: void accumulateProduct( const Mat\& src1, const Mat\& src2, Mat\& dst, const Mat\& mask=Mat() )
Adds the per-element product of two input images to the accumulator.
:param src1: The first input image, 1- or 3-channel, 8-bit or 32-bit floating point
:param src2: The second input image of the same type and the same size as ``src1``
:param dst: Accumulator with the same number of channels as input images, 32-bit or 64-bit floating-point
:param mask: Optional operation mask
The function adds the product of 2 images or their selected regions to the accumulator
``dst``
:
.. math::
\texttt{dst} (x,y) \leftarrow \texttt{dst} (x,y) + \texttt{src1} (x,y) \cdot \texttt{src2} (x,y) \quad \text{if} \quad \texttt{mask} (x,y) \ne 0
The function supports multi-channel images; each channel is processed independently.
See also:
:func:`accumulate`
,
:func:`accumulateSquare`
,
:func:`accumulateWeighted`
.. index:: accumulateWeighted
cv::accumulateWeighted
----------------------
`id=0.956120320296 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/accumulateWeighted>`__
.. cfunction:: void accumulateWeighted( const Mat\& src, Mat\& dst, double alpha, const Mat\& mask=Mat() )
Updates the running average.
:param src: The input image, 1- or 3-channel, 8-bit or 32-bit floating point
:param dst: The accumulator image with the same number of channels as input image, 32-bit or 64-bit floating-point
:param alpha: Weight of the input image
:param mask: Optional operation mask
The function calculates the weighted sum of the input image
``src``
and the accumulator
``dst``
so that
``dst``
becomes a running average of frame sequence:
.. math::
\texttt{dst} (x,y) \leftarrow (1- \texttt{alpha} ) \cdot \texttt{dst} (x,y) + \texttt{alpha} \cdot \texttt{src} (x,y) \quad \text{if} \quad \texttt{mask} (x,y) \ne 0
that is,
``alpha``
regulates the update speed (how fast the accumulator "forgets" about earlier images).
The function supports multi-channel images; each channel is processed independently.
See also:
:func:`accumulate`
,
:func:`accumulateSquare`
,
:func:`accumulateProduct`

146
modules/imgproc/doc/object_detection.rst Normal file
View File

@ -0,0 +1,146 @@
Object Detection
================
.. highlight:: cpp
.. index:: matchTemplate
cv::matchTemplate
-----------------
`id=0.821462672178 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/imgproc/matchTemplate>`__
.. cfunction:: void matchTemplate( const Mat\& image, const Mat\& templ, Mat\& result, int method )
Compares a template against overlapped image regions.
:param image: Image where the search is running; should be 8-bit or 32-bit floating-point
:param templ: Searched template; must be not greater than the source image and have the same data type
:param result: A map of comparison results; will be single-channel 32-bit floating-point.
If ``image`` is :math:`W \times H` and ``templ`` is :math:`w \times h` then ``result`` will be :math:`(W-w+1) \times (H-h+1)`
:param method: Specifies the comparison method (see below)
The function slides through
``image``
, compares the
overlapped patches of size
:math:`w \times h`
against
``templ``
using the specified method and stores the comparison results to
``result``
. Here are the formulas for the available comparison
methods (
:math:`I`
denotes
``image``
,
:math:`T`
``template``
,
:math:`R`
``result``
). The summation is done over template and/or the
image patch:
:math:`x' = 0...w-1, y' = 0...h-1`
* method=CV\_TM\_SQDIFF
.. math::
R(x,y)= \sum _{x',y'} (T(x',y')-I(x+x',y+y'))^2
* method=CV\_TM\_SQDIFF\_NORMED
.. math::
R(x,y)= \frac{\sum_{x',y'} (T(x',y')-I(x+x',y+y'))^2}{\sqrt{\sum_{x',y'}T(x',y')^2 \cdot \sum_{x',y'} I(x+x',y+y')^2}}
* method=CV\_TM\_CCORR
.. math::
R(x,y)= \sum _{x',y'} (T(x',y') \cdot I(x+x',y+y'))
* method=CV\_TM\_CCORR\_NORMED
.. math::
R(x,y)= \frac{\sum_{x',y'} (T(x',y') \cdot I'(x+x',y+y'))}{\sqrt{\sum_{x',y'}T(x',y')^2 \cdot \sum_{x',y'} I(x+x',y+y')^2}}
* method=CV\_TM\_CCOEFF
.. math::
R(x,y)= \sum _{x',y'} (T'(x',y') \cdot I(x+x',y+y'))
where
.. math::
\begin{array}{l} T'(x',y')=T(x',y') - 1/(w \cdot h) \cdot \sum _{x'',y''} T(x'',y'') \\ I'(x+x',y+y')=I(x+x',y+y') - 1/(w \cdot h) \cdot \sum _{x'',y''} I(x+x'',y+y'') \end{array}
* method=CV\_TM\_CCOEFF\_NORMED
.. math::
R(x,y)= \frac{ \sum_{x',y'} (T'(x',y') \cdot I'(x+x',y+y')) }{ \sqrt{\sum_{x',y'}T'(x',y')^2 \cdot \sum_{x',y'} I'(x+x',y+y')^2} }
After the function finishes the comparison, the best matches can be found as global minimums (when
``CV_TM_SQDIFF``
was used) or maximums (when
``CV_TM_CCORR``
or
``CV_TM_CCOEFF``
was used) using the
:func:`minMaxLoc`
function. In the case of a color image, template summation in the numerator and each sum in the denominator is done over all of the channels (and separate mean values are used for each channel). That is, the function can take a color template and a color image; the result will still be a single-channel image, which is easier to analyze.

6
modules/imgproc/doc/planar_subdivisions.rst Normal file
View File

@ -0,0 +1,6 @@
Planar Subdivisions
===================
.. highlight:: cpp

1086
modules/imgproc/doc/structural_analysis_and_shape_descriptors.rst Normal file
View File

File diff suppressed because it is too large Load Diff

31
modules/index.rst Normal file
View File

@ -0,0 +1,31 @@
.. opencvstd documentation master file, created by
sphinx-quickstart on Mon Feb 14 00:30:43 2011.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to opencvstd's documentation!
=====================================
Contents:
.. toctree::
:maxdepth: 2
core/doc/intro.rst
core/doc/core.rst
imgproc/doc/imgproc.rst
highgui/doc/highgui.rst
video/doc/video.rst
calib3d/doc/calib3d.rst
features2d/doc/features2d.rst
objdetect/doc/objdetect.rst
ml/doc/ml.rst
gpu/doc/gpu.rst
Indices and tables
==================
* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`

414
modules/ml/doc/boosting.rst Normal file
View File

@ -0,0 +1,414 @@
Boosting
========
.. highlight:: cpp
A common machine learning task is supervised learning. In supervised learning, the goal is to learn the functional relationship
:math:`F: y = F(x)`
between the input
:math:`x`
and the output
:math:`y`
. Predicting the qualitative output is called classification, while predicting the quantitative output is called regression.
Boosting is a powerful learning concept, which provide a solution to the supervised classification learning task. It combines the performance of many "weak" classifiers to produce a powerful 'committee'
:ref:`HTF01`
. A weak classifier is only required to be better than chance, and thus can be very simple and computationally inexpensive. Many of them smartly combined, however, results in a strong classifier, which often outperforms most 'monolithic' strong classifiers such as SVMs and Neural Networks.
Decision trees are the most popular weak classifiers used in boosting schemes. Often the simplest decision trees with only a single split node per tree (called stumps) are sufficient.
The boosted model is based on
:math:`N`
training examples
:math:`{(x_i,y_i)}1N`
with
:math:`x_i \in{R^K}`
and
:math:`y_i \in{-1, +1}`
.
:math:`x_i`
is a
:math:`K`
-component vector. Each component encodes a feature relevant for the learning task at hand. The desired two-class output is encoded as -1 and +1.
Different variants of boosting are known such as Discrete Adaboost, Real AdaBoost, LogitBoost, and Gentle AdaBoost
:ref:`FHT98`
. All of them are very similar in their overall structure. Therefore, we will look only at the standard two-class Discrete AdaBoost algorithm as shown in the box below. Each sample is initially assigned the same weight (step 2). Next a weak classifier
:math:`f_{m(x)}`
is trained on the weighted training data (step 3a). Its weighted training error and scaling factor
:math:`c_m`
is computed (step 3b). The weights are increased for training samples, which have been misclassified (step 3c). All weights are then normalized, and the process of finding the next weak classifier continues for another
:math:`M`
-1 times. The final classifier
:math:`F(x)`
is the sign of the weighted sum over the individual weak classifiers (step 4).
*
Given
:math:`N`
examples
:math:`{(x_i,y_i)}1N`
with
:math:`x_i \in{R^K}, y_i \in{-1, +1}`
.
*
Start with weights
:math:`w_i = 1/N, i = 1,...,N`
.
*
Repeat for
:math:`m`
=
:math:`1,2,...,M`
:
*
Fit the classifier
:math:`f_m(x) \in{-1,1}`
, using weights
:math:`w_i`
on the training data.
*
Compute
:math:`err_m = E_w [1_{(y =\neq f_m(x))}], c_m = log((1 - err_m)/err_m)`
.
*
Set
:math:`w_i \Leftarrow w_i exp[c_m 1_{(y_i \neq f_m(x_i))}], i = 1,2,...,N,`
and renormalize so that
:math:`\Sigma i w_i = 1`
.
*
Output the classifier sign
:math:`[\Sigma m = 1M c_m f_m(x)]`
.
Two-class Discrete AdaBoost Algorithm: Training (steps 1 to 3) and Evaluation (step 4)
**NOTE:**
As well as the classical boosting methods, the current implementation supports 2-class classifiers only. For M
:math:`>`
2 classes there is the
**AdaBoost.MH**
algorithm, described in
:ref:`FHT98`
, that reduces the problem to the 2-class problem, yet with a much larger training set.
In order to reduce computation time for boosted models without substantially losing accuracy, the influence trimming technique may be employed. As the training algorithm proceeds and the number of trees in the ensemble is increased, a larger number of the training samples are classified correctly and with increasing confidence, thereby those samples receive smaller weights on the subsequent iterations. Examples with very low relative weight have small impact on training of the weak classifier. Thus such examples may be excluded during the weak classifier training without having much effect on the induced classifier. This process is controlled with the weight
_
trim
_
rate parameter. Only examples with the summary fraction weight
_
trim
_
rate of the total weight mass are used in the weak classifier training. Note that the weights for
**all**
training examples are recomputed at each training iteration. Examples deleted at a particular iteration may be used again for learning some of the weak classifiers further
:ref:`FHT98`
.
**[HTF01] Hastie, T., Tibshirani, R., Friedman, J. H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Series in Statistics. 2001.**
**[FHT98] Friedman, J. H., Hastie, T. and Tibshirani, R. Additive Logistic Regression: a Statistical View of Boosting. Technical Report, Dept. of Statistics, Stanford University, 1998.**
.. index:: CvBoostParams
.. _CvBoostParams:
CvBoostParams
-------------
`id=0.227680975216 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoostParams>`__
.. ctype:: CvBoostParams
Boosting training parameters.
::
struct CvBoostParams : public CvDTreeParams
{
int boost_type;
int weak_count;
int split_criteria;
double weight_trim_rate;
CvBoostParams();
CvBoostParams( int boost_type, int weak_count, double weight_trim_rate,
int max_depth, bool use_surrogates, const float* priors );
};
..
The structure is derived from
:ref:`CvDTreeParams`
, but not all of the decision tree parameters are supported. In particular, cross-validation is not supported.
.. index:: CvBoostTree
.. _CvBoostTree:
CvBoostTree
-----------
`id=0.166418635075 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoostTree>`__
.. ctype:: CvBoostTree
Weak tree classifier.
::
class CvBoostTree: public CvDTree
{
public:
CvBoostTree();
virtual ~CvBoostTree();
virtual bool train( CvDTreeTrainData* _train_data,
const CvMat* subsample_idx, CvBoost* ensemble );
virtual void scale( double s );
virtual void read( CvFileStorage* fs, CvFileNode* node,
CvBoost* ensemble, CvDTreeTrainData* _data );
virtual void clear();
protected:
...
CvBoost* ensemble;
};
..
The weak classifier, a component of the boosted tree classifier
:ref:`CvBoost`
, is a derivative of
:ref:`CvDTree`
. Normally, there is no need to use the weak classifiers directly, however they can be accessed as elements of the sequence
``CvBoost::weak``
, retrieved by
``CvBoost::get_weak_predictors``
.
Note, that in the case of LogitBoost and Gentle AdaBoost each weak predictor is a regression tree, rather than a classification tree. Even in the case of Discrete AdaBoost and Real AdaBoost the
``CvBoostTree::predict``
return value (
``CvDTreeNode::value``
) is not the output class label; a negative value "votes" for class
#
0, a positive - for class
#
1. And the votes are weighted. The weight of each individual tree may be increased or decreased using the method
``CvBoostTree::scale``
.
.. index:: CvBoost
.. _CvBoost:
CvBoost
-------
`id=0.0263891264552 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoost>`__
.. ctype:: CvBoost
Boosted tree classifier.
::
class CvBoost : public CvStatModel
{
public:
// Boosting type
enum { DISCRETE=0, REAL=1, LOGIT=2, GENTLE=3 };
// Splitting criteria
enum { DEFAULT=0, GINI=1, MISCLASS=3, SQERR=4 };
CvBoost();
virtual ~CvBoost();
CvBoost( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
CvBoostParams params=CvBoostParams() );
virtual bool train( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
CvBoostParams params=CvBoostParams(),
bool update=false );
virtual float predict( const CvMat* _sample, const CvMat* _missing=0,
CvMat* weak_responses=0, CvSlice slice=CV_WHOLE_SEQ,
bool raw_mode=false ) const;
virtual void prune( CvSlice slice );
virtual void clear();
virtual void write( CvFileStorage* storage, const char* name );
virtual void read( CvFileStorage* storage, CvFileNode* node );
CvSeq* get_weak_predictors();
const CvBoostParams& get_params() const;
...
protected:
virtual bool set_params( const CvBoostParams& _params );
virtual void update_weights( CvBoostTree* tree );
virtual void trim_weights();
virtual void write_params( CvFileStorage* fs );
virtual void read_params( CvFileStorage* fs, CvFileNode* node );
CvDTreeTrainData* data;
CvBoostParams params;
CvSeq* weak;
...
};
..
.. index:: CvBoost::train
.. _CvBoost::train:
CvBoost::train
--------------
`id=0.756448003801 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoost%3A%3Atrain>`__
.. cfunction:: bool CvBoost::train( const CvMat* _train_data, int _tflag, const CvMat* _responses, const CvMat* _var_idx=0, const CvMat* _sample_idx=0, const CvMat* _var_type=0, const CvMat* _missing_mask=0, CvBoostParams params=CvBoostParams(), bool update=false )
Trains a boosted tree classifier.
The train method follows the common template; the last parameter
``update``
specifies whether the classifier needs to be updated (i.e. the new weak tree classifiers added to the existing ensemble), or the classifier needs to be rebuilt from scratch. The responses must be categorical, i.e. boosted trees can not be built for regression, and there should be 2 classes.
.. index:: CvBoost::predict
.. _CvBoost::predict:
CvBoost::predict
----------------
`id=0.275883150474 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoost%3A%3Apredict>`__
.. cfunction:: float CvBoost::predict( const CvMat* sample, const CvMat* missing=0, CvMat* weak_responses=0, CvSlice slice=CV_WHOLE_SEQ, bool raw_mode=false ) const
Predicts a response for the input sample.
The method
``CvBoost::predict``
runs the sample through the trees in the ensemble and returns the output class label based on the weighted voting.
.. index:: CvBoost::prune
.. _CvBoost::prune:
CvBoost::prune
--------------
`id=0.22443448309 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoost%3A%3Aprune>`__
.. cfunction:: void CvBoost::prune( CvSlice slice )
Removes the specified weak classifiers.
The method removes the specified weak classifiers from the sequence. Note that this method should not be confused with the pruning of individual decision trees, which is currently not supported.
.. index:: CvBoost::get_weak_predictors
.. _CvBoost::get_weak_predictors:
CvBoost::get_weak_predictors
----------------------------
`id=0.670781607621 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvBoost%3A%3Aget_weak_predictors>`__
.. cfunction:: CvSeq* CvBoost::get_weak_predictors()
Returns the sequence of weak tree classifiers.
The method returns the sequence of weak classifiers. Each element of the sequence is a pointer to a
``CvBoostTree``
class (or, probably, to some of its derivatives).

606
modules/ml/doc/decision_trees.rst Normal file
View File

@ -0,0 +1,606 @@
Decision Trees
==============
.. highlight:: cpp
The ML classes discussed in this section implement Classification And Regression Tree algorithms, which are described in
`[Breiman84] <#paper_Breiman84>`_
.
The class
:ref:`CvDTree`
represents a single decision tree that may be used alone, or as a base class in tree ensembles (see
:ref:`Boosting`
and
:ref:`Random Trees`
).
A decision tree is a binary tree (i.e. tree where each non-leaf node has exactly 2 child nodes). It can be used either for classification, when each tree leaf is marked with some class label (multiple leafs may have the same label), or for regression, when each tree leaf is also assigned a constant (so the approximation function is piecewise constant).
Predicting with Decision Trees
------------------------------
To reach a leaf node, and to obtain a response for the input feature
vector, the prediction procedure starts with the root node. From each
non-leaf node the procedure goes to the left (i.e. selects the left
child node as the next observed node), or to the right based on the
value of a certain variable, whose index is stored in the observed
node. The variable can be either ordered or categorical. In the first
case, the variable value is compared with the certain threshold (which
is also stored in the node); if the value is less than the threshold,
the procedure goes to the left, otherwise, to the right (for example,
if the weight is less than 1 kilogram, the procedure goes to the left,
else to the right). And in the second case the discrete variable value is
tested to see if it belongs to a certain subset of values (also stored
in the node) from a limited set of values the variable could take; if
yes, the procedure goes to the left, else - to the right (for example,
if the color is green or red, go to the left, else to the right). That
is, in each node, a pair of entities (variable
_
index, decision
_
rule
(threshold/subset)) is used. This pair is called a split (split on
the variable variable
_
index). Once a leaf node is reached, the value
assigned to this node is used as the output of prediction procedure.
Sometimes, certain features of the input vector are missed (for example, in the darkness it is difficult to determine the object color), and the prediction procedure may get stuck in the certain node (in the mentioned example if the node is split by color). To avoid such situations, decision trees use so-called surrogate splits. That is, in addition to the best "primary" split, every tree node may also be split on one or more other variables with nearly the same results.
Training Decision Trees
-----------------------
The tree is built recursively, starting from the root node. All of the training data (feature vectors and the responses) is used to split the root node. In each node the optimum decision rule (i.e. the best "primary" split) is found based on some criteria (in ML
``gini``
"purity" criteria is used for classification, and sum of squared errors is used for regression). Then, if necessary, the surrogate splits are found that resemble the results of the primary split on the training data; all of the data is divided using the primary and the surrogate splits (just like it is done in the prediction procedure) between the left and the right child node. Then the procedure recursively splits both left and right nodes. At each node the recursive procedure may stop (i.e. stop splitting the node further) in one of the following cases:
* depth of the tree branch being constructed has reached the specified maximum value.
* number of training samples in the node is less than the specified threshold, when it is not statistically representative to split the node further.
* all the samples in the node belong to the same class (or, in the case of regression, the variation is too small).
* the best split found does not give any noticeable improvement compared to a random choice.
When the tree is built, it may be pruned using a cross-validation procedure, if necessary. That is, some branches of the tree that may lead to the model overfitting are cut off. Normally this procedure is only applied to standalone decision trees, while tree ensembles usually build small enough trees and use their own protection schemes against overfitting.
Variable importance
-------------------
Besides the obvious use of decision trees - prediction, the tree can be also used for various data analysis. One of the key properties of the constructed decision tree algorithms is that it is possible to compute importance (relative decisive power) of each variable. For example, in a spam filter that uses a set of words occurred in the message as a feature vector, the variable importance rating can be used to determine the most "spam-indicating" words and thus help to keep the dictionary size reasonable.
Importance of each variable is computed over all the splits on this variable in the tree, primary and surrogate ones. Thus, to compute variable importance correctly, the surrogate splits must be enabled in the training parameters, even if there is no missing data.
**[Breiman84] Breiman, L., Friedman, J. Olshen, R. and Stone, C. (1984), "Classification and Regression Trees", Wadsworth.**
.. index:: CvDTreeSplit
.. _CvDTreeSplit:
CvDTreeSplit
------------
`id=0.286654154683 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTreeSplit>`__
.. ctype:: CvDTreeSplit
Decision tree node split.
::
struct CvDTreeSplit
{
int var_idx;
int inversed;
float quality;
CvDTreeSplit* next;
union
{
int subset[2];
struct
{
float c;
int split_point;
}
ord;
};
};
..
.. index:: CvDTreeNode
.. _CvDTreeNode:
CvDTreeNode
-----------
`id=0.948528874157 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTreeNode>`__
.. ctype:: CvDTreeNode
Decision tree node.
::
struct CvDTreeNode
{
int class_idx;
int Tn;
double value;
CvDTreeNode* parent;
CvDTreeNode* left;
CvDTreeNode* right;
CvDTreeSplit* split;
int sample_count;
int depth;
...
};
..
Other numerous fields of
``CvDTreeNode``
are used internally at the training stage.
.. index:: CvDTreeParams
.. _CvDTreeParams:
CvDTreeParams
-------------
`id=0.924935526415 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTreeParams>`__
.. ctype:: CvDTreeParams
Decision tree training parameters.
::
struct CvDTreeParams
{
int max_categories;
int max_depth;
int min_sample_count;
int cv_folds;
bool use_surrogates;
bool use_1se_rule;
bool truncate_pruned_tree;
float regression_accuracy;
const float* priors;
CvDTreeParams() : max_categories(10), max_depth(INT_MAX), min_sample_count(10),
cv_folds(10), use_surrogates(true), use_1se_rule(true),
truncate_pruned_tree(true), regression_accuracy(0.01f), priors(0)
{}
CvDTreeParams( int _max_depth, int _min_sample_count,
float _regression_accuracy, bool _use_surrogates,
int _max_categories, int _cv_folds,
bool _use_1se_rule, bool _truncate_pruned_tree,
const float* _priors );
};
..
The structure contains all the decision tree training parameters. There is a default constructor that initializes all the parameters with the default values tuned for standalone classification tree. Any of the parameters can be overridden then, or the structure may be fully initialized using the advanced variant of the constructor.
.. index:: CvDTreeTrainData
.. _CvDTreeTrainData:
CvDTreeTrainData
----------------
`id=0.0482986639469 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTreeTrainData>`__
.. ctype:: CvDTreeTrainData
Decision tree training data and shared data for tree ensembles.
::
struct CvDTreeTrainData
{
CvDTreeTrainData();
CvDTreeTrainData( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
const CvDTreeParams& _params=CvDTreeParams(),
bool _shared=false, bool _add_labels=false );
virtual ~CvDTreeTrainData();
virtual void set_data( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
const CvDTreeParams& _params=CvDTreeParams(),
bool _shared=false, bool _add_labels=false,
bool _update_data=false );
virtual void get_vectors( const CvMat* _subsample_idx,
float* values, uchar* missing, float* responses,
bool get_class_idx=false );
virtual CvDTreeNode* subsample_data( const CvMat* _subsample_idx );
virtual void write_params( CvFileStorage* fs );
virtual void read_params( CvFileStorage* fs, CvFileNode* node );
// release all the data
virtual void clear();
int get_num_classes() const;
int get_var_type(int vi) const;
int get_work_var_count() const;
virtual int* get_class_labels( CvDTreeNode* n );
virtual float* get_ord_responses( CvDTreeNode* n );
virtual int* get_labels( CvDTreeNode* n );
virtual int* get_cat_var_data( CvDTreeNode* n, int vi );
virtual CvPair32s32f* get_ord_var_data( CvDTreeNode* n, int vi );
virtual int get_child_buf_idx( CvDTreeNode* n );
////////////////////////////////////
virtual bool set_params( const CvDTreeParams& params );
virtual CvDTreeNode* new_node( CvDTreeNode* parent, int count,
int storage_idx, int offset );
virtual CvDTreeSplit* new_split_ord( int vi, float cmp_val,
int split_point, int inversed, float quality );
virtual CvDTreeSplit* new_split_cat( int vi, float quality );
virtual void free_node_data( CvDTreeNode* node );
virtual void free_train_data();
virtual void free_node( CvDTreeNode* node );
int sample_count, var_all, var_count, max_c_count;
int ord_var_count, cat_var_count;
bool have_labels, have_priors;
bool is_classifier;
int buf_count, buf_size;
bool shared;
CvMat* cat_count;
CvMat* cat_ofs;
CvMat* cat_map;
CvMat* counts;
CvMat* buf;
CvMat* direction;
CvMat* split_buf;
CvMat* var_idx;
CvMat* var_type; // i-th element =
// k<0 - ordered
// k>=0 - categorical, see k-th element of cat_* arrays
CvMat* priors;
CvDTreeParams params;
CvMemStorage* tree_storage;
CvMemStorage* temp_storage;
CvDTreeNode* data_root;
CvSet* node_heap;
CvSet* split_heap;
CvSet* cv_heap;
CvSet* nv_heap;
CvRNG rng;
};
..
This structure is mostly used internally for storing both standalone trees and tree ensembles efficiently. Basically, it contains 3 types of information:
#. The training parameters, an instance of :ref:`CvDTreeParams`.
#. The training data, preprocessed in order to find the best splits more efficiently. For tree ensembles this preprocessed data is reused by all the trees. Additionally, the training data characteristics that are shared by all trees in the ensemble are stored here: variable types, the number of classes, class label compression map etc.
#. Buffers, memory storages for tree nodes, splits and other elements of the trees constructed.
There are 2 ways of using this structure. In simple cases (e.g. a standalone tree, or the ready-to-use "black box" tree ensemble from ML, like
:ref:`Random Trees`
or
:ref:`Boosting`
) there is no need to care or even to know about the structure - just construct the needed statistical model, train it and use it. The
``CvDTreeTrainData``
structure will be constructed and used internally. However, for custom tree algorithms, or another sophisticated cases, the structure may be constructed and used explicitly. The scheme is the following:
*
The structure is initialized using the default constructor, followed by
``set_data``
(or it is built using the full form of constructor). The parameter
``_shared``
must be set to
``true``
.
*
One or more trees are trained using this data, see the special form of the method
``CvDTree::train``
.
*
Finally, the structure can be released only after all the trees using it are released.
.. index:: CvDTree
.. _CvDTree:
CvDTree
-------
`id=0.802824162542 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTree>`__
.. ctype:: CvDTree
Decision tree.
::
class CvDTree : public CvStatModel
{
public:
CvDTree();
virtual ~CvDTree();
virtual bool train( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
CvDTreeParams params=CvDTreeParams() );
virtual bool train( CvDTreeTrainData* _train_data,
const CvMat* _subsample_idx );
virtual CvDTreeNode* predict( const CvMat* _sample,
const CvMat* _missing_data_mask=0,
bool raw_mode=false ) const;
virtual const CvMat* get_var_importance();
virtual void clear();
virtual void read( CvFileStorage* fs, CvFileNode* node );
virtual void write( CvFileStorage* fs, const char* name );
// special read & write methods for trees in the tree ensembles
virtual void read( CvFileStorage* fs, CvFileNode* node,
CvDTreeTrainData* data );
virtual void write( CvFileStorage* fs );
const CvDTreeNode* get_root() const;
int get_pruned_tree_idx() const;
CvDTreeTrainData* get_data();
protected:
virtual bool do_train( const CvMat* _subsample_idx );
virtual void try_split_node( CvDTreeNode* n );
virtual void split_node_data( CvDTreeNode* n );
virtual CvDTreeSplit* find_best_split( CvDTreeNode* n );
virtual CvDTreeSplit* find_split_ord_class( CvDTreeNode* n, int vi );
virtual CvDTreeSplit* find_split_cat_class( CvDTreeNode* n, int vi );
virtual CvDTreeSplit* find_split_ord_reg( CvDTreeNode* n, int vi );
virtual CvDTreeSplit* find_split_cat_reg( CvDTreeNode* n, int vi );
virtual CvDTreeSplit* find_surrogate_split_ord( CvDTreeNode* n, int vi );
virtual CvDTreeSplit* find_surrogate_split_cat( CvDTreeNode* n, int vi );
virtual double calc_node_dir( CvDTreeNode* node );
virtual void complete_node_dir( CvDTreeNode* node );
virtual void cluster_categories( const int* vectors, int vector_count,
int var_count, int* sums, int k, int* cluster_labels );
virtual void calc_node_value( CvDTreeNode* node );
virtual void prune_cv();
virtual double update_tree_rnc( int T, int fold );
virtual int cut_tree( int T, int fold, double min_alpha );
virtual void free_prune_data(bool cut_tree);
virtual void free_tree();
virtual void write_node( CvFileStorage* fs, CvDTreeNode* node );
virtual void write_split( CvFileStorage* fs, CvDTreeSplit* split );
virtual CvDTreeNode* read_node( CvFileStorage* fs,
CvFileNode* node,
CvDTreeNode* parent );
virtual CvDTreeSplit* read_split( CvFileStorage* fs, CvFileNode* node );
virtual void write_tree_nodes( CvFileStorage* fs );
virtual void read_tree_nodes( CvFileStorage* fs, CvFileNode* node );
CvDTreeNode* root;
int pruned_tree_idx;
CvMat* var_importance;
CvDTreeTrainData* data;
};
..
.. index:: CvDTree::train
.. _CvDTree::train:
CvDTree::train
--------------
`id=0.215158058664 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTree%3A%3Atrain>`__
.. cfunction:: bool CvDTree::train( const CvMat* _train_data, int _tflag, const CvMat* _responses, const CvMat* _var_idx=0, const CvMat* _sample_idx=0, const CvMat* _var_type=0, const CvMat* _missing_mask=0, CvDTreeParams params=CvDTreeParams() )
.. cfunction:: bool CvDTree::train( CvDTreeTrainData* _train_data, const CvMat* _subsample_idx )
Trains a decision tree.
There are 2
``train``
methods in
``CvDTree``
.
The first method follows the generic
``CvStatModel::train``
conventions, it is the most complete form. Both data layouts (
``_tflag=CV_ROW_SAMPLE``
and
``_tflag=CV_COL_SAMPLE``
) are supported, as well as sample and variable subsets, missing measurements, arbitrary combinations of input and output variable types etc. The last parameter contains all of the necessary training parameters, see the
:ref:`CvDTreeParams`
description.
The second method
``train``
is mostly used for building tree ensembles. It takes the pre-constructed
:ref:`CvDTreeTrainData`
instance and the optional subset of training set. The indices in
``_subsample_idx``
are counted relatively to the
``_sample_idx``
, passed to
``CvDTreeTrainData``
constructor. For example, if
``_sample_idx=[1, 5, 7, 100]``
, then
``_subsample_idx=[0,3]``
means that the samples
``[1, 100]``
of the original training set are used.
.. index:: CvDTree::predict
.. _CvDTree::predict:
CvDTree::predict
----------------
`id=0.366805937359 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvDTree%3A%3Apredict>`__
.. cfunction:: CvDTreeNode* CvDTree::predict( const CvMat* _sample, const CvMat* _missing_data_mask=0, bool raw_mode=false ) const
Returns the leaf node of the decision tree corresponding to the input vector.
The method takes the feature vector and the optional missing measurement mask on input, traverses the decision tree and returns the reached leaf node on output. The prediction result, either the class label or the estimated function value, may be retrieved as the
``value``
field of the
:ref:`CvDTreeNode`
structure, for example: dtree-
:math:`>`
predict(sample,mask)-
:math:`>`
value.
The last parameter is normally set to
``false``
, implying a regular
input. If it is
``true``
, the method assumes that all the values of
the discrete input variables have been already normalized to
:math:`0`
to
:math:`num\_of\_categories_i-1`
ranges. (as the decision tree uses such
normalized representation internally). It is useful for faster prediction
with tree ensembles. For ordered input variables the flag is not used.
Example: Building A Tree for Classifying Mushrooms. See the
``mushroom.cpp``
sample that demonstrates how to build and use the
decision tree.

436
modules/ml/doc/expectation_maximization.rst Normal file
View File

@ -0,0 +1,436 @@
Expectation-Maximization
========================
.. highlight:: cpp
The EM (Expectation-Maximization) algorithm estimates the parameters of the multivariate probability density function in the form of a Gaussian mixture distribution with a specified number of mixtures.
Consider the set of the feature vectors
:math:`x_1, x_2,...,x_{N}`
: N vectors from a d-dimensional Euclidean space drawn from a Gaussian mixture:
.. math::
p(x;a_k,S_k, \pi _k) = \sum _{k=1}^{m} \pi _kp_k(x), \quad \pi _k \geq 0, \quad \sum _{k=1}^{m} \pi _k=1,
.. math::
p_k(x)= \varphi (x;a_k,S_k)= \frac{1}{(2\pi)^{d/2}\mid{S_k}\mid^{1/2}} exp \left \{ - \frac{1}{2} (x-a_k)^TS_k^{-1}(x-a_k) \right \} ,
where
:math:`m`
is the number of mixtures,
:math:`p_k`
is the normal distribution
density with the mean
:math:`a_k`
and covariance matrix
:math:`S_k`
,
:math:`\pi_k`
is the weight of the k-th mixture. Given the number of mixtures
:math:`M`
and the samples
:math:`x_i`
,
:math:`i=1..N`
the algorithm finds the
maximum-likelihood estimates (MLE) of the all the mixture parameters,
i.e.
:math:`a_k`
,
:math:`S_k`
and
:math:`\pi_k`
:
.. math::
L(x, \theta )=logp(x, \theta )= \sum _{i=1}^{N}log \left ( \sum _{k=1}^{m} \pi _kp_k(x) \right ) \to \max _{ \theta \in \Theta },
.. math::
\Theta = \left \{ (a_k,S_k, \pi _k): a_k \in \mathbbm{R} ^d,S_k=S_k^T>0,S_k \in \mathbbm{R} ^{d \times d}, \pi _k \geq 0, \sum _{k=1}^{m} \pi _k=1 \right \} .
EM algorithm is an iterative procedure. Each iteration of it includes
two steps. At the first step (Expectation-step, or E-step), we find a
probability
:math:`p_{i,k}`
(denoted
:math:`\alpha_{i,k}`
in the formula below) of
sample
``i``
to belong to mixture
``k``
using the currently
available mixture parameter estimates:
.. math::
\alpha _{ki} = \frac{\pi_k\varphi(x;a_k,S_k)}{\sum\limits_{j=1}^{m}\pi_j\varphi(x;a_j,S_j)} .
At the second step (Maximization-step, or M-step) the mixture parameter estimates are refined using the computed probabilities:
.. math::
\pi _k= \frac{1}{N} \sum _{i=1}^{N} \alpha _{ki}, \quad a_k= \frac{\sum\limits_{i=1}^{N}\alpha_{ki}x_i}{\sum\limits_{i=1}^{N}\alpha_{ki}} , \quad S_k= \frac{\sum\limits_{i=1}^{N}\alpha_{ki}(x_i-a_k)(x_i-a_k)^T}{\sum\limits_{i=1}^{N}\alpha_{ki}} ,
Alternatively, the algorithm may start with the M-step when the initial values for
:math:`p_{i,k}`
can be provided. Another alternative when
:math:`p_{i,k}`
are unknown, is to use a simpler clustering algorithm to pre-cluster the input samples and thus obtain initial
:math:`p_{i,k}`
. Often (and in ML) the
:ref:`KMeans2`
algorithm is used for that purpose.
One of the main that EM algorithm should deal with is the large number
of parameters to estimate. The majority of the parameters sits in
covariance matrices, which are
:math:`d \times d`
elements each
(where
:math:`d`
is the feature space dimensionality). However, in
many practical problems the covariance matrices are close to diagonal,
or even to
:math:`\mu_k*I`
, where
:math:`I`
is identity matrix and
:math:`\mu_k`
is mixture-dependent "scale" parameter. So a robust computation
scheme could be to start with the harder constraints on the covariance
matrices and then use the estimated parameters as an input for a less
constrained optimization problem (often a diagonal covariance matrix is
already a good enough approximation).
**References:**
*
Bilmes98 J. A. Bilmes. A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical Report TR-97-021, International Computer Science Institute and Computer Science Division, University of California at Berkeley, April 1998.
.. index:: CvEMParams
.. _CvEMParams:
CvEMParams
----------
`id=0.432576013672 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvEMParams>`__
.. ctype:: CvEMParams
Parameters of the EM algorithm.
::
struct CvEMParams
{
CvEMParams() : nclusters(10), cov_mat_type(CvEM::COV_MAT_DIAGONAL),
start_step(CvEM::START_AUTO_STEP), probs(0), weights(0), means(0),
covs(0)
{
term_crit=cvTermCriteria( CV_TERMCRIT_ITER+CV_TERMCRIT_EPS,
100, FLT_EPSILON );
}
CvEMParams( int _nclusters, int _cov_mat_type=1/*CvEM::COV_MAT_DIAGONAL*/,
int _start_step=0/*CvEM::START_AUTO_STEP*/,
CvTermCriteria _term_crit=cvTermCriteria(
CV_TERMCRIT_ITER+CV_TERMCRIT_EPS,
100, FLT_EPSILON),
CvMat* _probs=0, CvMat* _weights=0,
CvMat* _means=0, CvMat** _covs=0 ) :
nclusters(_nclusters), cov_mat_type(_cov_mat_type),
start_step(_start_step),
probs(_probs), weights(_weights), means(_means), covs(_covs),
term_crit(_term_crit)
{}
int nclusters;
int cov_mat_type;
int start_step;
const CvMat* probs;
const CvMat* weights;
const CvMat* means;
const CvMat** covs;
CvTermCriteria term_crit;
};
..
The structure has 2 constructors, the default one represents a rough rule-of-thumb, with another one it is possible to override a variety of parameters, from a single number of mixtures (the only essential problem-dependent parameter), to the initial values for the mixture parameters.
.. index:: CvEM
.. _CvEM:
CvEM
----
`id=0.808344863567 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvEM>`__
.. ctype:: CvEM
EM model.
::
class CV_EXPORTS CvEM : public CvStatModel
{
public:
// Type of covariance matrices
enum { COV_MAT_SPHERICAL=0, COV_MAT_DIAGONAL=1, COV_MAT_GENERIC=2 };
// The initial step
enum { START_E_STEP=1, START_M_STEP=2, START_AUTO_STEP=0 };
CvEM();
CvEM( const CvMat* samples, const CvMat* sample_idx=0,
CvEMParams params=CvEMParams(), CvMat* labels=0 );
virtual ~CvEM();
virtual bool train( const CvMat* samples, const CvMat* sample_idx=0,
CvEMParams params=CvEMParams(), CvMat* labels=0 );
virtual float predict( const CvMat* sample, CvMat* probs ) const;
virtual void clear();
int get_nclusters() const { return params.nclusters; }
const CvMat* get_means() const { return means; }
const CvMat** get_covs() const { return covs; }
const CvMat* get_weights() const { return weights; }
const CvMat* get_probs() const { return probs; }
protected:
virtual void set_params( const CvEMParams& params,
const CvVectors& train_data );
virtual void init_em( const CvVectors& train_data );
virtual double run_em( const CvVectors& train_data );
virtual void init_auto( const CvVectors& samples );
virtual void kmeans( const CvVectors& train_data, int nclusters,
CvMat* labels, CvTermCriteria criteria,
const CvMat* means );
CvEMParams params;
double log_likelihood;
CvMat* means;
CvMat** covs;
CvMat* weights;
CvMat* probs;
CvMat* log_weight_div_det;
CvMat* inv_eigen_values;
CvMat** cov_rotate_mats;
};
..
.. index:: CvEM::train
.. _CvEM::train:
CvEM::train
-----------
`id=0.340076585117 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvEM%3A%3Atrain>`__
.. cfunction:: void CvEM::train( const CvMat* samples, const CvMat* sample_idx=0, CvEMParams params=CvEMParams(), CvMat* labels=0 )
Estimates the Gaussian mixture parameters from the sample set.
Unlike many of the ML models, EM is an unsupervised learning algorithm and it does not take responses (class labels or the function values) on input. Instead, it computes the
:ref:`MLE`
of the Gaussian mixture parameters from the input sample set, stores all the parameters inside the structure:
:math:`p_{i,k}`
in
``probs``
,
:math:`a_k`
in
``means``
:math:`S_k`
in
``covs[k]``
,
:math:`\pi_k`
in
``weights``
and optionally computes the output "class label" for each sample:
:math:`\texttt{labels}_i=\texttt{arg max}_k(p_{i,k}), i=1..N`
(i.e. indices of the most-probable mixture for each sample).
The trained model can be used further for prediction, just like any other classifier. The model trained is similar to the
:ref:`Bayes classifier`
.
Example: Clustering random samples of multi-Gaussian distribution using EM
::
#include "ml.h"
#include "highgui.h"
int main( int argc, char** argv )
{
const int N = 4;
const int N1 = (int)sqrt((double)N);
const CvScalar colors[] = {{0,0,255}},{{0,255,0}},
{{0,255,255}},{{255,255,0}
;
int i, j;
int nsamples = 100;
CvRNG rng_state = cvRNG(-1);
CvMat* samples = cvCreateMat( nsamples, 2, CV_32FC1 );
CvMat* labels = cvCreateMat( nsamples, 1, CV_32SC1 );
IplImage* img = cvCreateImage( cvSize( 500, 500 ), 8, 3 );
float _sample[2];
CvMat sample = cvMat( 1, 2, CV_32FC1, _sample );
CvEM em_model;
CvEMParams params;
CvMat samples_part;
cvReshape( samples, samples, 2, 0 );
for( i = 0; i < N; i++ )
{
CvScalar mean, sigma;
// form the training samples
cvGetRows( samples, &samples_part, i*nsamples/N,
(i+1)*nsamples/N );
mean = cvScalar(((i
((i/N1)+1.)*img->height/(N1+1));
sigma = cvScalar(30,30);
cvRandArr( &rng_state, &samples_part, CV_RAND_NORMAL,
mean, sigma );
}
cvReshape( samples, samples, 1, 0 );
// initialize model's parameters
params.covs = NULL;
params.means = NULL;
params.weights = NULL;
params.probs = NULL;
params.nclusters = N;
params.cov_mat_type = CvEM::COV_MAT_SPHERICAL;
params.start_step = CvEM::START_AUTO_STEP;
params.term_crit.max_iter = 10;
params.term_crit.epsilon = 0.1;
params.term_crit.type = CV_TERMCRIT_ITER|CV_TERMCRIT_EPS;
// cluster the data
em_model.train( samples, 0, params, labels );
#if 0
// the piece of code shows how to repeatedly optimize the model
// with less-constrained parameters
//(COV_MAT_DIAGONAL instead of COV_MAT_SPHERICAL)
// when the output of the first stage is used as input for the second.
CvEM em_model2;
params.cov_mat_type = CvEM::COV_MAT_DIAGONAL;
params.start_step = CvEM::START_E_STEP;
params.means = em_model.get_means();
params.covs = (const CvMat**)em_model.get_covs();
params.weights = em_model.get_weights();
em_model2.train( samples, 0, params, labels );
// to use em_model2, replace em_model.predict()
// with em_model2.predict() below
#endif
// classify every image pixel
cvZero( img );
for( i = 0; i < img->height; i++ )
{
for( j = 0; j < img->width; j++ )
{
CvPoint pt = cvPoint(j, i);
sample.data.fl[0] = (float)j;
sample.data.fl[1] = (float)i;
int response = cvRound(em_model.predict( &sample, NULL ));
CvScalar c = colors[response];
cvCircle( img, pt, 1, cvScalar(c.val[0]*0.75,
c.val[1]*0.75,c.val[2]*0.75), CV_FILLED );
}
}
//draw the clustered samples
for( i = 0; i < nsamples; i++ )
{
CvPoint pt;
pt.x = cvRound(samples->data.fl[i*2]);
pt.y = cvRound(samples->data.fl[i*2+1]);
cvCircle( img, pt, 1, colors[labels->data.i[i]], CV_FILLED );
}
cvNamedWindow( "EM-clustering result", 1 );
cvShowImage( "EM-clustering result", img );
cvWaitKey(0);
cvReleaseMat( &samples );
cvReleaseMat( &labels );
return 0;
}
..

254
modules/ml/doc/k_nearest_neighbors.rst Normal file
View File

@ -0,0 +1,254 @@
K Nearest Neighbors
===================
.. highlight:: cpp
The algorithm caches all of the training samples, and predicts the response for a new sample by analyzing a certain number (
**K**
) of the nearest neighbors of the sample (using voting, calculating weighted sum etc.) The method is sometimes referred to as "learning by example", because for prediction it looks for the feature vector with a known response that is closest to the given vector.
.. index:: CvKNearest
.. _CvKNearest:
CvKNearest
----------
`id=0.969498355265 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvKNearest>`__
.. ctype:: CvKNearest
K Nearest Neighbors model.
::
class CvKNearest : public CvStatModel
{
public:
CvKNearest();
virtual ~CvKNearest();
CvKNearest( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _sample_idx=0, bool _is_regression=false, int max_k=32 );
virtual bool train( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _sample_idx=0, bool is_regression=false,
int _max_k=32, bool _update_base=false );
virtual float find_nearest( const CvMat* _samples, int k, CvMat* results,
const float** neighbors=0, CvMat* neighbor_responses=0, CvMat* dist=0 ) const;
virtual void clear();
int get_max_k() const;
int get_var_count() const;
int get_sample_count() const;
bool is_regression() const;
protected:
...
};
..
.. index:: CvKNearest::train
.. _CvKNearest::train:
CvKNearest::train
-----------------
`id=0.0998674771945 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvKNearest%3A%3Atrain>`__
.. cfunction:: bool CvKNearest::train( const CvMat* _train_data, const CvMat* _responses, const CvMat* _sample_idx=0, bool is_regression=false, int _max_k=32, bool _update_base=false )
Trains the model.
The method trains the K-Nearest model. It follows the conventions of generic
``train``
"method" with the following limitations: only CV
_
ROW
_
SAMPLE data layout is supported, the input variables are all ordered, the output variables can be either categorical (
``is_regression=false``
) or ordered (
``is_regression=true``
), variable subsets (
``var_idx``
) and missing measurements are not supported.
The parameter
``_max_k``
specifies the number of maximum neighbors that may be passed to the method
``find_nearest``
.
The parameter
``_update_base``
specifies whether the model is trained from scratch
(
``_update_base=false``
), or it is updated using the new training data (
``_update_base=true``
). In the latter case the parameter
``_max_k``
must not be larger than the original value.
.. index:: CvKNearest::find_nearest
.. _CvKNearest::find_nearest:
CvKNearest::find_nearest
------------------------
`id=0.654974872601 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvKNearest%3A%3Afind_nearest>`__
.. cfunction:: float CvKNearest::find_nearest( const CvMat* _samples, int k, CvMat* results=0, const float** neighbors=0, CvMat* neighbor_responses=0, CvMat* dist=0 ) const
Finds the neighbors for the input vectors.
For each input vector (which are the rows of the matrix
``_samples``
) the method finds the
:math:`\texttt{k} \le
\texttt{get\_max\_k()}`
nearest neighbor. In the case of regression,
the predicted result will be a mean value of the particular vector's
neighbor responses. In the case of classification the class is determined
by voting.
For custom classification/regression prediction, the method can optionally return pointers to the neighbor vectors themselves (
``neighbors``
, an array of
``k*_samples->rows``
pointers), their corresponding output values (
``neighbor_responses``
, a vector of
``k*_samples->rows``
elements) and the distances from the input vectors to the neighbors (
``dist``
, also a vector of
``k*_samples->rows``
elements).
For each input vector the neighbors are sorted by their distances to the vector.
If only a single input vector is passed, all output matrices are optional and the predicted value is returned by the method.
::
#include "ml.h"
#include "highgui.h"
int main( int argc, char** argv )
{
const int K = 10;
int i, j, k, accuracy;
float response;
int train_sample_count = 100;
CvRNG rng_state = cvRNG(-1);
CvMat* trainData = cvCreateMat( train_sample_count, 2, CV_32FC1 );
CvMat* trainClasses = cvCreateMat( train_sample_count, 1, CV_32FC1 );
IplImage* img = cvCreateImage( cvSize( 500, 500 ), 8, 3 );
float _sample[2];
CvMat sample = cvMat( 1, 2, CV_32FC1, _sample );
cvZero( img );
CvMat trainData1, trainData2, trainClasses1, trainClasses2;
// form the training samples
cvGetRows( trainData, &trainData1, 0, train_sample_count/2 );
cvRandArr( &rng_state, &trainData1, CV_RAND_NORMAL, cvScalar(200,200), cvScalar(50,50) );
cvGetRows( trainData, &trainData2, train_sample_count/2, train_sample_count );
cvRandArr( &rng_state, &trainData2, CV_RAND_NORMAL, cvScalar(300,300), cvScalar(50,50) );
cvGetRows( trainClasses, &trainClasses1, 0, train_sample_count/2 );
cvSet( &trainClasses1, cvScalar(1) );
cvGetRows( trainClasses, &trainClasses2, train_sample_count/2, train_sample_count );
cvSet( &trainClasses2, cvScalar(2) );
// learn classifier
CvKNearest knn( trainData, trainClasses, 0, false, K );
CvMat* nearests = cvCreateMat( 1, K, CV_32FC1);
for( i = 0; i < img->height; i++ )
{
for( j = 0; j < img->width; j++ )
{
sample.data.fl[0] = (float)j;
sample.data.fl[1] = (float)i;
// estimates the response and get the neighbors' labels
response = knn.find_nearest(&sample,K,0,0,nearests,0);
// compute the number of neighbors representing the majority
for( k = 0, accuracy = 0; k < K; k++ )
{
if( nearests->data.fl[k] == response)
accuracy++;
}
// highlight the pixel depending on the accuracy (or confidence)
cvSet2D( img, i, j, response == 1 ?
(accuracy > 5 ? CV_RGB(180,0,0) : CV_RGB(180,120,0)) :
(accuracy > 5 ? CV_RGB(0,180,0) : CV_RGB(120,120,0)) );
}
}
// display the original training samples
for( i = 0; i < train_sample_count/2; i++ )
{
CvPoint pt;
pt.x = cvRound(trainData1.data.fl[i*2]);
pt.y = cvRound(trainData1.data.fl[i*2+1]);
cvCircle( img, pt, 2, CV_RGB(255,0,0), CV_FILLED );
pt.x = cvRound(trainData2.data.fl[i*2]);
pt.y = cvRound(trainData2.data.fl[i*2+1]);
cvCircle( img, pt, 2, CV_RGB(0,255,0), CV_FILLED );
}
cvNamedWindow( "classifier result", 1 );
cvShowImage( "classifier result", img );
cvWaitKey(0);
cvReleaseMat( &trainClasses );
cvReleaseMat( &trainData );
return 0;
}
..

22
modules/ml/doc/ml.rst Normal file
View File

@ -0,0 +1,22 @@
****************
Machine Learning
****************
The Machine Learning Library (MLL) is a set of classes and functions for statistical classification, regression and clustering of data.
Most of the classification and regression algorithms are implemented as C++ classes. As the algorithms have different seta of features (like the ability to handle missing measurements, or categorical input variables etc.), there is a little common ground between the classes. This common ground is defined by the class `CvStatModel` that all the other ML classes are derived from.
.. toctree::
:maxdepth: 2
statistical_models
normal_bayes_classifier
k_nearest_neighbors
support_vector_machines
decision_trees
boosting
random_trees
expectation-maximization
neural_networks

399
modules/ml/doc/neural_networks.rst Normal file
View File

@ -0,0 +1,399 @@
Neural Networks
===============
.. highlight:: cpp
ML implements feed-forward artificial neural networks, more particularly, multi-layer perceptrons (MLP), the most commonly used type of neural networks. MLP consists of the input layer, output layer and one or more hidden layers. Each layer of MLP includes one or more neurons that are directionally linked with the neurons from the previous and the next layer. Here is an example of a 3-layer perceptron with 3 inputs, 2 outputs and the hidden layer including 5 neurons:
.. image:: ../../pics/mlp_.png
All the neurons in MLP are similar. Each of them has several input links (i.e. it takes the output values from several neurons in the previous layer on input) and several output links (i.e. it passes the response to several neurons in the next layer). The values retrieved from the previous layer are summed with certain weights, individual for each neuron, plus the bias term, and the sum is transformed using the activation function
:math:`f`
that may be also different for different neurons. Here is the picture:
.. image:: ../../pics/neuron_model.png
In other words, given the outputs
:math:`x_j`
of the layer
:math:`n`
, the outputs
:math:`y_i`
of the layer
:math:`n+1`
are computed as:
.. math::
u_i = \sum _j (w^{n+1}_{i,j}*x_j) + w^{n+1}_{i,bias}
.. math::
y_i = f(u_i)
Different activation functions may be used, ML implements 3 standard ones:
*
Identity function (
``CvANN_MLP::IDENTITY``
):
:math:`f(x)=x`
*
Symmetrical sigmoid (
``CvANN_MLP::SIGMOID_SYM``
):
:math:`f(x)=\beta*(1-e^{-\alpha x})/(1+e^{-\alpha x}`
), the default choice for MLP; the standard sigmoid with
:math:`\beta =1, \alpha =1`
is shown below:
.. image:: ../../pics/sigmoid_bipolar.png
*
Gaussian function (
``CvANN_MLP::GAUSSIAN``
):
:math:`f(x)=\beta e^{-\alpha x*x}`
, not completely supported by the moment.
In ML all the neurons have the same activation functions, with the same free parameters (
:math:`\alpha, \beta`
) that are specified by user and are not altered by the training algorithms.
So the whole trained network works as follows: It takes the feature vector on input, the vector size is equal to the size of the input layer, when the values are passed as input to the first hidden layer, the outputs of the hidden layer are computed using the weights and the activation functions and passed further downstream, until we compute the output layer.
So, in order to compute the network one needs to know all the
weights
:math:`w^{n+1)}_{i,j}`
. The weights are computed by the training
algorithm. The algorithm takes a training set: multiple input vectors
with the corresponding output vectors, and iteratively adjusts the
weights to try to make the network give the desired response on the
provided input vectors.
The larger the network size (the number of hidden layers and their sizes),
the more is the potential network flexibility, and the error on the
training set could be made arbitrarily small. But at the same time the
learned network will also "learn" the noise present in the training set,
so the error on the test set usually starts increasing after the network
size reaches some limit. Besides, the larger networks are train much
longer than the smaller ones, so it is reasonable to preprocess the data
(using
:ref:`CalcPCA`
or similar technique) and train a smaller network
on only the essential features.
Another feature of the MLP's is their inability to handle categorical
data as is, however there is a workaround. If a certain feature in the
input or output (i.e. in the case of
``n``
-class classifier for
:math:`n>2`
) layer is categorical and can take
:math:`M>2`
different values, it makes sense to represent it as binary tuple of
``M``
elements, where
``i``
-th element is 1 if and only if the
feature is equal to the
``i``
-th value out of
``M``
possible. It
will increase the size of the input/output layer, but will speedup the
training algorithm convergence and at the same time enable "fuzzy" values
of such variables, i.e. a tuple of probabilities instead of a fixed value.
ML implements 2 algorithms for training MLP's. The first is the classical
random sequential back-propagation algorithm
and the second (default one) is batch RPROP algorithm.
References:
*
http://en.wikipedia.org/wiki/Backpropagation
. Wikipedia article about the back-propagation algorithm.
*
Y. LeCun, L. Bottou, G.B. Orr and K.-R. Muller, "Efficient backprop", in Neural Networks---Tricks of the Trade, Springer Lecture Notes in Computer Sciences 1524, pp.5-50, 1998.
*
M. Riedmiller and H. Braun, "A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm", Proc. ICNN, San Francisco (1993).
.. index:: CvANN_MLP_TrainParams
.. _CvANN_MLP_TrainParams:
CvANN_MLP_TrainParams
---------------------
`id=0.637270235159 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvANN_MLP_TrainParams>`__
.. ctype:: CvANN_MLP_TrainParams
Parameters of the MLP training algorithm.
::
struct CvANN_MLP_TrainParams
{
CvANN_MLP_TrainParams();
CvANN_MLP_TrainParams( CvTermCriteria term_crit, int train_method,
double param1, double param2=0 );
~CvANN_MLP_TrainParams();
enum { BACKPROP=0, RPROP=1 };
CvTermCriteria term_crit;
int train_method;
// backpropagation parameters
double bp_dw_scale, bp_moment_scale;
// rprop parameters
double rp_dw0, rp_dw_plus, rp_dw_minus, rp_dw_min, rp_dw_max;
};
..
The structure has default constructor that initializes parameters for
``RPROP``
algorithm. There is also more advanced constructor to customize the parameters and/or choose backpropagation algorithm. Finally, the individual parameters can be adjusted after the structure is created.
.. index:: CvANN_MLP
.. _CvANN_MLP:
CvANN_MLP
---------
`id=0.404391979594 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvANN_MLP>`__
.. ctype:: CvANN_MLP
MLP model.
::
class CvANN_MLP : public CvStatModel
{
public:
CvANN_MLP();
CvANN_MLP( const CvMat* _layer_sizes,
int _activ_func=SIGMOID_SYM,
double _f_param1=0, double _f_param2=0 );
virtual ~CvANN_MLP();
virtual void create( const CvMat* _layer_sizes,
int _activ_func=SIGMOID_SYM,
double _f_param1=0, double _f_param2=0 );
virtual int train( const CvMat* _inputs, const CvMat* _outputs,
const CvMat* _sample_weights,
const CvMat* _sample_idx=0,
CvANN_MLP_TrainParams _params = CvANN_MLP_TrainParams(),
int flags=0 );
virtual float predict( const CvMat* _inputs,
CvMat* _outputs ) const;
virtual void clear();
// possible activation functions
enum { IDENTITY = 0, SIGMOID_SYM = 1, GAUSSIAN = 2 };
// available training flags
enum { UPDATE_WEIGHTS = 1, NO_INPUT_SCALE = 2, NO_OUTPUT_SCALE = 4 };
virtual void read( CvFileStorage* fs, CvFileNode* node );
virtual void write( CvFileStorage* storage, const char* name );
int get_layer_count() { return layer_sizes ? layer_sizes->cols : 0; }
const CvMat* get_layer_sizes() { return layer_sizes; }
protected:
virtual bool prepare_to_train( const CvMat* _inputs, const CvMat* _outputs,
const CvMat* _sample_weights, const CvMat* _sample_idx,
CvANN_MLP_TrainParams _params,
CvVectors* _ivecs, CvVectors* _ovecs, double** _sw, int _flags );
// sequential random backpropagation
virtual int train_backprop( CvVectors _ivecs, CvVectors _ovecs,
const double* _sw );
// RPROP algorithm
virtual int train_rprop( CvVectors _ivecs, CvVectors _ovecs,
const double* _sw );
virtual void calc_activ_func( CvMat* xf, const double* bias ) const;
virtual void calc_activ_func_deriv( CvMat* xf, CvMat* deriv,
const double* bias ) const;
virtual void set_activ_func( int _activ_func=SIGMOID_SYM,
double _f_param1=0, double _f_param2=0 );
virtual void init_weights();
virtual void scale_input( const CvMat* _src, CvMat* _dst ) const;
virtual void scale_output( const CvMat* _src, CvMat* _dst ) const;
virtual void calc_input_scale( const CvVectors* vecs, int flags );
virtual void calc_output_scale( const CvVectors* vecs, int flags );
virtual void write_params( CvFileStorage* fs );
virtual void read_params( CvFileStorage* fs, CvFileNode* node );
CvMat* layer_sizes;
CvMat* wbuf;
CvMat* sample_weights;
double** weights;
double f_param1, f_param2;
double min_val, max_val, min_val1, max_val1;
int activ_func;
int max_count, max_buf_sz;
CvANN_MLP_TrainParams params;
CvRNG rng;
};
..
Unlike many other models in ML that are constructed and trained at once, in the MLP model these steps are separated. First, a network with the specified topology is created using the non-default constructor or the method
``create``
. All the weights are set to zeros. Then the network is trained using the set of input and output vectors. The training procedure can be repeated more than once, i.e. the weights can be adjusted based on the new training data.
.. index:: CvANN_MLP::create
.. _CvANN_MLP::create:
CvANN_MLP::create
-----------------
`id=0.505267168137 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvANN_MLP%3A%3Acreate>`__
.. cfunction:: void CvANN_MLP::create( const CvMat* _layer_sizes, int _activ_func=SIGMOID_SYM, double _f_param1=0, double _f_param2=0 )
Constructs the MLP with the specified topology
:param _layer_sizes: The integer vector specifies the number of neurons in each layer including the input and output layers.
:param _activ_func: Specifies the activation function for each neuron; one of ``CvANN_MLP::IDENTITY`` , ``CvANN_MLP::SIGMOID_SYM`` and ``CvANN_MLP::GAUSSIAN`` .
:param _f_param1,_f_param2: Free parameters of the activation function, :math:`\alpha` and :math:`\beta` , respectively. See the formulas in the introduction section.
The method creates a MLP network with the specified topology and assigns the same activation function to all the neurons.
.. index:: CvANN_MLP::train
.. _CvANN_MLP::train:
CvANN_MLP::train
----------------
`id=0.561890021588 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvANN_MLP%3A%3Atrain>`__
.. cfunction:: int CvANN_MLP::train( const CvMat* _inputs, const CvMat* _outputs, const CvMat* _sample_weights, const CvMat* _sample_idx=0, CvANN_MLP_TrainParams _params = CvANN_MLP_TrainParams(), int flags=0 )
Trains/updates MLP.
:param _inputs: A floating-point matrix of input vectors, one vector per row.
:param _outputs: A floating-point matrix of the corresponding output vectors, one vector per row.
:param _sample_weights: (RPROP only) The optional floating-point vector of weights for each sample. Some samples may be more important than others for training, and the user may want to raise the weight of certain classes to find the right balance between hit-rate and false-alarm rate etc.
:param _sample_idx: The optional integer vector indicating the samples (i.e. rows of ``_inputs`` and ``_outputs`` ) that are taken into account.
:param _params: The training params. See ``CvANN_MLP_TrainParams`` description.
:param _flags: The various parameters to control the training algorithm. May be a combination of the following:
* **UPDATE_WEIGHTS = 1** algorithm updates the network weights, rather than computes them from scratch (in the latter case the weights are initialized using *Nguyen-Widrow* algorithm).
* **NO_INPUT_SCALE** algorithm does not normalize the input vectors. If this flag is not set, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation =1. If the network is assumed to be updated frequently, the new training data could be much different from original one. In this case user should take care of proper normalization.
* **NO_OUTPUT_SCALE** algorithm does not normalize the output vectors. If the flag is not set, the training algorithm normalizes each output features independently, by transforming it to the certain range depending on the activation function used.
This method applies the specified training algorithm to compute/adjust the network weights. It returns the number of done iterations.

125
modules/ml/doc/normal_bayes_classifier.rst Normal file
View File

@ -0,0 +1,125 @@
Normal Bayes Classifier
=======================
.. highlight:: cpp
This is a simple classification model assuming that feature vectors from each class are normally distributed (though, not necessarily independently distributed), so the whole data distribution function is assumed to be a Gaussian mixture, one component per class. Using the training data the algorithm estimates mean vectors and covariance matrices for every class, and then it uses them for prediction.
**[Fukunaga90] K. Fukunaga. Introduction to Statistical Pattern Recognition. second ed., New York: Academic Press, 1990.**
.. index:: CvNormalBayesClassifier
.. _CvNormalBayesClassifier:
CvNormalBayesClassifier
-----------------------
`id=0.110421013491 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvNormalBayesClassifier>`__
.. ctype:: CvNormalBayesClassifier
Bayes classifier for normally distributed data.
::
class CvNormalBayesClassifier : public CvStatModel
{
public:
CvNormalBayesClassifier();
virtual ~CvNormalBayesClassifier();
CvNormalBayesClassifier( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _var_idx=0, const CvMat* _sample_idx=0 );
virtual bool train( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _var_idx = 0, const CvMat* _sample_idx=0, bool update=false );
virtual float predict( const CvMat* _samples, CvMat* results=0 ) const;
virtual void clear();
virtual void save( const char* filename, const char* name=0 );
virtual void load( const char* filename, const char* name=0 );
virtual void write( CvFileStorage* storage, const char* name );
virtual void read( CvFileStorage* storage, CvFileNode* node );
protected:
...
};
..
.. index:: CvNormalBayesClassifier::train
.. _CvNormalBayesClassifier::train:
CvNormalBayesClassifier::train
------------------------------
`id=0.746566750452 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvNormalBayesClassifier%3A%3Atrain>`__
.. cfunction:: bool CvNormalBayesClassifier::train( const CvMat* _train_data, const CvMat* _responses, const CvMat* _var_idx =0, const CvMat* _sample_idx=0, bool update=false )
Trains the model.
The method trains the Normal Bayes classifier. It follows the conventions of the generic
``train``
"method" with the following limitations: only CV
_
ROW
_
SAMPLE data layout is supported; the input variables are all ordered; the output variable is categorical (i.e. elements of
``_responses``
must be integer numbers, though the vector may have
``CV_32FC1``
type), and missing measurements are not supported.
In addition, there is an
``update``
flag that identifies whether the model should be trained from scratch (
``update=false``
) or should be updated using the new training data (
``update=true``
).
.. index:: CvNormalBayesClassifier::predict
.. _CvNormalBayesClassifier::predict:
CvNormalBayesClassifier::predict
--------------------------------
`id=0.821415185096 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvNormalBayesClassifier%3A%3Apredict>`__
.. cfunction:: float CvNormalBayesClassifier::predict( const CvMat* samples, CvMat* results=0 ) const
Predicts the response for sample(s)
The method
``predict``
estimates the most probable classes for the input vectors. The input vectors (one or more) are stored as rows of the matrix
``samples``
. In the case of multiple input vectors, there should be one output vector
``results``
. The predicted class for a single input vector is returned by the method.

415
modules/ml/doc/random_trees.rst Normal file
View File

@ -0,0 +1,415 @@
Random Trees
============
.. highlight:: cpp
Random trees have been introduced by Leo Breiman and Adele Cutler:
http://www.stat.berkeley.edu/users/breiman/RandomForests/
. The algorithm can deal with both classification and regression problems. Random trees is a collection (ensemble) of tree predictors that is called
**forest**
further in this section (the term has been also introduced by L. Breiman). The classification works as follows: the random trees classifier takes the input feature vector, classifies it with every tree in the forest, and outputs the class label that recieved the majority of "votes". In the case of regression the classifier response is the average of the responses over all the trees in the forest.
All the trees are trained with the same parameters, but on the different training sets, which are generated from the original training set using the bootstrap procedure: for each training set we randomly select the same number of vectors as in the original set (
``=N``
). The vectors are chosen with replacement. That is, some vectors will occur more than once and some will be absent. At each node of each tree trained not all the variables are used to find the best split, rather than a random subset of them. With each node a new subset is generated, however its size is fixed for all the nodes and all the trees. It is a training parameter, set to
:math:`\sqrt{number\_of\_variables}`
by default. None of the trees that are built are pruned.
In random trees there is no need for any accuracy estimation procedures, such as cross-validation or bootstrap, or a separate test set to get an estimate of the training error. The error is estimated internally during the training. When the training set for the current tree is drawn by sampling with replacement, some vectors are left out (so-called
*oob (out-of-bag) data*
). The size of oob data is about
``N/3``
. The classification error is estimated by using this oob-data as following:
*
Get a prediction for each vector, which is oob relatively to the i-th tree, using the very i-th tree.
*
After all the trees have been trained, for each vector that has ever been oob, find the class-"winner" for it (i.e. the class that has got the majority of votes in the trees, where the vector was oob) and compare it to the ground-truth response.
*
Then the classification error estimate is computed as ratio of number of misclassified oob vectors to all the vectors in the original data. In the case of regression the oob-error is computed as the squared error for oob vectors difference divided by the total number of vectors.
**References:**
*
Machine Learning, Wald I, July 2002.
http://stat-www.berkeley.edu/users/breiman/wald2002-1.pdf
*
Looking Inside the Black Box, Wald II, July 2002.
http://stat-www.berkeley.edu/users/breiman/wald2002-2.pdf
*
Software for the Masses, Wald III, July 2002.
http://stat-www.berkeley.edu/users/breiman/wald2002-3.pdf
*
And other articles from the web site
http://www.stat.berkeley.edu/users/breiman/RandomForests/cc_home.htm
.
.. index:: CvRTParams
.. _CvRTParams:
CvRTParams
----------
`id=0.971665272168 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTParams>`__
.. ctype:: CvRTParams
Training Parameters of Random Trees.
::
struct CvRTParams : public CvDTreeParams
{
bool calc_var_importance;
int nactive_vars;
CvTermCriteria term_crit;
CvRTParams() : CvDTreeParams( 5, 10, 0, false, 10, 0, false, false, 0 ),
calc_var_importance(false), nactive_vars(0)
{
term_crit = cvTermCriteria( CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 50, 0.1 );
}
CvRTParams( int _max_depth, int _min_sample_count,
float _regression_accuracy, bool _use_surrogates,
int _max_categories, const float* _priors,
bool _calc_var_importance,
int _nactive_vars, int max_tree_count,
float forest_accuracy, int termcrit_type );
};
..
The set of training parameters for the forest is the superset of the training parameters for a single tree. However, Random trees do not need all the functionality/features of decision trees, most noticeably, the trees are not pruned, so the cross-validation parameters are not used.
.. index:: CvRTrees
.. _CvRTrees:
CvRTrees
--------
`id=0.485875932457 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTrees>`__
.. ctype:: CvRTrees
Random Trees.
::
class CvRTrees : public CvStatModel
{
public:
CvRTrees();
virtual ~CvRTrees();
virtual bool train( const CvMat* _train_data, int _tflag,
const CvMat* _responses, const CvMat* _var_idx=0,
const CvMat* _sample_idx=0, const CvMat* _var_type=0,
const CvMat* _missing_mask=0,
CvRTParams params=CvRTParams() );
virtual float predict( const CvMat* sample, const CvMat* missing = 0 )
const;
virtual void clear();
virtual const CvMat* get_var_importance();
virtual float get_proximity( const CvMat* sample_1, const CvMat* sample_2 )
const;
virtual void read( CvFileStorage* fs, CvFileNode* node );
virtual void write( CvFileStorage* fs, const char* name );
CvMat* get_active_var_mask();
CvRNG* get_rng();
int get_tree_count() const;
CvForestTree* get_tree(int i) const;
protected:
bool grow_forest( const CvTermCriteria term_crit );
// array of the trees of the forest
CvForestTree** trees;
CvDTreeTrainData* data;
int ntrees;
int nclasses;
...
};
..
.. index:: CvRTrees::train
.. _CvRTrees::train:
CvRTrees::train
---------------
`id=0.951910664821 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTrees%3A%3Atrain>`__
.. cfunction:: bool CvRTrees::train( const CvMat* train_data, int tflag, const CvMat* responses, const CvMat* comp_idx=0, const CvMat* sample_idx=0, const CvMat* var_type=0, const CvMat* missing_mask=0, CvRTParams params=CvRTParams() )
Trains the Random Trees model.
The method
``CvRTrees::train``
is very similar to the first form of
``CvDTree::train``
() and follows the generic method
``CvStatModel::train``
conventions. All of the specific to the algorithm training parameters are passed as a
:ref:`CvRTParams`
instance. The estimate of the training error (
``oob-error``
) is stored in the protected class member
``oob_error``
.
.. index:: CvRTrees::predict
.. _CvRTrees::predict:
CvRTrees::predict
-----------------
`id=0.175799484956 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTrees%3A%3Apredict>`__
.. cfunction:: double CvRTrees::predict( const CvMat* sample, const CvMat* missing=0 ) const
Predicts the output for the input sample.
The input parameters of the prediction method are the same as in
``CvDTree::predict``
, but the return value type is different. This method returns the cumulative result from all the trees in the forest (the class that receives the majority of voices, or the mean of the regression function estimates).
.. index:: CvRTrees::get_var_importance
.. _CvRTrees::get_var_importance:
CvRTrees::get_var_importance
----------------------------
`id=0.336660771362 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTrees%3A%3Aget_var_importance>`__
.. cfunction:: const CvMat* CvRTrees::get_var_importance() const
Retrieves the variable importance array.
The method returns the variable importance vector, computed at the training stage when
``:ref:`CvRTParams`::calc_var_importance``
is set. If the training flag is not set, then the
``NULL``
pointer is returned. This is unlike decision trees, where variable importance can be computed anytime after the training.
.. index:: CvRTrees::get_proximity
.. _CvRTrees::get_proximity:
CvRTrees::get_proximity
-----------------------
`id=0.2120965436 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvRTrees%3A%3Aget_proximity>`__
.. cfunction:: float CvRTrees::get_proximity( const CvMat* sample_1, const CvMat* sample_2 ) const
Retrieves the proximity measure between two training samples.
The method returns proximity measure between any two samples (the ratio of the those trees in the ensemble, in which the samples fall into the same leaf node, to the total number of the trees).
Example: Prediction of mushroom goodness using random trees classifier
::
#include <float.h>
#include <stdio.h>
#include <ctype.h>
#include "ml.h"
int main( void )
{
CvStatModel* cls = NULL;
CvFileStorage* storage = cvOpenFileStorage( "Mushroom.xml",
NULL,CV_STORAGE_READ );
CvMat* data = (CvMat*)cvReadByName(storage, NULL, "sample", 0 );
CvMat train_data, test_data;
CvMat response;
CvMat* missed = NULL;
CvMat* comp_idx = NULL;
CvMat* sample_idx = NULL;
CvMat* type_mask = NULL;
int resp_col = 0;
int i,j;
CvRTreesParams params;
CvTreeClassifierTrainParams cart_params;
const int ntrain_samples = 1000;
const int ntest_samples = 1000;
const int nvars = 23;
if(data == NULL || data->cols != nvars)
{
puts("Error in source data");
return -1;
}
cvGetSubRect( data, &train_data, cvRect(0, 0, nvars, ntrain_samples) );
cvGetSubRect( data, &test_data, cvRect(0, ntrain_samples, nvars,
ntrain_samples + ntest_samples) );
resp_col = 0;
cvGetCol( &train_data, &response, resp_col);
/* create missed variable matrix */
missed = cvCreateMat(train_data.rows, train_data.cols, CV_8UC1);
for( i = 0; i < train_data.rows; i++ )
for( j = 0; j < train_data.cols; j++ )
CV_MAT_ELEM(*missed,uchar,i,j)
= (uchar)(CV_MAT_ELEM(train_data,float,i,j) < 0);
/* create comp_idx vector */
comp_idx = cvCreateMat(1, train_data.cols-1, CV_32SC1);
for( i = 0; i < train_data.cols; i++ )
{
if(i<resp_col)CV_MAT_ELEM(*comp_idx,int,0,i) = i;
if(i>resp_col)CV_MAT_ELEM(*comp_idx,int,0,i-1) = i;
}
/* create sample_idx vector */
sample_idx = cvCreateMat(1, train_data.rows, CV_32SC1);
for( j = i = 0; i < train_data.rows; i++ )
{
if(CV_MAT_ELEM(response,float,i,0) < 0) continue;
CV_MAT_ELEM(*sample_idx,int,0,j) = i;
j++;
}
sample_idx->cols = j;
/* create type mask */
type_mask = cvCreateMat(1, train_data.cols+1, CV_8UC1);
cvSet( type_mask, cvRealScalar(CV_VAR_CATEGORICAL), 0);
// initialize training parameters
cvSetDefaultParamTreeClassifier((CvStatModelParams*)&cart_params);
cart_params.wrong_feature_as_unknown = 1;
params.tree_params = &cart_params;
params.term_crit.max_iter = 50;
params.term_crit.epsilon = 0.1;
params.term_crit.type = CV_TERMCRIT_ITER|CV_TERMCRIT_EPS;
puts("Random forest results");
cls = cvCreateRTreesClassifier( &train_data,
CV_ROW_SAMPLE,
&response,
(CvStatModelParams*)&
params,
comp_idx,
sample_idx,
type_mask,
missed );
if( cls )
{
CvMat sample = cvMat( 1, nvars, CV_32FC1, test_data.data.fl );
CvMat test_resp;
int wrong = 0, total = 0;
cvGetCol( &test_data, &test_resp, resp_col);
for( i = 0; i < ntest_samples; i++, sample.data.fl += nvars )
{
if( CV_MAT_ELEM(test_resp,float,i,0) >= 0 )
{
float resp = cls->predict( cls, &sample, NULL );
wrong += (fabs(resp-response.data.fl[i]) > 1e-3 ) ? 1 : 0;
total++;
}
}
printf( "Test set error =
}
else
puts("Error forest creation");
cvReleaseMat(&missed);
cvReleaseMat(&sample_idx);
cvReleaseMat(&comp_idx);
cvReleaseMat(&type_mask);
cvReleaseMat(&data);
cvReleaseStatModel(&cls);
cvReleaseFileStorage(&storage);
return 0;
}
..

426
modules/ml/doc/statistical_models.rst Normal file
View File

@ -0,0 +1,426 @@
Statistical Models
==================
.. highlight:: cpp
.. index:: CvStatModel
.. _CvStatModel:
CvStatModel
-----------
`id=0.709260507321 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel>`__
.. ctype:: CvStatModel
Base class for the statistical models in ML.
::
class CvStatModel
{
public:
/* CvStatModel(); */
/* CvStatModel( const CvMat* train_data ... ); */
virtual ~CvStatModel();
virtual void clear()=0;
/* virtual bool train( const CvMat* train_data, [int tflag,] ..., const
CvMat* responses, ...,
[const CvMat* var_idx,] ..., [const CvMat* sample_idx,] ...
[const CvMat* var_type,] ..., [const CvMat* missing_mask,]
<misc_training_alg_params> ... )=0;
*/
/* virtual float predict( const CvMat* sample ... ) const=0; */
virtual void save( const char* filename, const char* name=0 )=0;
virtual void load( const char* filename, const char* name=0 )=0;
virtual void write( CvFileStorage* storage, const char* name )=0;
virtual void read( CvFileStorage* storage, CvFileNode* node )=0;
};
..
In this declaration some methods are commented off. Actually, these are methods for which there is no unified API (with the exception of the default constructor), however, there are many similarities in the syntax and semantics that are briefly described below in this section, as if they are a part of the base class.
.. index:: CvStatModel::CvStatModel
.. _CvStatModel::CvStatModel:
CvStatModel::CvStatModel
------------------------
`id=0.362486770202 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3ACvStatModel>`__
.. cfunction:: CvStatModel::CvStatModel()
Default constructor.
Each statistical model class in ML has a default constructor without parameters. This constructor is useful for 2-stage model construction, when the default constructor is followed by
``train()``
or
``load()``
.
.. index:: CvStatModel::CvStatModel(...)
.. _CvStatModel::CvStatModel(...):
CvStatModel::CvStatModel(...)
-----------------------------
`id=0.672522046035 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3ACvStatModel%28...%29>`__
.. cfunction:: CvStatModel::CvStatModel( const CvMat* train_data ... )
Training constructor.
Most ML classes provide single-step construct and train constructors. This constructor is equivalent to the default constructor, followed by the
``train()``
method with the parameters that are passed to the constructor.
.. index:: CvStatModel::~CvStatModel
.. _CvStatModel::~CvStatModel:
CvStatModel::~CvStatModel
-------------------------
`id=0.264685391089 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3A%7ECvStatModel>`__
.. cfunction:: CvStatModel::~CvStatModel()
Virtual destructor.
The destructor of the base class is declared as virtual, so it is safe to write the following code:
::
CvStatModel* model;
if( use_svm )
model = new CvSVM(... /* SVM params */);
else
model = new CvDTree(... /* Decision tree params */);
...
delete model;
..
Normally, the destructor of each derived class does nothing, but in this instance it calls the overridden method
``clear()``
that deallocates all the memory.
.. index:: CvStatModel::clear
.. _CvStatModel::clear:
CvStatModel::clear
------------------
`id=0.0232469661173 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Aclear>`__
.. cfunction:: void CvStatModel::clear()
Deallocates memory and resets the model state.
The method
``clear``
does the same job as the destructor; it deallocates all the memory occupied by the class members. But the object itself is not destructed, and can be reused further. This method is called from the destructor, from the
``train``
methods of the derived classes, from the methods
``load()``
,
``read()``
or even explicitly by the user.
.. index:: CvStatModel::save
.. _CvStatModel::save:
CvStatModel::save
-----------------
`id=0.852967404887 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Asave>`__
.. cfunction:: void CvStatModel::save( const char* filename, const char* name=0 )
Saves the model to a file.
The method
``save``
stores the complete model state to the specified XML or YAML file with the specified name or default name (that depends on the particular class).
``Data persistence``
functionality from CxCore is used.
.. index:: CvStatModel::load
.. _CvStatModel::load:
CvStatModel::load
-----------------
`id=0.957875843108 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Aload>`__
.. cfunction:: void CvStatModel::load( const char* filename, const char* name=0 )
Loads the model from a file.
The method
``load``
loads the complete model state with the specified name (or default model-dependent name) from the specified XML or YAML file. The previous model state is cleared by
``clear()``
.
Note that the method is virtual, so any model can be loaded using this virtual method. However, unlike the C types of OpenCV that can be loaded using the generic
\
cross{cvLoad}, here the model type must be known, because an empty model must be constructed beforehand. This limitation will be removed in the later ML versions.
.. index:: CvStatModel::write
.. _CvStatModel::write:
CvStatModel::write
------------------
`id=0.167242991674 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Awrite>`__
.. cfunction:: void CvStatModel::write( CvFileStorage* storage, const char* name )
Writes the model to file storage.
The method
``write``
stores the complete model state to the file storage with the specified name or default name (that depends on the particular class). The method is called by
``save()``
.
.. index:: CvStatModel::read
.. _CvStatModel::read:
CvStatModel::read
-----------------
`id=0.959831015705 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Aread>`__
.. cfunction:: void CvStatMode::read( CvFileStorage* storage, CvFileNode* node )
Reads the model from file storage.
The method
``read``
restores the complete model state from the specified node of the file storage. The node must be located by the user using the function
:ref:`GetFileNodeByName`
.
The previous model state is cleared by
``clear()``
.
.. index:: CvStatModel::train
.. _CvStatModel::train:
CvStatModel::train
------------------
`id=0.616920786727 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Atrain>`__
.. cfunction:: bool CvStatMode::train( const CvMat* train_data, [int tflag,] ..., const CvMat* responses, ..., [const CvMat* var_idx,] ..., [const CvMat* sample_idx,] ... [const CvMat* var_type,] ..., [const CvMat* missing_mask,] <misc_training_alg_params> ... )
Trains the model.
The method trains the statistical model using a set of input feature vectors and the corresponding output values (responses). Both input and output vectors/values are passed as matrices. By default the input feature vectors are stored as
``train_data``
rows, i.e. all the components (features) of a training vector are stored continuously. However, some algorithms can handle the transposed representation, when all values of each particular feature (component/input variable) over the whole input set are stored continuously. If both layouts are supported, the method includes
``tflag``
parameter that specifies the orientation:
*
``tflag=CV_ROW_SAMPLE``
means that the feature vectors are stored as rows,
*
``tflag=CV_COL_SAMPLE``
means that the feature vectors are stored as columns.
The
``train_data``
must have a
``CV_32FC1``
(32-bit floating-point, single-channel) format. Responses are usually stored in the 1d vector (a row or a column) of
``CV_32SC1``
(only in the classification problem) or
``CV_32FC1``
format, one value per input vector (although some algorithms, like various flavors of neural nets, take vector responses).
For classification problems the responses are discrete class labels; for regression problems the responses are values of the function to be approximated. Some algorithms can deal only with classification problems, some - only with regression problems, and some can deal with both problems. In the latter case the type of output variable is either passed as separate parameter, or as a last element of
``var_type``
vector:
*
``CV_VAR_CATEGORICAL``
means that the output values are discrete class labels,
*
``CV_VAR_ORDERED(=CV_VAR_NUMERICAL)``
means that the output values are ordered, i.e. 2 different values can be compared as numbers, and this is a regression problem
The types of input variables can be also specified using
``var_type``
. Most algorithms can handle only ordered input variables.
Many models in the ML may be trained on a selected feature subset, and/or on a selected sample subset of the training set. To make it easier for the user, the method
``train``
usually includes
``var_idx``
and
``sample_idx``
parameters. The former identifies variables (features) of interest, and the latter identifies samples of interest. Both vectors are either integer (
``CV_32SC1``
) vectors, i.e. lists of 0-based indices, or 8-bit (
``CV_8UC1``
) masks of active variables/samples. The user may pass
``NULL``
pointers instead of either of the arguments, meaning that all of the variables/samples are used for training.
Additionally some algorithms can handle missing measurements, that is when certain features of certain training samples have unknown values (for example, they forgot to measure a temperature of patient A on Monday). The parameter
``missing_mask``
, an 8-bit matrix the same size as
``train_data``
, is used to mark the missed values (non-zero elements of the mask).
Usually, the previous model state is cleared by
``clear()``
before running the training procedure. However, some algorithms may optionally update the model state with the new training data, instead of resetting it.
.. index:: CvStatModel::predict
.. _CvStatModel::predict:
CvStatModel::predict
--------------------
`id=0.404351209628 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvStatModel%3A%3Apredict>`__
.. cfunction:: float CvStatMode::predict( const CvMat* sample[, <prediction_params>] ) const
Predicts the response for the sample.
The method is used to predict the response for a new sample. In the case of classification the method returns the class label, in the case of regression - the output function value. The input sample must have as many components as the
``train_data``
passed to
``train``
contains. If the
``var_idx``
parameter is passed to
``train``
, it is remembered and then is used to extract only the necessary components from the input sample in the method
``predict``
.
The suffix "const" means that prediction does not affect the internal model state, so the method can be safely called from within different threads.

417
modules/ml/doc/support_vector_machines.rst Normal file
View File

@ -0,0 +1,417 @@
Support Vector Machines
=======================
.. highlight:: cpp
Originally, support vector machines (SVM) was a technique for building an optimal (in some sense) binary (2-class) classifier. Then the technique has been extended to regression and clustering problems. SVM is a partial case of kernel-based methods, it maps feature vectors into higher-dimensional space using some kernel function, and then it builds an optimal linear discriminating function in this space (or an optimal hyper-plane that fits into the training data, ...). in the case of SVM the kernel is not defined explicitly. Instead, a distance between any 2 points in the hyper-space needs to be defined.
The solution is optimal in a sense that the margin between the separating hyper-plane and the nearest feature vectors from the both classes (in the case of 2-class classifier) is maximal. The feature vectors that are the closest to the hyper-plane are called "support vectors", meaning that the position of other vectors does not affect the hyper-plane (the decision function).
There are a lot of good references on SVM. Here are only a few ones to start with.
*
**[Burges98] C. Burges. "A tutorial on support vector machines for pattern recognition", Knowledge Discovery and Data Mining 2(2), 1998.**
(available online at
http://citeseer.ist.psu.edu/burges98tutorial.html
).
*
**LIBSVM - A Library for Support Vector Machines. By Chih-Chung Chang and Chih-Jen Lin**
(
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
)
.. index:: CvSVM
.. _CvSVM:
CvSVM
-----
`id=0.838668945864 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM>`__
.. ctype:: CvSVM
Support Vector Machines.
::
class CvSVM : public CvStatModel
{
public:
// SVM type
enum { C_SVC=100, NU_SVC=101, ONE_CLASS=102, EPS_SVR=103, NU_SVR=104 };
// SVM kernel type
enum { LINEAR=0, POLY=1, RBF=2, SIGMOID=3 };
// SVM params type
enum { C=0, GAMMA=1, P=2, NU=3, COEF=4, DEGREE=5 };
CvSVM();
virtual ~CvSVM();
CvSVM( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _var_idx=0, const CvMat* _sample_idx=0,
CvSVMParams _params=CvSVMParams() );
virtual bool train( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _var_idx=0, const CvMat* _sample_idx=0,
CvSVMParams _params=CvSVMParams() );
virtual bool train_auto( const CvMat* _train_data, const CvMat* _responses,
const CvMat* _var_idx, const CvMat* _sample_idx, CvSVMParams _params,
int k_fold = 10,
CvParamGrid C_grid = get_default_grid(CvSVM::C),
CvParamGrid gamma_grid = get_default_grid(CvSVM::GAMMA),
CvParamGrid p_grid = get_default_grid(CvSVM::P),
CvParamGrid nu_grid = get_default_grid(CvSVM::NU),
CvParamGrid coef_grid = get_default_grid(CvSVM::COEF),
CvParamGrid degree_grid = get_default_grid(CvSVM::DEGREE) );
virtual float predict( const CvMat* _sample ) const;
virtual int get_support_vector_count() const;
virtual const float* get_support_vector(int i) const;
virtual CvSVMParams get_params() const { return params; };
virtual void clear();
static CvParamGrid get_default_grid( int param_id );
virtual void save( const char* filename, const char* name=0 );
virtual void load( const char* filename, const char* name=0 );
virtual void write( CvFileStorage* storage, const char* name );
virtual void read( CvFileStorage* storage, CvFileNode* node );
int get_var_count() const { return var_idx ? var_idx->cols : var_all; }
protected:
...
};
..
.. index:: CvSVMParams
.. _CvSVMParams:
CvSVMParams
-----------
`id=0.577929883484 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVMParams>`__
.. ctype:: CvSVMParams
SVM training parameters.
::
struct CvSVMParams
{
CvSVMParams();
CvSVMParams( int _svm_type, int _kernel_type,
double _degree, double _gamma, double _coef0,
double _C, double _nu, double _p,
CvMat* _class_weights, CvTermCriteria _term_crit );
int svm_type;
int kernel_type;
double degree; // for poly
double gamma; // for poly/rbf/sigmoid
double coef0; // for poly/sigmoid
double C; // for CV_SVM_C_SVC, CV_SVM_EPS_SVR and CV_SVM_NU_SVR
double nu; // for CV_SVM_NU_SVC, CV_SVM_ONE_CLASS, and CV_SVM_NU_SVR
double p; // for CV_SVM_EPS_SVR
CvMat* class_weights; // for CV_SVM_C_SVC
CvTermCriteria term_crit; // termination criteria
};
..
The structure must be initialized and passed to the training method of
:ref:`CvSVM`
.
.. index:: CvSVM::train
.. _CvSVM::train:
CvSVM::train
------------
`id=0.720656682385 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM%3A%3Atrain>`__
.. cfunction:: bool CvSVM::train( const CvMat* _train_data, const CvMat* _responses, const CvMat* _var_idx=0, const CvMat* _sample_idx=0, CvSVMParams _params=CvSVMParams() )
Trains SVM.
The method trains the SVM model. It follows the conventions of the generic
``train``
"method" with the following limitations: only the CV
_
ROW
_
SAMPLE data layout is supported, the input variables are all ordered, the output variables can be either categorical (
``_params.svm_type=CvSVM::C_SVC``
or
``_params.svm_type=CvSVM::NU_SVC``
), or ordered (
``_params.svm_type=CvSVM::EPS_SVR``
or
``_params.svm_type=CvSVM::NU_SVR``
), or not required at all (
``_params.svm_type=CvSVM::ONE_CLASS``
), missing measurements are not supported.
All the other parameters are gathered in
:ref:`CvSVMParams`
structure.
.. index:: CvSVM::train_auto
.. _CvSVM::train_auto:
CvSVM::train_auto
-----------------
`id=0.63289997524 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM%3A%3Atrain_auto>`__
.. cfunction:: train_auto( const CvMat* _train_data, const CvMat* _responses, const CvMat* _var_idx, const CvMat* _sample_idx, CvSVMParams params, int k_fold = 10, CvParamGrid C_grid = get_default_grid(CvSVM::C), CvParamGrid gamma_grid = get_default_grid(CvSVM::GAMMA), CvParamGrid p_grid = get_default_grid(CvSVM::P), CvParamGrid nu_grid = get_default_grid(CvSVM::NU), CvParamGrid coef_grid = get_default_grid(CvSVM::COEF), CvParamGrid degree_grid = get_default_grid(CvSVM::DEGREE) )
Trains SVM with optimal parameters.
:param k_fold: Cross-validation parameter. The training set is divided into ``k_fold`` subsets, one subset being used to train the model, the others forming the test set. So, the SVM algorithm is executed ``k_fold`` times.
The method trains the SVM model automatically by choosing the optimal
parameters
``C``
,
``gamma``
,
``p``
,
``nu``
,
``coef0``
,
``degree``
from
:ref:`CvSVMParams`
. By optimal
one means that the cross-validation estimate of the test set error
is minimal. The parameters are iterated by a logarithmic grid, for
example, the parameter
``gamma``
takes the values in the set
(
:math:`min`
,
:math:`min*step`
,
:math:`min*{step}^2`
, ...
:math:`min*{step}^n`
)
where
:math:`min`
is
``gamma_grid.min_val``
,
:math:`step`
is
``gamma_grid.step``
, and
:math:`n`
is the maximal index such, that
.. math::
\texttt{gamma\_grid.min\_val} * \texttt{gamma\_grid.step} ^n < \texttt{gamma\_grid.max\_val}
So
``step``
must always be greater than 1.
If there is no need in optimization in some parameter, the according grid step should be set to any value less or equal to 1. For example, to avoid optimization in
``gamma``
one should set
``gamma_grid.step = 0``
,
``gamma_grid.min_val``
,
``gamma_grid.max_val``
being arbitrary numbers. In this case, the value
``params.gamma``
will be taken for
``gamma``
.
And, finally, if the optimization in some parameter is required, but
there is no idea of the corresponding grid, one may call the function
``CvSVM::get_default_grid``
. In
order to generate a grid, say, for
``gamma``
, call
``CvSVM::get_default_grid(CvSVM::GAMMA)``
.
This function works for the case of classification
(
``params.svm_type=CvSVM::C_SVC``
or
``params.svm_type=CvSVM::NU_SVC``
)
as well as for the regression
(
``params.svm_type=CvSVM::EPS_SVR``
or
``params.svm_type=CvSVM::NU_SVR``
). If
``params.svm_type=CvSVM::ONE_CLASS``
, no optimization is made and the usual SVM with specified in
``params``
parameters is executed.
.. index:: CvSVM::get_default_grid
.. _CvSVM::get_default_grid:
CvSVM::get_default_grid
-----------------------
`id=0.647625940741 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM%3A%3Aget_default_grid>`__
.. cfunction:: CvParamGrid CvSVM::get_default_grid( int param_id )
Generates a grid for the SVM parameters.
:param param_id: Must be one of the following:
* **CvSVM::C**
* **CvSVM::GAMMA**
* **CvSVM::P**
* **CvSVM::NU**
* **CvSVM::COEF**
* **CvSVM::DEGREE**
.
The grid will be generated for the parameter with this ID.
The function generates a grid for the specified parameter of the SVM algorithm. The grid may be passed to the function
``CvSVM::train_auto``
.
.. index:: CvSVM::get_params
.. _CvSVM::get_params:
CvSVM::get_params
-----------------
`id=0.179013680104 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM%3A%3Aget_params>`__
.. cfunction:: CvSVMParams CvSVM::get_params() const
Returns the current SVM parameters.
This function may be used to get the optimal parameters that were obtained while automatically training
``CvSVM::train_auto``
.
.. index:: CvSVM::get_support_vector*
.. _CvSVM::get_support_vector*:
CvSVM::get_support_vector*
--------------------------
`id=0.988886411952 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/ml/CvSVM%3A%3Aget_support_vector%2A>`__
.. cfunction:: int CvSVM::get_support_vector_count() const
.. cfunction:: const float* CvSVM::get_support_vector(int i) const
Retrieves the number of support vectors and the particular vector.
The methods can be used to retrieve the set of support vectors.

564
modules/objdetect/doc/cascade_classification.rst Normal file
View File

@ -0,0 +1,564 @@
Cascade Classification
======================
.. highlight:: cpp
.. index:: FeatureEvaluator
.. _FeatureEvaluator:
FeatureEvaluator
----------------
`id=0.360131889668 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator>`__
.. ctype:: FeatureEvaluator
Base class for computing feature values in cascade classifiers.
::
class CV_EXPORTS FeatureEvaluator
{
public:
enum { HAAR = 0, LBP = 1 }; // supported feature types
virtual ~FeatureEvaluator(); // destructor
virtual bool read(const FileNode& node);
virtual Ptr<FeatureEvaluator> clone() const;
virtual int getFeatureType() const;
virtual bool setImage(const Mat& img, Size origWinSize);
virtual bool setWindow(Point p);
virtual double calcOrd(int featureIdx) const;
virtual int calcCat(int featureIdx) const;
static Ptr<FeatureEvaluator> create(int type);
};
..
.. index:: FeatureEvaluator::read
cv::FeatureEvaluator::read
--------------------------
`id=0.201865718724 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3Aread>`__
.. cfunction:: bool FeatureEvaluator::read(const FileNode\& node)
Reads parameters of the features from a FileStorage node.
:param node: File node from which the feature parameters are read.
.. index:: FeatureEvaluator::clone
cv::FeatureEvaluator::clone
---------------------------
`id=0.296896128079 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3Aclone>`__
.. cfunction:: Ptr<FeatureEvaluator> FeatureEvaluator::clone() const
Returns a full copy of the feature evaluator.
.. index:: FeatureEvaluator::getFeatureType
cv::FeatureEvaluator::getFeatureType
------------------------------------
`id=0.0597446379803 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3AgetFeatureType>`__
.. cfunction:: int FeatureEvaluator::getFeatureType() const
Returns the feature type (HAAR or LBP for now).
.. index:: FeatureEvaluator::setImage
cv::FeatureEvaluator::setImage
------------------------------
`id=0.203782054077 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3AsetImage>`__
.. cfunction:: bool FeatureEvaluator::setImage(const Mat\& img, Size origWinSize)
Sets the image in which to compute the features.
:param img: Matrix of type ``CV_8UC1`` containing the image in which to compute the features.
:param origWinSize: Size of training images.
.. index:: FeatureEvaluator::setWindow
cv::FeatureEvaluator::setWindow
-------------------------------
`id=0.403436827824 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3AsetWindow>`__
:func:`CascadeClassifier::runAt`
.. cfunction:: bool FeatureEvaluator::setWindow(Point p)
Sets window in the current image in which the features will be computed (called by ).
:param p: The upper left point of window in which the features will be computed. Size of the window is equal to size of training images.
.. index:: FeatureEvaluator::calcOrd
cv::FeatureEvaluator::calcOrd
-----------------------------
`id=0.549815479033 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3AcalcOrd>`__
.. cfunction:: double FeatureEvaluator::calcOrd(int featureIdx) const
Computes value of an ordered (numerical) feature.
:param featureIdx: Index of feature whose value will be computed.
Returns computed value of ordered feature.
.. index:: FeatureEvaluator::calcCat
cv::FeatureEvaluator::calcCat
-----------------------------
`id=0.581631081759 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3AcalcCat>`__
.. cfunction:: int FeatureEvaluator::calcCat(int featureIdx) const
Computes value of a categorical feature.
:param featureIdx: Index of feature whose value will be computed.
Returns computed label of categorical feature, i.e. value from [0,... (number of categories - 1)].
.. index:: FeatureEvaluator::create
cv::FeatureEvaluator::create
----------------------------
`id=0.415170878436 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/FeatureEvaluator%3A%3Acreate>`__
.. cfunction:: static Ptr<FeatureEvaluator> FeatureEvaluator::create(int type)
Constructs feature evaluator.
:param type: Type of features evaluated by cascade (HAAR or LBP for now).
.. index:: CascadeClassifier
.. _CascadeClassifier:
CascadeClassifier
-----------------
`id=0.173067043388 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier>`__
.. ctype:: CascadeClassifier
The cascade classifier class for object detection.
::
class CascadeClassifier
{
public:
// structure for storing tree node
struct CV_EXPORTS DTreeNode
{
int featureIdx; // feature index on which is a split
float threshold; // split threshold of ordered features only
int left; // left child index in the tree nodes array
int right; // right child index in the tree nodes array
};
// structure for storing desision tree
struct CV_EXPORTS DTree
{
int nodeCount; // nodes count
};
// structure for storing cascade stage (BOOST only for now)
struct CV_EXPORTS Stage
{
int first; // first tree index in tree array
int ntrees; // number of trees
float threshold; // treshold of stage sum
};
enum { BOOST = 0 }; // supported stage types
// mode of detection (see parameter flags in function HaarDetectObjects)
enum { DO_CANNY_PRUNING = CV_HAAR_DO_CANNY_PRUNING,
SCALE_IMAGE = CV_HAAR_SCALE_IMAGE,
FIND_BIGGEST_OBJECT = CV_HAAR_FIND_BIGGEST_OBJECT,
DO_ROUGH_SEARCH = CV_HAAR_DO_ROUGH_SEARCH };
CascadeClassifier(); // default constructor
CascadeClassifier(const string& filename);
~CascadeClassifier(); // destructor
bool empty() const;
bool load(const string& filename);
bool read(const FileNode& node);
void detectMultiScale( const Mat& image, vector<Rect>& objects,
double scaleFactor=1.1, int minNeighbors=3,
int flags=0, Size minSize=Size());
bool setImage( Ptr<FeatureEvaluator>&, const Mat& );
int runAt( Ptr<FeatureEvaluator>&, Point );
bool is_stump_based; // true, if the trees are stumps
int stageType; // stage type (BOOST only for now)
int featureType; // feature type (HAAR or LBP for now)
int ncategories; // number of categories (for categorical features only)
Size origWinSize; // size of training images
vector<Stage> stages; // vector of stages (BOOST for now)
vector<DTree> classifiers; // vector of decision trees
vector<DTreeNode> nodes; // vector of tree nodes
vector<float> leaves; // vector of leaf values
vector<int> subsets; // subsets of split by categorical feature
Ptr<FeatureEvaluator> feval; // pointer to feature evaluator
Ptr<CvHaarClassifierCascade> oldCascade; // pointer to old cascade
};
..
.. index:: CascadeClassifier::CascadeClassifier
cv::CascadeClassifier::CascadeClassifier
----------------------------------------
`id=0.751407128029 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3ACascadeClassifier>`__
.. cfunction:: CascadeClassifier::CascadeClassifier(const string\& filename)
Loads the classifier from file.
:param filename: Name of file from which classifier will be load.
.. index:: CascadeClassifier::empty
cv::CascadeClassifier::empty
----------------------------
`id=0.907371026536 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3Aempty>`__
.. cfunction:: bool CascadeClassifier::empty() const
Checks if the classifier has been loaded or not.
.. index:: CascadeClassifier::load
cv::CascadeClassifier::load
---------------------------
`id=0.689328093704 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3Aload>`__
.. cfunction:: bool CascadeClassifier::load(const string\& filename)
Loads the classifier from file. The previous content is destroyed.
:param filename: Name of file from which classifier will be load. File may contain as old haar classifier (trained by haartraining application) or new cascade classifier (trained traincascade application).
.. index:: CascadeClassifier::read
cv::CascadeClassifier::read
---------------------------
`id=0.21698114693 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3Aread>`__
.. cfunction:: bool CascadeClassifier::read(const FileNode\& node)
Reads the classifier from a FileStorage node. File may contain a new cascade classifier (trained traincascade application) only.
.. index:: CascadeClassifier::detectMultiScale
cv::CascadeClassifier::detectMultiScale
---------------------------------------
`id=0.0317051017457 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3AdetectMultiScale>`__
.. cfunction:: void CascadeClassifier::detectMultiScale( const Mat\& image, vector<Rect>\& objects, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size())
Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.
:param image: Matrix of type ``CV_8U`` containing the image in which to detect objects.
:param objects: Vector of rectangles such that each rectangle contains the detected object.
:param scaleFactor: Specifies how much the image size is reduced at each image scale.
:param minNeighbors: Speficifes how many neighbors should each candiate rectangle have to retain it.
:param flags: This parameter is not used for new cascade and have the same meaning for old cascade as in function cvHaarDetectObjects.
:param minSize: The minimum possible object size. Objects smaller than that are ignored.
.. index:: CascadeClassifier::setImage
cv::CascadeClassifier::setImage
-------------------------------
`id=0.632605719384 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3AsetImage>`__
.. cfunction:: bool CascadeClassifier::setImage( Ptr<FeatureEvaluator>\& feval, const Mat\& image )
Sets the image for detection (called by detectMultiScale at each image level).
:param feval: Pointer to feature evaluator which is used for computing features.
:param image: Matrix of type ``CV_8UC1`` containing the image in which to compute the features.
.. index:: CascadeClassifier::runAt
cv::CascadeClassifier::runAt
----------------------------
`id=0.159942031477 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/CascadeClassifier%3A%3ArunAt>`__
.. cfunction:: int CascadeClassifier::runAt( Ptr<FeatureEvaluator>\& feval, Point pt )
Runs the detector at the specified point (the image that the detector is working with should be set by setImage).
:param feval: Feature evaluator which is used for computing features.
:param pt: The upper left point of window in which the features will be computed. Size of the window is equal to size of training images.
Returns:
1 - if cascade classifier detects object in the given location.
-si - otherwise. si is an index of stage which first predicted that given window is a background image.
.. index:: groupRectangles
cv::groupRectangles
-------------------
`id=0.226659440065 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/objdetect/groupRectangles>`__
.. cfunction:: void groupRectangles(vector<Rect>\& rectList, int groupThreshold, double eps=0.2)
Groups the object candidate rectangles
:param rectList: The input/output vector of rectangles. On output there will be retained and grouped rectangles
:param groupThreshold: The minimum possible number of rectangles, minus 1, in a group of rectangles to retain it.
:param eps: The relative difference between sides of the rectangles to merge them into a group
The function is a wrapper for a generic function
:func:`partition`
. It clusters all the input rectangles using the rectangle equivalence criteria, that combines rectangles that have similar sizes and similar locations (the similarity is defined by
``eps``
). When
``eps=0``
, no clustering is done at all. If
:math:`\texttt{eps}\rightarrow +\inf`
, all the rectangles will be put in one cluster. Then, the small clusters, containing less than or equal to
``groupThreshold``
rectangles, will be rejected. In each other cluster the average rectangle will be computed and put into the output rectangle list.

8
modules/objdetect/doc/objdetect.rst Normal file
View File

@ -0,0 +1,8 @@
****************
Object Detection
****************
.. toctree::
:maxdepth: 2
cascade_classification

BIN
modules/python/hdr_parser.pyc Executable file
View File

Binary file not shown.

471
modules/video/doc/motion_analysis_and_object_tracking.rst Normal file
View File

@ -0,0 +1,471 @@
Motion Analysis and Object Tracking
===================================
.. highlight:: cpp
.. index:: calcOpticalFlowPyrLK
cv::calcOpticalFlowPyrLK
------------------------
`id=0.801764538588 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/calcOpticalFlowPyrLK>`__
.. cfunction:: void calcOpticalFlowPyrLK( const Mat\& prevImg, const Mat\& nextImg, const vector<Point2f>\& prevPts, vector<Point2f>\& nextPts, vector<uchar>\& status, vector<float>\& err, Size winSize=Size(15,15), int maxLevel=3, TermCriteria criteria=TermCriteria( TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01), double derivLambda=0.5, int flags=0 )
Calculates the optical flow for a sparse feature set using the iterative Lucas-Kanade method with pyramids
:param prevImg: The first 8-bit single-channel or 3-channel input image
:param nextImg: The second input image of the same size and the same type as ``prevImg``
:param prevPts: Vector of points for which the flow needs to be found
:param nextPts: The output vector of points containing the calculated new positions of the input features in the second image
:param status: The output status vector. Each element of the vector is set to 1 if the flow for the corresponding features has been found, 0 otherwise
:param err: The output vector that will contain the difference between patches around the original and moved points
:param winSize: Size of the search window at each pyramid level
:param maxLevel: 0-based maximal pyramid level number. If 0, pyramids are not used (single level), if 1, two levels are used etc.
:param criteria: Specifies the termination criteria of the iterative search algorithm (after the specified maximum number of iterations ``criteria.maxCount`` or when the search window moves by less than ``criteria.epsilon``
:param derivLambda: The relative weight of the spatial image derivatives impact to the optical flow estimation. If ``derivLambda=0`` , only the image intensity is used, if ``derivLambda=1`` , only derivatives are used. Any other values between 0 and 1 means that both derivatives and the image intensity are used (in the corresponding proportions).
:param flags: The operation flags:
* **OPTFLOW_USE_INITIAL_FLOW** use initial estimations stored in ``nextPts`` . If the flag is not set, then initially :math:`\texttt{nextPts}\leftarrow\texttt{prevPts}`
The function implements the sparse iterative version of the Lucas-Kanade optical flow in pyramids, see
Bouguet00
.
.. index:: calcOpticalFlowFarneback
cv::calcOpticalFlowFarneback
----------------------------
`id=0.147581673853 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/calcOpticalFlowFarneback>`__
.. cfunction:: void calcOpticalFlowFarneback( const Mat\& prevImg, const Mat\& nextImg, Mat\& flow, double pyrScale, int levels, int winsize, int iterations, int polyN, double polySigma, int flags )
Computes dense optical flow using Gunnar Farneback's algorithm
:param prevImg: The first 8-bit single-channel input image
:param nextImg: The second input image of the same size and the same type as ``prevImg``
:param flow: The computed flow image; will have the same size as ``prevImg`` and type ``CV_32FC2``
:param pyrScale: Specifies the image scale (<1) to build the pyramids for each image. ``pyrScale=0.5`` means the classical pyramid, where each next layer is twice smaller than the previous
:param levels: The number of pyramid layers, including the initial image. ``levels=1`` means that no extra layers are created and only the original images are used
:param winsize: The averaging window size; The larger values increase the algorithm robustness to image noise and give more chances for fast motion detection, but yield more blurred motion field
:param iterations: The number of iterations the algorithm does at each pyramid level
:param polyN: Size of the pixel neighborhood used to find polynomial expansion in each pixel. The larger values mean that the image will be approximated with smoother surfaces, yielding more robust algorithm and more blurred motion field. Typically, ``polyN`` =5 or 7
:param polySigma: Standard deviation of the Gaussian that is used to smooth derivatives that are used as a basis for the polynomial expansion. For ``polyN=5`` you can set ``polySigma=1.1`` , for ``polyN=7`` a good value would be ``polySigma=1.5``
:param flags: The operation flags; can be a combination of the following:
* **OPTFLOW_USE_INITIAL_FLOW** Use the input ``flow`` as the initial flow approximation
* **OPTFLOW_FARNEBACK_GAUSSIAN** Use a Gaussian :math:`\texttt{winsize}\times\texttt{winsize}` filter instead of box filter of the same size for optical flow estimation. Usually, this option gives more accurate flow than with a box filter, at the cost of lower speed (and normally ``winsize`` for a Gaussian window should be set to a larger value to achieve the same level of robustness)
The function finds optical flow for each
``prevImg``
pixel using the alorithm so that
.. math::
\texttt{prevImg} (x,y) \sim \texttt{nextImg} ( \texttt{flow} (x,y)[0], \texttt{flow} (x,y)[1])
.. index:: updateMotionHistory
cv::updateMotionHistory
-----------------------
`id=0.684725809289 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/updateMotionHistory>`__
.. cfunction:: void updateMotionHistory( const Mat\& silhouette, Mat\& mhi, double timestamp, double duration )
Updates the motion history image by a moving silhouette.
:param silhouette: Silhouette mask that has non-zero pixels where the motion occurs
:param mhi: Motion history image, that is updated by the function (single-channel, 32-bit floating-point)
:param timestamp: Current time in milliseconds or other units
:param duration: Maximal duration of the motion track in the same units as ``timestamp``
The function updates the motion history image as following:
.. math::
\texttt{mhi} (x,y)= \forkthree{\texttt{timestamp}}{if $\texttt{silhouette}(x,y) \ne 0$}{0}{if $\texttt{silhouette}(x,y) = 0$ and $\texttt{mhi} < (\texttt{timestamp} - \texttt{duration})$}{\texttt{mhi}(x,y)}{otherwise}
That is, MHI pixels where motion occurs are set to the current
``timestamp``
, while the pixels where motion happened last time a long time ago are cleared.
The function, together with
:func:`calcMotionGradient`
and
:func:`calcGlobalOrientation`
, implements the motion templates technique, described in
Davis97
and
Bradski00
.
See also the OpenCV sample
``motempl.c``
that demonstrates the use of all the motion template functions.
.. index:: calcMotionGradient
cv::calcMotionGradient
----------------------
`id=0.911487015982 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/calcMotionGradient>`__
.. cfunction:: void calcMotionGradient( const Mat\& mhi, Mat\& mask, Mat\& orientation, double delta1, double delta2, int apertureSize=3 )
Calculates the gradient orientation of a motion history image.
:param mhi: Motion history single-channel floating-point image
:param mask: The output mask image; will have the type ``CV_8UC1`` and the same size as ``mhi`` . Its non-zero elements will mark pixels where the motion gradient data is correct
:param orientation: The output motion gradient orientation image; will have the same type and the same size as ``mhi`` . Each pixel of it will the motion orientation in degrees, from 0 to 360.
:param delta1, delta2: The minimal and maximal allowed difference between ``mhi`` values within a pixel neighorhood. That is, the function finds the minimum ( :math:`m(x,y)` ) and maximum ( :math:`M(x,y)` ) ``mhi`` values over :math:`3 \times 3` neighborhood of each pixel and marks the motion orientation at :math:`(x, y)` as valid only if
.. math::
\min ( \texttt{delta1} , \texttt{delta2} ) \le M(x,y)-m(x,y) \le \max ( \texttt{delta1} , \texttt{delta2} ).
:param apertureSize: The aperture size of :func:`Sobel` operator
The function calculates the gradient orientation at each pixel
:math:`(x, y)`
as:
.. math::
\texttt{orientation} (x,y)= \arctan{\frac{d\texttt{mhi}/dy}{d\texttt{mhi}/dx}}
(in fact,
:func:`fastArctan`
and
:func:`phase`
are used, so that the computed angle is measured in degrees and covers the full range 0..360). Also, the
``mask``
is filled to indicate pixels where the computed angle is valid.
.. index:: calcGlobalOrientation
cv::calcGlobalOrientation
-------------------------
`id=0.785441857219 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/calcGlobalOrientation>`__
.. cfunction:: double calcGlobalOrientation( const Mat\& orientation, const Mat\& mask, const Mat\& mhi, double timestamp, double duration )
Calculates the global motion orientation in some selected region.
:param orientation: Motion gradient orientation image, calculated by the function :func:`calcMotionGradient`
:param mask: Mask image. It may be a conjunction of a valid gradient mask, also calculated by :func:`calcMotionGradient` , and the mask of the region, whose direction needs to be calculated
:param mhi: The motion history image, calculated by :func:`updateMotionHistory`
:param timestamp: The timestamp passed to :func:`updateMotionHistory`
:param duration: Maximal duration of motion track in milliseconds, passed to :func:`updateMotionHistory`
The function calculates the average
motion direction in the selected region and returns the angle between
0 degrees and 360 degrees. The average direction is computed from
the weighted orientation histogram, where a recent motion has larger
weight and the motion occurred in the past has smaller weight, as recorded in
``mhi``
.
.. index:: CamShift
cv::CamShift
------------
`id=0.364212510583 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/CamShift>`__
.. cfunction:: RotatedRect CamShift( const Mat\& probImage, Rect\& window, TermCriteria criteria )
Finds the object center, size, and orientation
:param probImage: Back projection of the object histogram; see :func:`calcBackProject`
:param window: Initial search window
:param criteria: Stop criteria for the underlying :func:`meanShift`
The function implements the CAMSHIFT object tracking algrorithm
Bradski98
.
First, it finds an object center using
:func:`meanShift`
and then adjust the window size and finds the optimal rotation. The function returns the rotated rectangle structure that includes the object position, size and the orientation. The next position of the search window can be obtained with
``RotatedRect::boundingRect()``
.
See the OpenCV sample
``camshiftdemo.c``
that tracks colored objects.
.. index:: meanShift
cv::meanShift
-------------
`id=0.437046716762 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/meanShift>`__
.. cfunction:: int meanShift( const Mat\& probImage, Rect\& window, TermCriteria criteria )
Finds the object on a back projection image.
:param probImage: Back projection of the object histogram; see :func:`calcBackProject`
:param window: Initial search window
:param criteria: The stop criteria for the iterative search algorithm
The function implements iterative object search algorithm. It takes the object back projection on input and the initial position. The mass center in
``window``
of the back projection image is computed and the search window center shifts to the mass center. The procedure is repeated until the specified number of iterations
``criteria.maxCount``
is done or until the window center shifts by less than
``criteria.epsilon``
. The algorithm is used inside
:func:`CamShift`
and, unlike
:func:`CamShift`
, the search window size or orientation do not change during the search. You can simply pass the output of
:func:`calcBackProject`
to this function, but better results can be obtained if you pre-filter the back projection and remove the noise (e.g. by retrieving connected components with
:func:`findContours`
, throwing away contours with small area (
:func:`contourArea`
) and rendering the remaining contours with
:func:`drawContours`
)
.. index:: KalmanFilter
.. _KalmanFilter:
KalmanFilter
------------
`id=0.4483617174 Comments from the Wiki <http://opencv.willowgarage.com/wiki/documentation/cpp/video/KalmanFilter>`__
.. ctype:: KalmanFilter
Kalman filter class
::
class KalmanFilter
{
public:
KalmanFilter();
KalmanFilter(int dynamParams, int measureParams, int controlParams=0);
void init(int dynamParams, int measureParams, int controlParams=0);
// predicts statePre from statePost
const Mat& predict(const Mat& control=Mat());
// corrects statePre based on the input measurement vector
// and stores the result to statePost.
const Mat& correct(const Mat& measurement);
Mat statePre; // predicted state (x'(k)):
// x(k)=A*x(k-1)+B*u(k)
Mat statePost; // corrected state (x(k)):
// x(k)=x'(k)+K(k)*(z(k)-H*x'(k))
Mat transitionMatrix; // state transition matrix (A)
Mat controlMatrix; // control matrix (B)
// (it is not used if there is no control)
Mat measurementMatrix; // measurement matrix (H)
Mat processNoiseCov; // process noise covariance matrix (Q)
Mat measurementNoiseCov;// measurement noise covariance matrix (R)
Mat errorCovPre; // priori error estimate covariance matrix (P'(k)):
// P'(k)=A*P(k-1)*At + Q)*/
Mat gain; // Kalman gain matrix (K(k)):
// K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)
Mat errorCovPost; // posteriori error estimate covariance matrix (P(k)):
// P(k)=(I-K(k)*H)*P'(k)
...
};
..
The class implements standard Kalman filter
http://en.wikipedia.org/wiki/Kalman_filter
. However, you can modify
``transitionMatrix``
,
``controlMatrix``
and
``measurementMatrix``
to get the extended Kalman filter functionality. See the OpenCV sample
``kalman.c``

8
modules/video/doc/video.rst Normal file
View File

@ -0,0 +1,8 @@
**************
Video Analysis
**************
.. toctree::
:maxdepth: 2
motion_analysis_and_object_tracking