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

Improved RST parser; fixed small typos found by new parser

Browse Source
This commit is contained in:
Andrey Kamaev 2011-07-07 11:23:51 +00:00
parent edf0b40d42
commit 741a689f65
14 changed files with 169 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst
View File

@ -180,7 +180,7 @@ The function returns the final re-projection error.
.. note::
If you use a non-square (=non-NxN) grid and :ocv:func:`findChessboardCorners` for calibration, and ``calibrateCamera`` returns bad values (zero distortion coefficients, an image center very far from ``(w/2-0.5,h/2-0.5)``, and/or large differences between :math:`f_x` and :math:`f_y` (ratios of 10:1 or more)), then you have probably used ``patternSize=cvSize(rows,cols)`` instead of using ``patternSize=cvSize(cols,rows)`` in :ocv:func:`findChessboardCorners` .
If you use a non-square (=non-NxN) grid and :ocv:func:`findChessboardCorners` for calibration, and ``calibrateCamera`` returns bad values (zero distortion coefficients, an image center very far from ``(w/2-0.5,h/2-0.5)``, and/or large differences between :math:`f_x` and :math:`f_y` (ratios of 10:1 or more)), then you have probably used ``patternSize=cvSize(rows,cols)`` instead of using ``patternSize=cvSize(cols,rows)`` in :ocv:func:`findChessboardCorners` .
.. seealso::

2
modules/core/doc/dynamic_structures.rst
View File

@ -176,6 +176,8 @@ The structure ``CvGraphScanner`` is used for depth-first graph traversal. See di
CvTreeNodeIterator
------------------
.. ocv:struct:: CvTreeNodeIterator
The structure ``CvTreeNodeIterator`` is used to traverse trees of sequences.
ClearGraph

2
modules/core/doc/operations_on_arrays.rst
View File

@ -2398,7 +2398,7 @@ For some values of ``p`` , such as integer values, 0.5 and -0.5, specialized fas
RNG
---
.. ocv:class: RNG
.. ocv:class:: RNG
Random number generator. It encapsulates the state (currently, a 64-bit integer) and has methods to return scalar random values and to fill arrays with random values. Currently it supports uniform and Gaussian (normal) distributions. The generator uses Multiply-With-Carry algorithm, introduced by G. Marsaglia (
http://en.wikipedia.org/wiki/Multiply-with-carry

6
modules/gpu/doc/image_filtering.rst
View File

@ -240,7 +240,7 @@ gpu::boxFilter
:param anchor: Anchor point. The default value ``Point(-1, -1)`` means that the anchor is at the kernel center.
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. seealso:: :ocv:func:`boxFilter`
@ -365,7 +365,7 @@ gpu::morphologyEx
:param iterations: Number of times erosion and dilation to be applied.
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. seealso:: :ocv:func:`morphologyEx`
@ -433,7 +433,7 @@ gpu::Laplacian
:param scale: Optional scale factor for the computed Laplacian values. By default, no scaling is applied (see :ocv:func:`getDerivKernels` ).
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. note:: This filter does not check out-of-border accesses, so only a proper sub-matrix of a bigger matrix has to be passed to it.
.. seealso:: :ocv:func:`Laplacian`,:ocv:func:`gpu::filter2D` .

4
modules/gpu/doc/initalization_and_information.rst
View File

@ -166,9 +166,9 @@ Class providing a set of static methods to check what NVIDIA* card architecture
The following method checks whether the module was built with the support of the given feature:
.. ocv:function:: static bool gpu::TargetArchs::builtWith(GpuFeature feature)
.. ocv:function:: static bool gpu::TargetArchs::builtWith(GpuFeature feature)
:param feature: Feature to be checked. See :ocv:class:`gpu::GpuFeature`.
:param feature: Feature to be checked. See :ocv:class:`gpu::GpuFeature`.
There is a set of methods to check whether the module contains intermediate (PTX) or binary GPU code for the given architecture(s):

2
modules/gpu/doc/matrix_reductions.rst
View File

@ -7,7 +7,7 @@ Matrix Reductions
gpu::meanStdDev
-------------------
.. cpp:function:: void gpu::meanStdDev(const GpuMat\& mtx, Scalar\& mean, Scalar\& stddev)
.. ocv:function:: void gpu::meanStdDev(const GpuMat\& mtx, Scalar\& mean, Scalar\& stddev)
Computes a mean value and a standard deviation of matrix elements.

2
modules/imgproc/doc/filtering.rst
View File

@ -579,7 +579,7 @@ The function supports the mode when ``src`` is already in the middle of ``dst``
.. seealso::
:ocv:func:`borderInterpolate`
:ocv:func:`borderInterpolate`
createBoxFilter

4
modules/imgproc/doc/geometric_transformations.rst
View File

@ -486,7 +486,7 @@ Applies a perspective transformation to an image.
:param dst: Destination image that has the size ``dsize`` and the same type as ``src`` .
:param M: :math:`3\times 3` transformation matrix.
:param M: :math:`3\times 3` transformation matrix.
:param dsize: Size of the destination image.
@ -697,4 +697,4 @@ where ``undistort()`` is an approximate iterative algorithm that estimates the n
The function can be used for both a stereo camera head or a monocular camera (when R is empty).

16
modules/imgproc/doc/histograms.rst
View File

@ -124,9 +124,9 @@ Calculates the back projection of a histogram.
:param hist: Input histogram that can be dense or sparse.
:param backProject: Destination back projection aray that is a single-channel array of the same size and depth as ``arrays[0]`` .
:param ranges: Array of arrays of the histogram bin boundaries in each dimension. See :ocv:func:`calcHist` .
:param scale: Optional scale factor for the output back projection.
:param uniform: Flag indicating whether the histogram is uniform or not (see above).
@ -164,16 +164,16 @@ Compares two histograms.
:param H1: First compared histogram.
:param H2: Second compared histogram of the same size as ``H1`` .
:param method: Comparison method that could be one of the following:
* **CV_COMP_CORREL** Correlation
* **CV_COMP_CORREL** Correlation
* **CV_COMP_CHISQR** Chi-Square
* **CV_COMP_CHISQR** Chi-Square
* **CV_COMP_INTERSECT** Intersection
* **CV_COMP_INTERSECT** Intersection
* **CV_COMP_BHATTACHARYYA** Bhattacharyya distance
* **CV_COMP_BHATTACHARYYA** Bhattacharyya distance
The functions ``compareHist`` compare two dense or two sparse histograms using the specified method:
@ -588,4 +588,4 @@ between the calculated minimum and maximum distances are incremented
.. [RubnerSept98] Y. Rubner. C. Tomasi, L.J. Guibas. *The Earth Mover’s Distance as a Metric for Image Retrieval*. Technical Report STAN-CS-TN-98-86, Department of Computer Science, Stanford University, September 1998.
.. [Iivarinen97] Jukka Iivarinen, Markus Peura, Jaakko Srel, and Ari Visa. *Comparison of Combined Shape Descriptors for Irregular Objects*, 8th British Machine Vision Conference, BMVC'97. http://www.cis.hut.fi/research/IA/paper/publications/bmvc97/bmvc97.html
.. [Iivarinen97] Jukka Iivarinen, Markus Peura, Jaakko Srel, and Ari Visa. *Comparison of Combined Shape Descriptors for Irregular Objects*, 8th British Machine Vision Conference, BMVC'97. http://www.cis.hut.fi/research/IA/paper/publications/bmvc97/bmvc97.html

20
modules/imgproc/doc/miscellaneous_transformations.rst
View File

@ -24,7 +24,7 @@ Applies an adaptive threshold to an array.
:param adaptiveMethod: Adaptive thresholding algorithm to use, ``ADAPTIVE_THRESH_MEAN_C`` or ``ADAPTIVE_THRESH_GAUSSIAN_C`` . See the details below.
:param thresholdType: Thresholding type that must be either ``THRESH_BINARY`` or ``THRESH_BINARY_INV`` .
:param blockSize: Size of a pixel neighborhood that is used to calculate a threshold value for the pixel: 3, 5, 7, and so on.
:param C: Constant subtracted from the mean or weighted mean (see the details below). Normally, it is positive but may be zero or negative as well.
@ -497,10 +497,10 @@ Fills a connected component with the given color.
:param image: Input/output 1- or 3-channel, 8-bit, or floating-point image. It is modified by the function unless the ``FLOODFILL_MASK_ONLY`` flag is set in the second variant of the function. See the details below.
:param mask: (For the second function only) Operation mask that should be a single-channel 8-bit image, 2 pixels wider and 2 pixels taller. The function uses and updates the mask, so you take responsibility of initializing the ``mask`` content. Flood-filling cannot go across non-zero pixels in the mask. For example, an edge detector output can be used as a mask to stop filling at edges. It is possible to use the same mask in multiple calls to the function to make sure the filled area does not overlap.
.. note::
Since the mask is larger than the filled image, a pixel :math:`(x, y)` in ``image`` corresponds to the pixel :math:`(x+1, y+1)` in the ``mask`` .
.. note::
Since the mask is larger than the filled image, a pixel :math:`(x, y)` in ``image`` corresponds to the pixel :math:`(x+1, y+1)` in the ``mask`` .
:param seed: Starting point.
:param newVal: New value of the repainted domain pixels.
@ -608,9 +608,9 @@ Restores the selected region in an image using the region neighborhood.
:param flags: Inpainting method that could be one of the following:
* **INPAINT_NS** Navier-Stokes based method.
* **INPAINT_NS** Navier-Stokes based method.
* **INPAINT_TELEA** Method by Alexandru Telea [Telea04]_.
* **INPAINT_TELEA** Method by Alexandru Telea [Telea04]_.
The function reconstructs the selected image area from the pixel near the area boundary. The function may be used to remove dust and scratches from a scanned photo, or to remove undesirable objects from still images or video. See
http://en.wikipedia.org/wiki/Inpainting
@ -821,11 +821,11 @@ Runs the GrabCut algorithm.
:param mode: Operation mode that could be one of the following:
* **GC_INIT_WITH_RECT** The function initializes the state and the mask using the provided rectangle. After that it runs ``iterCount`` iterations of the algorithm.
* **GC_INIT_WITH_RECT** The function initializes the state and the mask using the provided rectangle. After that it runs ``iterCount`` iterations of the algorithm.
* **GC_INIT_WITH_MASK** The function initializes the state using the provided mask. Note that ``GC_INIT_WITH_RECT`` and ``GC_INIT_WITH_MASK`` can be combined. Then, all the pixels outside of the ROI are automatically initialized with ``GC_BGD`` .
* **GC_INIT_WITH_MASK** The function initializes the state using the provided mask. Note that ``GC_INIT_WITH_RECT`` and ``GC_INIT_WITH_MASK`` can be combined. Then, all the pixels outside of the ROI are automatically initialized with ``GC_BGD`` .
* **GC_EVAL** The value means that the algorithm should just resume.
* **GC_EVAL** The value means that the algorithm should just resume.
The function implements the `GrabCut image segmentation algorithm <http://en.wikipedia.org/wiki/GrabCut>`_.
See the sample ``grabcut.cpp`` to learn how to use the function.

2
modules/imgproc/doc/motion_analysis_and_object_tracking.rst
View File

@ -85,7 +85,7 @@ Adds the per-element product of two input images to the accumulator.
:param src1: First input image, 1- or 3-channel, 8-bit or 32-bit floating point.
:param src2: 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.

2
modules/imgproc/doc/object_detection.rst
View File

@ -19,7 +19,7 @@ Compares a template against overlapped image regions.
:param templ: Searched template. It must be not greater than the source image and have the same data type.
:param result: Map of comparison results. It must be single-channel 32-bit floating-point. If ``image`` is :math:`W \times H` and ``templ`` is :math:`w \times h` , then ``result`` is :math:`(W-w+1) \times (H-h+1)` .
:param method: Parameter specifying the comparison method (see below).
The function slides through ``image`` , compares the

160
modules/java/rst_parser.py
View File

@ -48,7 +48,7 @@ class ParamParser(object):
offset = line.find(":param")
assert offset > 0
self.prefix = line[:offset]
assert self.prefix==" "*len(self.prefix)
assert self.prefix==" "*len(self.prefix), ":param definition should be prefixed with spaces"
line = line[offset + 6:].lstrip()
name_end = line.find(":")
assert name_end > 0
@ -72,25 +72,46 @@ class RstParser(object):
def __init__(self, cpp_parser):
self.cpp_parser = cpp_parser
self.definitions = {}
self.sections_parsed = 0
self.sections_total = 0
self.sections_skipped = 0
def parse(self, module_path):
def parse(self, module_name, module_path=None):
if module_path is None:
module_path = "../" + module_name
doclist = glob.glob(os.path.join(module_path,"doc/*.rst"))
for doc in doclist:
self.parse_rst_file(doc)
self.parse_rst_file(module_name, doc)
def parse_section_safe(self, module_name, section_name, file_name, lineno, lines):
try:
self.parse_section(module_name, section_name, file_name, lineno, lines)
except AssertionError, args:
print "RST parser error: assertion in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
print " Details: %s" % args
def parse_section(self, module_name, section_name, file_name, lineno, lines):
self.sections_total += 1
# skip sections having whitespace in name
if section_name.find(" ") >= 0 and section_name.find("::operator") < 0:
print "SKIPPED: \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
self.sections_skipped += 1
return
def parse_section(self, section_name, file_name, lineno, lines):
func = {}
func["name"] = section_name
func["file"] = file_name
func["line"] = lineno
func["module"] = module_name
# parse section name
class_separator_idx = func["name"].find("::")
section_name = self.parse_namespace(func, section_name)
class_separator_idx = section_name.find("::")
if class_separator_idx > 0:
func["class"] = func["name"][:class_separator_idx]
func["method"] = func["name"][class_separator_idx+2:]
func["class"] = section_name[:class_separator_idx]
func["method"] = section_name[class_separator_idx+2:]
else:
func["method"] = func["name"]
func["method"] = section_name
skip_code_lines = False
expected_brief = True
@ -107,7 +128,7 @@ class RstParser(object):
# skip lines if line-skipping mode is activated
if skip_code_lines:
if not l or l.startswith(" ") or l.startswith("\t"):
if not l or l.startswith(" "):
continue
else:
skip_code_lines = False
@ -132,7 +153,7 @@ class RstParser(object):
continue
else:
self.add_new_pdecl(func, pdecl)
#do not continue - current line can contain next parameter definition
# do not continue - current line can contain next parameter definition
# todo: parse structure members; skip them for now
if ll.startswith(".. ocv:member::"):
@ -185,6 +206,9 @@ class RstParser(object):
# record other lines as long description
func["long"] = func.get("long", "") + "\n" + ll
# endfor l in lines
if fdecl.balance != 0:
print "RST parser error: invalid parentheses balance in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
# save last parameter if needed
if pdecl.active:
@ -194,13 +218,17 @@ class RstParser(object):
func = self.normalize(func)
if self.validate(func):
self.definitions[func["name"]] = func
self.sections_parsed += 1
#self.print_info(func)
elif func:
self.print_info(func, True)
pass
def parse_rst_file(self, doc):
def parse_rst_file(self, module_name, doc):
doc = os.path.abspath(doc)
lineno = 0
whitespace_warnings = 0
max_whitespace_warnings = 10
lines = []
flineno = 0
@ -210,14 +238,23 @@ class RstParser(object):
df = open(doc, "rt")
for l in df.readlines():
lineno += 1
# handle tabs
if l.find("\t") >= 0:
whitespace_warnings += 1
if whitespace_warnings <= max_whitespace_warnings:
print "RST parser warning: tab symbol instead of space is used at file %s (line %s)" % (doc, lineno)
l = l.replace("\t", " ")
# handle first line
if prev_line == None:
prev_line = l.rstrip()
continue
ll = l.rstrip()
if len(prev_line) > 0 and len(ll) >= len(prev_line) and ll == "-" * len(ll):
#new function candidate
# new function candidate
if len(lines) > 1:
self.parse_section(fname, doc, flineno, lines[:len(lines)-1])
self.parse_section_safe(module_name, fname, doc, flineno, lines[:len(lines)-1])
lines = []
flineno = lineno-1
fname = prev_line.strip()
@ -226,9 +263,18 @@ class RstParser(object):
prev_line = ll
df.close()
#don't forget about the last function section in file!!!
# don't forget about the last function section in file!!!
if len(lines) > 1:
self.parse_section(fname, doc, flineno, lines[:len(lines)])
self.parse_section_safe(module_name, fname, doc, flineno, lines[:len(lines)])
def parse_namespace(self, func, section_name):
known_namespaces = ["cv", "gpu", "flann"]
l = section_name.strip()
for namespace in known_namespaces:
if l.startswith(namespace + "::"):
func["namespace"] = namespace
return l[len(namespace)+2:]
return section_name
def add_new_fdecl(self, func, decl):
decls = func.get("decls",[])
@ -242,40 +288,43 @@ class RstParser(object):
def add_new_pdecl(self, func, decl):
params = func.get("params",{})
if decl.name in params:
print "Parser error: parameter \"%s\" for %s is defined multiple times. See %s line %s" \
print "RST parser error: redefinition of parameter \"%s\" in \"%s\" File: %s (line %s)" \
% (decl.name, func["name"], func["file"], func["line"])
else:
params[decl.name] = decl.comment
func["params"] = params
def print_info(self, func, skipped=False):
print ""
print
if skipped:
print "SKIPPED DEFINITION:"
print "name: %s" % (func.get("name","~empty~"))
print "file: %s (line %s)" % (func.get("file","~empty~"), func.get("line","~empty~"))
print "is class: %s" % func.get("isclass",False)
print "is struct: %s" % func.get("isstruct",False)
print "module: %s" % func.get("module","~unknown~")
print "namespace: %s" % func.get("namespace", "~empty~")
print "class: %s" % (func.get("class","~empty~"))
print "method: %s" % (func.get("method","~empty~"))
print "brief: %s" % (func.get("brief","~empty~"))
if "decls" in func:
print "declarations:"
for d in func["decls"]:
print " %7s: %s" % (d[0], re.sub(r"[ \t]+", " ", d[1]))
print " %7s: %s" % (d[0], re.sub(r"[ ]+", " ", d[1]))
if "params" in func:
print "parameters:"
for name, comment in func["params"].items():
print "%23s: %s" % (name, comment)
if not skipped:
print "long: %s" % (func.get("long","~empty~"))
print
def validate(self, func):
if func.get("decls",None) is None:
if not func.get("isclass",False):
if not func.get("isclass",False) and not func.get("isstruct",False):
return False
if func["name"] in self.definitions:
print "Parser error: function/class/struct \"%s\" in %s line %s is already documented in %s line %s" \
print "RST parser error: \"%s\" from file: %s (line %s) is already documented in file: %s (line %s)" \
% (func["name"], func["file"], func["line"], self.definitions[func["name"]]["file"], self.definitions[func["name"]]["line"])
return False
#todo: validate parameter names
@ -306,8 +355,32 @@ class RstParser(object):
if cmt:
params[name] = cmt
func["params"] = params
# special case for old C functions - section name should omit "cv" prefix
if not func.get("isclass",False) and not func.get("isstruct",False):
self.fixOldCFunctionName(func)
return func
def fixOldCFunctionName(self, func):
if not "decls" in func:
return
fname = None
for decl in func["decls"]:
if decl[0] != "C" and decl[0] != "Python1":
return
if decl[0] == "C":
fname = decl[2][0]
if fname is None:
return
fname = fname.replace(".", "::")
if fname == "cv::cv" + func.get("name", ""):
func["name"] = fname[2:]
func["method"] = fname[2:]
else:
print "RST parser warning: invalid definition of old C function \"%s\" - section name is \"%s\" instead of \"%s\". File: %s (line %s)" % (fname, func["name"], fname[6:], func["file"], func["line"])
# self.print_info(func)
def normalizeText(self, s):
if s is None:
return s
@ -316,7 +389,7 @@ class RstParser(object):
# remove tailing ::
s = re.sub(r"::$", "\n", s)
# remove extra line breaks before/after _ or ,
s = re.sub(r"\n[ \t]*([_,])\n", r"\1", s)
s = re.sub(r"\n[ ]*([_,])\n", r"\1", s)
# remove extra line breaks after `
#s = re.sub(r"`\n", "` ", s)
# remove extra line breaks before *
@ -326,17 +399,17 @@ class RstParser(object):
# remove extra line breaks after #.
s = re.sub(r"\n#\.\n", "\n#. ", s)
# remove extra line breaks before `
s = re.sub(r"\n[ \t]*`", " `", s)
s = re.sub(r"\n[ ]*`", " `", s)
# remove trailing whitespaces
s = re.sub(r"[ \t]+$", "", s)
s = re.sub(r"[ ]+$", "", s)
# remove whitespace before .
s = re.sub(r"[ \t]+\.", "\.", s)
s = re.sub(r"[ ]+\.", "\.", s)
# remove .. for references
s = re.sub(r"\.\. \[", "[", s)
# unescape
s = re.sub(r"\\(.)", "\\1", s)
# compress whitespace
s = re.sub(r"[ \t]+", " ", s)
s = re.sub(r"[ ]+", " ", s)
s = s.replace("**", "")
s = s.replace("``", "\"")
@ -363,10 +436,43 @@ if __name__ == "__main__":
module = sys.argv[1]
if not os.path.isdir(os.path.join(rst_parser_dir, "../" + module)):
if module != "all" and not os.path.isdir(os.path.join(rst_parser_dir, "../" + module)):
print "Module \"" + module + "\" could not be found."
exit(1)
parser = RstParser(hdr_parser.CppHeaderParser())
parser.parse(os.path.join(rst_parser_dir, "../" + module))
if module == "all":
for m in ["androidcamera", "calib3d", "contrib", "core", "features2d", "flann", "gpu", "haartraining", "highgui", "imgproc", "java", "legacy", "ml", "objdetect", "ocl", "python", "stitching", "traincascade", "ts", "video"]:
parser.parse(m, os.path.join(rst_parser_dir, "../" + m))
else:
parser.parse(module, os.path.join(rst_parser_dir, "../" + module))
# summary
print
print "RST Parser Summary:"
print " Total sections: %s" % parser.sections_total
print " Skipped sections: %s" % parser.sections_skipped
print " Parsed sections: %s" % parser.sections_parsed
print " Invalid sections: %s" % (parser.sections_total - parser.sections_parsed - parser.sections_skipped)
# statistic by language
stat = {}
classes = 0
structs = 0
for name, d in parser.definitions.items():
if d.get("isclass", False):
classes += 1
elif d.get("isstruct", False):
structs += 1
else:
for decl in d.get("decls",[]):
stat[decl[0]] = stat.get(decl[0],0) + 1
print
print " classes documented: %s" % classes
print " structs documented: %s" % structs
for lang in sorted(stat.items()):
print " %7s functions documented: %s" % lang

6
modules/video/doc/motion_analysis_and_object_tracking.rst
View File

@ -480,7 +480,7 @@ Updates the predicted state from the measurement.
BackgroundSubtractor
--------------------
.. ocv:class: BackgroundSubtractor
.. ocv:class:: BackgroundSubtractor
Base class for background/foreground segmentation. ::
@ -522,7 +522,7 @@ Computes a background image.
BackgroundSubtractorMOG
-----------------------
.. ocv:class: BackgroundSubtractorMOG : public BackgroundSubtractor
.. ocv:class:: BackgroundSubtractorMOG : public BackgroundSubtractor
Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm.
@ -567,7 +567,7 @@ BackgroundSubtractorMOG2
------------------------
Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm.
.. ocv:class: BackgroundSubtractorMOG2 : public BackgroundSubtractor
.. ocv:class:: BackgroundSubtractorMOG2 : public BackgroundSubtractor
Here are important members of the class that control the algorithm, which you can set after constructing the class instance: