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

Integration object detection using Latent SVM. Sample was added.

Browse Source
This commit is contained in:
Valentina Kustikova 2010-10-09 11:36:06 +00:00
parent a22f74c362
commit fbfccffbaa
24 changed files with 5986 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/objdetect/CMakeLists.txt
View File

@ -1 +1 @@
define_opencv_module(objdetect opencv_core opencv_imgproc)
define_opencv_module(objdetect opencv_core opencv_imgproc opencv_highgui)

123
modules/objdetect/include/opencv2/objdetect/objdetect.hpp
View File

@ -139,6 +139,129 @@ CVAPI(void) cvSetImagesForHaarClassifierCascade( CvHaarClassifierCascade* cascad
CVAPI(int) cvRunHaarClassifierCascade( const CvHaarClassifierCascade* cascade,
CvPoint pt, int start_stage CV_DEFAULT(0));
/****************************************************************************************\
* Latent SVM Object Detection functions *
\****************************************************************************************/
// DataType: STRUCT position
// Structure describes the position of the filter in the feature pyramid
// l - level in the feature pyramid
// (x, y) - coordinate in level l
typedef struct
{
unsigned int x;
unsigned int y;
unsigned int l;
} position;
// DataType: STRUCT filterObject
// Description of the filter, which corresponds to the part of the object
// V - ideal (penalty = 0) position of the partial filter
// from the root filter position (V_i in the paper)
// penaltyFunction - vector describes penalty function (d_i in the paper)
// pf[0] * x + pf[1] * y + pf[2] * x^2 + pf[3] * y^2
// FILTER DESCRIPTION
// Rectangular map (sizeX x sizeY),
// every cell stores feature vector (dimension = p)
// H - matrix of feature vectors
// to set and get feature vectors (i,j)
// used formula H[(j * sizeX + i) * p + k], where
// k - component of feature vector in cell (i, j)
// END OF FILTER DESCRIPTION
// xp - auxillary parameter for internal use
// size of row in feature vectors
// (yp = (int) (p / xp); p = xp * yp)
typedef struct{
position V;
float fineFunction[4];
unsigned int sizeX;
unsigned int sizeY;
unsigned int p;
unsigned int xp;
float *H;
} filterObject;
// data type: STRUCT CvLatentSvmDetector
// structure contains internal representation of trained Latent SVM detector
// num_filters - total number of filters (root plus part) in model
// num_components - number of components in model
// num_part_filters - array containing number of part filters for each component
// filters - root and part filters for all model components
// b - biases for all model components
// score_threshold - confidence level threshold
typedef struct CvLatentSvmDetector
{
int num_filters;
int num_components;
int* num_part_filters;
filterObject** filters;
float* b;
float score_threshold;
}
CvLatentSvmDetector;
// data type: STRUCT CvObjectDetection
// structure contains the bounding box and confidence level for detected object
// rect - bounding box for a detected object
// score - confidence level
typedef struct CvObjectDetection
{
CvRect rect;
float score;
} CvObjectDetection;
//////////////// Object Detection using Latent SVM //////////////
/*
// load trained detector from a file
//
// API
// CvLatentSvmDetector* cvLoadLatentSvmDetector(const char* filename);
// INPUT
// filename - path to the file containing the parameters of
- trained Latent SVM detector
// OUTPUT
// trained Latent SVM detector in internal representation
*/
CVAPI(CvLatentSvmDetector*) cvLoadLatentSvmDetector(const char* filename);
/*
// release memory allocated for CvLatentSvmDetector structure
//
// API
// void cvReleaseLatentSvmDetector(CvLatentSvmDetector** detector);
// INPUT
// detector - CvLatentSvmDetector structure to be released
// OUTPUT
*/
CVAPI(void) cvReleaseLatentSvmDetector(CvLatentSvmDetector** detector);
/*
// find rectangular regions in the given image that are likely
// to contain objects and corresponding confidence levels
//
// API
// CvSeq* cvLatentSvmDetectObjects(const IplImage* image,
// CvLatentSvmDetector* detector,
// CvMemStorage* storage,
// float overlap_threshold = 0.5f);
// INPUT
// image - image to detect objects in
// detector - Latent SVM detector in internal representation
// storage - memory storage to store the resultant sequence
// of the object candidate rectangles
// overlap_threshold - threshold for the non-maximum suppression algorithm
= 0.5f [here will be the reference to original paper]
// OUTPUT
// sequence of detected objects (bounding boxes and confidence levels stored in CvObjectDetection structures)
*/
CVAPI(CvSeq*) cvLatentSvmDetectObjects(IplImage* image,
CvLatentSvmDetector* detector,
CvMemStorage* storage,
float overlap_threshold CV_DEFAULT(0.5f));
#ifdef __cplusplus
}

140
modules/objdetect/src/_distancetransform.h Normal file
View File

@ -0,0 +1,140 @@
#ifndef DIST_TRANSFORM
#define DIST_TRANSFORM
#include "precomp.hpp"
#include "_types.h"
#include "_error.h"
/*
// Computation the point of intersection functions
// (parabolas on the variable y)
// a(y - q1) + b(q1 - y)(q1 - y) + f[q1]
// a(y - q2) + b(q2 - y)(q2 - y) + f[q2]
//
// API
// int GetPointOfIntersection(const F_type *f,
const F_type a, const F_type b,
int q1, int q2, F_type *point);
// INPUT
// f - function on the regular grid
// a - coefficient of the function
// b - coefficient of the function
// q1 - parameter of the function
// q2 - parameter of the function
// OUTPUT
// point - point of intersection
// RESULT
// Error status
*/
int GetPointOfIntersection(const float *f,
const float a, const float b,
int q1, int q2, float *point);
/*
// Decision of one dimensional problem generalized distance transform
// on the regular grid at all points
// min (a(y' - y) + b(y' - y)(y' - y) + f(y')) (on y')
//
// API
// int DistanceTransformOneDimensionalProblem(const F_type *f, const int n,
const F_type a, const F_type b,
F_type *distanceTransform,
int *points);
// INPUT
// f - function on the regular grid
// n - grid dimension
// a - coefficient of optimizable function
// b - coefficient of optimizable function
// OUTPUT
// distanceTransform - values of generalized distance transform
// points - arguments that corresponds to the optimal value of function
// RESULT
// Error status
*/
int DistanceTransformOneDimensionalProblem(const float *f, const int n,
const float a, const float b,
float *distanceTransform,
int *points);
/*
// Computation next cycle element
//
// API
// int GetNextCycleElement(int k, int n, int q);
// INPUT
// k - index of the previous cycle element
// n - number of matrix rows
// q - parameter that equal (number_of_rows * number_of_columns - 1)
// OUTPUT
// None
// RESULT
// Next cycle element
*/
int GetNextCycleElement(int k, int n, int q);
/*
// Transposition of cycle elements
//
// API
// void TransposeCycleElements(F_type *a, int *cycle, int cycle_len);
// INPUT
// a - initial matrix
// cycle - cycle
// cycle_len - cycle length
// OUTPUT
// a - matrix with transposed elements
// RESULT
// None
*/
void TransposeCycleElements(float *a, int *cycle, int cycle_len);
/*
// Getting transposed matrix
//
// API
// void Transpose(F_type *a, int n, int m);
// INPUT
// a - initial matrix
// n - number of rows
// m - number of columns
// OUTPUT
// a - transposed matrix
// RESULT
// Error status
*/
void Transpose(float *a, int n, int m);
/*
// Decision of two dimensional problem generalized distance transform
// on the regular grid at all points
// min{d2(y' - y) + d4(y' - y)(y' - y) +
min(d1(x' - x) + d3(x' - x)(x' - x) + f(x',y'))} (on x', y')
//
// API
// int DistanceTransformTwoDimensionalProblem(const F_type *f,
const int n, const int m,
const F_type coeff[4],
F_type *distanceTransform,
int *pointsX, int *pointsY);
// INPUT
// f - function on the regular grid
// n - number of rows
// m - number of columns
// coeff - coefficients of optimizable function
coeff[0] = d1, coeff[1] = d2,
coeff[2] = d3, coeff[3] = d4
// OUTPUT
// distanceTransform - values of generalized distance transform
// pointsX - arguments x' that correspond to the optimal value
// pointsY - arguments y' that correspond to the optimal value
// RESULT
// Error status
*/
int DistanceTransformTwoDimensionalProblem(const float *f,
const int n, const int m,
const float coeff[4],
float *distanceTransform,
int *pointsX, int *pointsY);
#endif

16
modules/objdetect/src/_error.h Normal file
View File

@ -0,0 +1,16 @@
#ifndef SVM_ERROR
#define SVM_ERROR
#define LATENT_SVM_OK 0
#define DISTANCE_TRANSFORM_OK 1
#define DISTANCE_TRANSFORM_GET_INTERSECTION_ERROR -1
#define DISTANCE_TRANSFORM_ERROR -2
#define DISTANCE_TRANSFORM_EQUAL_POINTS -3
#define LATENT_SVM_GET_FEATURE_PYRAMID_FAILED -4
#define LATENT_SVM_SEARCH_OBJECT_FAILED -5
#define LATENT_SVM_FAILED_SUPERPOSITION -6
#define FILTER_OUT_OF_BOUNDARIES -7
#define FFT_OK 2
#define FFT_ERROR -8
#endif

81
modules/objdetect/src/_fft.h Normal file
View File

@ -0,0 +1,81 @@
#ifndef _FFT_H
#define _FFT_H
#include "precomp.hpp"
#include "_types.h"
#include "_error.h"
#include <math.h>
/*
// 1-dimensional FFT
//
// API
// int fft(float *x_in, float *x_out, int n, int shift);
// INPUT
// x_in - input signal
// n - number of elements for searching Fourier image
// shift - shift between input elements
// OUTPUT
// x_out - output signal (contains 2n elements in order
Re(x_in[0]), Im(x_in[0]), Re(x_in[1]), Im(x_in[1]) and etc.)
// RESULT
// Error status
*/
int fft(float *x_in, float *x_out, int n, int shift);
/*
// Inverse 1-dimensional FFT
//
// API
// int fftInverse(float *x_in, float *x_out, int n, int shift);
// INPUT
// x_in - Fourier image of 1d input signal(contains 2n elements
in order Re(x_in[0]), Im(x_in[0]),
Re(x_in[1]), Im(x_in[1]) and etc.)
// n - number of elements for searching counter FFT image
// shift - shift between input elements
// OUTPUT
// x_in - input signal (contains n elements)
// RESULT
// Error status
*/
int fftInverse(float *x_in, float *x_out, int n, int shift);
/*
// 2-dimensional FFT
//
// API
// int fft2d(float *x_in, float *x_out, int numRows, int numColls);
// INPUT
// x_in - input signal (matrix, launched by rows)
// numRows - number of rows
// numColls - number of collumns
// OUTPUT
// x_out - output signal (contains (2 * numRows * numColls) elements
in order Re(x_in[0][0]), Im(x_in[0][0]),
Re(x_in[0][1]), Im(x_in[0][1]) and etc.)
// RESULT
// Error status
*/
int fft2d(float *x_in, float *x_out, int numRows, int numColls);
/*
// Inverse 2-dimensional FFT
//
// API
// int fftInverse2d(float *x_in, float *x_out, int numRows, int numColls);
// INPUT
// x_in - Fourier image of matrix (contains (2 * numRows * numColls)
elements in order Re(x_in[0][0]), Im(x_in[0][0]),
Re(x_in[0][1]), Im(x_in[0][1]) and etc.)
// numRows - number of rows
// numColls - number of collumns
// OUTPUT
// x_out - initial signal (matrix, launched by rows)
// RESULT
// Error status
*/
int fftInverse2d(float *x_in, float *x_out, int numRows, int numColls);
#endif

401
modules/objdetect/src/_latentsvm.h Normal file
View File

@ -0,0 +1,401 @@
/*****************************************************************************/
/* Latent SVM prediction API */
/*****************************************************************************/
#ifndef SVM_LATENTSVM
#define SVM_LATENTSVM
#include <stdio.h>
#include "precomp.hpp"
#include "_types.h"
#include "_error.h"
#include "_routine.h"
//////////////////////////////////////////////////////////////
// Building feature pyramid
// (pyramid constructed both contrast and non-contrast image)
//////////////////////////////////////////////////////////////
/*
// Getting feature pyramid
//
// API
// int getFeaturePyramid(IplImage * image, const filterObject **all_F,
const int n_f,
const int lambda, const int k,
const int startX, const int startY,
const int W, const int H, featurePyramid **maps);
// INPUT
// image - image
// lambda - resize scale
// k - size of cells
// startX - X coordinate of the image rectangle to search
// startY - Y coordinate of the image rectangle to search
// W - width of the image rectangle to search
// H - height of the image rectangle to search
// OUTPUT
// maps - feature maps for all levels
// RESULT
// Error status
*/
int getFeaturePyramid(IplImage * image,
const int lambda, const int k,
const int startX, const int startY,
const int W, const int H, featurePyramid **maps);
/*
// Getting feature map for the selected subimage
//
// API
// int getFeatureMaps(const IplImage * image, const int k, featureMap **map);
// INPUT
// image - selected subimage
// k - size of cells
// OUTPUT
// map - feature map
// RESULT
// Error status
*/
int getFeatureMaps_dp(const IplImage * image, const int k, featureMap **map);
/*
// Feature map Normalization and Truncation
//
// API
// int normalizationAndTruncationFeatureMaps(featureMap *map, const float alfa);
// INPUT
// map - feature map
// alfa - truncation threshold
// OUTPUT
// map - truncated and normalized feature map
// RESULT
// Error status
*/
int normalizationAndTruncationFeatureMaps(featureMap *map, const float alfa);
/*
// Feature map reduction
// In each cell we reduce dimension of the feature vector
// according to original paper special procedure
//
// API
// int PCAFeatureMaps(featureMap *map)
// INPUT
// map - feature map
// OUTPUT
// map - feature map
// RESULT
// Error status
*/
int PCAFeatureMaps(featureMap *map);
//////////////////////////////////////////////////////////////
// search object
//////////////////////////////////////////////////////////////
/*
// Transformation filter displacement from the block space
// to the space of pixels at the initial image
//
// API
// int convertPoints(int countLevel, int lambda,
int initialImageLevel,
CvPoint *points, int *levels,
CvPoint **partsDisplacement, int kPoints, int n,
int maxXBorder,
int maxYBorder);
// INPUT
// countLevel - the number of levels in the feature pyramid
// lambda - method parameter
// initialImageLevel - level of feature pyramid that contains feature map
for initial image
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// partsDisplacement - displacement of part filters (in the block space)
// kPoints - number of root filter positions
// n - number of part filters
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// points - the set of root filter positions (in the space of pixels)
// partsDisplacement - displacement of part filters (in the space of pixels)
// RESULT
// Error status
*/
int convertPoints(int countLevel, int lambda,
int initialImageLevel,
CvPoint *points, int *levels,
CvPoint **partsDisplacement, int kPoints, int n,
int maxXBorder,
int maxYBorder);
/*
// Elimination boxes that are outside the image boudaries
//
// API
// int clippingBoxes(int width, int height,
CvPoint *points, int kPoints);
// INPUT
// width - image wediht
// height - image heigth
// points - a set of points (coordinates of top left or
bottom right corners)
// kPoints - points number
// OUTPUT
// points - updated points (if coordinates less than zero then
set zero coordinate, if coordinates more than image
size then set coordinates equal image size)
// RESULT
// Error status
*/
#ifdef __cplusplus
extern "C"
#endif
int clippingBoxes(int width, int height,
CvPoint *points, int kPoints);
/*
// Creation feature pyramid with nullable border
//
// API
// featurePyramid* createFeaturePyramidWithBorder(const IplImage *image,
int maxXBorder, int maxYBorder);
// INPUT
// image - initial image
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// RESULT
// Feature pyramid with nullable border
*/
#ifdef __cplusplus
extern "C"
#endif
featurePyramid* createFeaturePyramidWithBorder(IplImage *image,
int maxXBorder, int maxYBorder);
/*
// Computation of the root filter displacement and values of score function
//
// API
// int searchObject(const featurePyramid *H, const filterObject **all_F, int n,
float b,
int maxXBorder,
int maxYBorder,
CvPoint **points, int **levels, int *kPoints, float *score,
CvPoint ***partsDisplacement);
// INPUT
// H - feature pyramid
// all_F - the set of filters (the first element is root filter,
other elements - part filters)
// n - the number of part filters
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// points - positions (x, y) of the upper-left corner
of root filter frame
// levels - levels that correspond to each position
// kPoints - number of positions
// score - value of the score function
// partsDisplacement - part filters displacement for each position
of the root filter
// RESULT
// Error status
*/
int searchObject(const featurePyramid *H, const filterObject **all_F, int n,
float b,
int maxXBorder,
int maxYBorder,
CvPoint **points, int **levels, int *kPoints, float *score,
CvPoint ***partsDisplacement);
/*
// Computation of the root filter displacement and values of score function
//
// API
// int searchObjectThreshold(const featurePyramid *H,
const filterObject **all_F, int n,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
CvPoint **points, int **levels, int *kPoints,
float **score, CvPoint ***partsDisplacement);
// INPUT
// H - feature pyramid
// all_F - the set of filters (the first element is root filter,
other elements - part filters)
// n - the number of part filters
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// scoreThreshold - score threshold
// OUTPUT
// points - positions (x, y) of the upper-left corner
of root filter frame
// levels - levels that correspond to each position
// kPoints - number of positions
// score - values of the score function
// partsDisplacement - part filters displacement for each position
of the root filter
// RESULT
// Error status
*/
int searchObjectThreshold(const featurePyramid *H,
const filterObject **all_F, int n,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
CvPoint **points, int **levels, int *kPoints,
float **score, CvPoint ***partsDisplacement);
/*
// Computation root filters displacement and values of score function
//
// API
// int searchObjectThresholdSomeComponents(const featurePyramid *H,
const filterObject **filters,
int kComponents, const int *kPartFilters,
const float *b, float scoreThreshold,
CvPoint **points, CvPoint **oppPoints,
float **score, int *kPoints);
// INPUT
// H - feature pyramid
// filters - filters (root filter then it's part filters, etc.)
// kComponents - root filters number
// kPartFilters - array of part filters number for each component
// b - array of linear terms
// scoreThreshold - score threshold
// OUTPUT
// points - root filters displacement (top left corners)
// oppPoints - root filters displacement (bottom right corners)
// score - array of score values
// kPoints - number of boxes
// RESULT
// Error status
*/
#ifdef __cplusplus
extern "C"
#endif
int searchObjectThresholdSomeComponents(const featurePyramid *H,
const filterObject **filters,
int kComponents, const int *kPartFilters,
const float *b, float scoreThreshold,
CvPoint **points, CvPoint **oppPoints,
float **score, int *kPoints);
/*
// Compute opposite point for filter box
//
// API
// int getOppositePoint(CvPoint point,
int sizeX, int sizeY,
float step, int degree,
CvPoint *oppositePoint);
// INPUT
// point - coordinates of filter top left corner
(in the space of pixels)
// (sizeX, sizeY) - filter dimension in the block space
// step - scaling factor
// degree - degree of the scaling factor
// OUTPUT
// oppositePoint - coordinates of filter bottom corner
(in the space of pixels)
// RESULT
// Error status
*/
int getOppositePoint(CvPoint point,
int sizeX, int sizeY,
float step, int degree,
CvPoint *oppositePoint);
/*
// Drawing root filter boxes
//
// API
// int showRootFilterBoxes(const IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
// INPUT
// image - initial image
// filter - root filter object
// points - a set of points
// levels - levels of feature pyramid
// kPoints - number of points
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// window contained initial image and filter boxes
// RESULT
// Error status
*/
int showRootFilterBoxes(IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
/*
// Drawing part filter boxes
//
// API
// int showPartFilterBoxes(const IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
// INPUT
// image - initial image
// filters - a set of part filters
// n - number of part filters
// partsDisplacement - a set of points
// levels - levels of feature pyramid
// kPoints - number of foot filter positions
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// window contained initial image and filter boxes
// RESULT
// Error status
*/
int showPartFilterBoxes(IplImage *image,
const filterObject **filters,
int n, CvPoint **partsDisplacement,
int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
/*
// Drawing boxes
//
// API
// int showBoxes(const IplImage *img,
const CvPoint *points, const CvPoint *oppositePoints, int kPoints,
CvScalar color, int thickness, int line_type, int shift);
// INPUT
// img - initial image
// points - top left corner coordinates
// oppositePoints - right bottom corner coordinates
// kPoints - points number
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// RESULT
// Error status
*/
int showBoxes(IplImage *img,
const CvPoint *points, const CvPoint *oppositePoints, int kPoints,
CvScalar color, int thickness, int line_type, int shift);
#endif

66
modules/objdetect/src/_lsvmparser.h Normal file
View File

@ -0,0 +1,66 @@
#ifndef LSVM_PARSER
#define LSVM_PARSER
#include "precomp.hpp"
#include "_types.h"
#define MODEL 1
#define P 2
#define COMP 3
#define SCORE 4
#define RFILTER 100
#define PFILTERs 101
#define PFILTER 200
#define SIZEX 150
#define SIZEY 151
#define WEIGHTS 152
#define TAGV 300
#define Vx 350
#define Vy 351
#define TAGD 400
#define Dx 451
#define Dy 452
#define Dxx 453
#define Dyy 454
#define BTAG 500
#define STEP_END 1000
#define EMODEL (STEP_END + MODEL)
#define EP (STEP_END + P)
#define ECOMP (STEP_END + COMP)
#define ESCORE (STEP_END + SCORE)
#define ERFILTER (STEP_END + RFILTER)
#define EPFILTERs (STEP_END + PFILTERs)
#define EPFILTER (STEP_END + PFILTER)
#define ESIZEX (STEP_END + SIZEX)
#define ESIZEY (STEP_END + SIZEY)
#define EWEIGHTS (STEP_END + WEIGHTS)
#define ETAGV (STEP_END + TAGV)
#define EVx (STEP_END + Vx)
#define EVy (STEP_END + Vy)
#define ETAGD (STEP_END + TAGD)
#define EDx (STEP_END + Dx)
#define EDy (STEP_END + Dy)
#define EDxx (STEP_END + Dxx)
#define EDyy (STEP_END + Dyy)
#define EBTAG (STEP_END + BTAG)
//extern "C" {
void LSVMparser(const char * filename, filterObject *** model, int *last, int *max, int **comp, float **b, int *count, float * score);
#ifdef __cplusplus
extern "C"
#endif
int loadModel(
// Âõîäíûå ïàðàìåòðû
const char *modelPath,// - ïóòü äî ôàéëà ñ ìîäåëüþ
// Âûõîäíûå ïàðàìåòðû
filterObject ***filters,// - ìàññèâ óêàçàòåëåé íà ôèëüòðû êîìïîíåíò
int *kFilters, //- îáùåå êîëè÷åñòâî ôèëüòðîâ âî âñåõ ìîäåëÿõ
int *kComponents, //- êîëè÷åñòâî êîìïîíåíò
int **kPartFilters, //- ìàññèâ, ñîäåðæàùèé êîëè÷åñòâî òî÷íûõ ôèëüòðîâ â êàæäîé êîìïîíåíòå
float **b, //- ìàññèâ ëèíåéíûõ ÷ëåíîâ â îöåíî÷íîé ôóíêöèè
float *scoreThreshold); //- ïîðîã äëÿ score)
//};
#endif

396
modules/objdetect/src/_matching.h Normal file
View File

@ -0,0 +1,396 @@
/*****************************************************************************/
/* Matching procedure API */
/*****************************************************************************/
//
#ifndef SVM_MATCHING
#define SVM_MATCHING
#include "_latentsvm.h"
#include "_error.h"
#include "_distancetransform.h"
#include "_fft.h"
#include "_routine.h"
//extern "C" {
/*
// Function for convolution computation
//
// API
// int convolution(const filterObject *Fi, const featureMap *map, float *f);
// INPUT
// Fi - filter object
// map - feature map
// OUTPUT
// f - the convolution
// RESULT
// Error status
*/
int convolution(const filterObject *Fi, const featureMap *map, float *f);
/*
// Computation multiplication of FFT images
//
// API
// int fftImagesMulti(float *fftImage1, float *fftImage2, int numRows, int numColls,
float *multi);
// INPUT
// fftImage1 - first fft image
// fftImage2 - second fft image
// (numRows, numColls) - image dimesions
// OUTPUT
// multi - multiplication
// RESULT
// Error status
*/
int fftImagesMulti(float *fftImage1, float *fftImage2, int numRows, int numColls,
float *multi);
/*
// Turnover filter matrix for the single feature
//
// API
// int rot2PI(float *filter, int dimX, int dimY, float *rot2PIFilter,
int p, int shift);
// INPUT
// filter - filter weight matrix
// (dimX, dimY) - dimension of filter matrix
// p - number of features
// shift - number of feature (or channel)
// OUTPUT
// rot2PIFilter - rotated matrix
// RESULT
// Error status
*/
int rot2PI(float *filter, int dimX, int dimY, float *rot2PIFilter,
int p, int shift);
/*
// Addition nullable bars to the dimension of feature map (single feature)
//
// API
// int addNullableBars(float *rot2PIFilter, int dimX, int dimY,
float *newFilter, int newDimX, int newDimY);
// INPUT
// rot2PIFilter - filter matrix for the single feature that was rotated
// (dimX, dimY) - dimension rot2PIFilter
// (newDimX, newDimY)- dimension of feature map for the single feature
// OUTPUT
// newFilter - filter matrix with nullable bars
// RESULT
// Error status
*/
int addNullableBars(float *rot2PIFilter, int dimX, int dimY,
float *newFilter, int newDimX, int newDimY);
/*
// Computation FFT image for filter object
//
// API
// int getFFTImageFilterObject(const filterObject *filter,
int mapDimX, int mapDimY,
fftImage **image);
// INPUT
// filter - filter object
// (mapDimX, mapDimY)- dimension of feature map
// OUTPUT
// image - fft image
// RESULT
// Error status
*/
int getFFTImageFilterObject(const filterObject *filter,
int mapDimX, int mapDimY,
fftImage **image);
/*
// Computation FFT image for feature map
//
// API
// int getFFTImageFeatureMap(const featureMap *map, fftImage **image);
// INPUT
// OUTPUT
// RESULT
// Error status
*/
int getFFTImageFeatureMap(const featureMap *map, fftImage **image);
/*
// Function for convolution computation using FFT
//
// API
// int convFFTConv2d(const fftImage *featMapImage, const fftImage *filterImage,
int filterDimX, int filterDimY, float **conv);
// INPUT
// featMapImage - feature map image
// filterImage - filter image
// (filterDimX,filterDimY) - filter dimension
// OUTPUT
// conv - the convolution
// RESULT
// Error status
*/
int convFFTConv2d(const fftImage *featMapImage, const fftImage *filterImage,
int filterDimX, int filterDimY, float **conv);
/*
// Computation objective function D according the original paper
//
// API
// int filterDispositionLevel(const filterObject *Fi, const featureMap *pyramid,
float **scoreFi,
int **pointsX, int **pointsY);
// INPUT
// Fi - filter object (weights and coefficients of penalty
function that are used in this routine)
// pyramid - feature map
// OUTPUT
// scoreFi - values of distance transform on the level at all positions
// (pointsX, pointsY)- positions that correspond to the maximum value
of distance transform at all grid nodes
// RESULT
// Error status
*/
int filterDispositionLevel(const filterObject *Fi, const featureMap *pyramid,
float **scoreFi,
int **pointsX, int **pointsY);
/*
// Computation objective function D according the original paper using FFT
//
// API
// int filterDispositionLevelFFT(const filterObject *Fi, const fftImage *featMapImage,
float **scoreFi,
int **pointsX, int **pointsY);
// INPUT
// Fi - filter object (weights and coefficients of penalty
function that are used in this routine)
// featMapImage - FFT image of feature map
// OUTPUT
// scoreFi - values of distance transform on the level at all positions
// (pointsX, pointsY)- positions that correspond to the maximum value
of distance transform at all grid nodes
// RESULT
// Error status
*/
int filterDispositionLevelFFT(const filterObject *Fi, const fftImage *featMapImage,
float **scoreFi,
int **pointsX, int **pointsY);
/*
// Computation border size for feature map
//
// API
// int computeBorderSize(int maxXBorder, int maxYBorder, int *bx, int *by);
// INPUT
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// bx - border size (X-direction)
// by - border size (Y-direction)
// RESULT
// Error status
*/
int computeBorderSize(int maxXBorder, int maxYBorder, int *bx, int *by);
/*
// Addition nullable border to the feature map
//
// API
// int addNullableBorder(featureMap *map, int bx, int by);
// INPUT
// map - feature map
// bx - border size (X-direction)
// by - border size (Y-direction)
// OUTPUT
// RESULT
// Error status
*/
int addNullableBorder(featureMap *map, int bx, int by);
/*
// Computation the maximum of the score function at the level
//
// API
// int maxFunctionalScoreFixedLevel(const filterObject **all_F, int n,
const featurePyramid *H,
int level, float b,
int maxXBorder, int maxYBorder,
float *score, CvPoint **points, int *kPoints,
CvPoint ***partsDisplacement);
// INPUT
// all_F - the set of filters (the first element is root filter,
the other - part filters)
// n - the number of part filters
// H - feature pyramid
// level - feature pyramid level for computation maximum score
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// score - the maximum of the score function at the level
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// kPoints - number of root filter positions
// partsDisplacement - displacement of part filters (in the block space)
// RESULT
// Error status
*/
int maxFunctionalScoreFixedLevel(const filterObject **all_F, int n,
const featurePyramid *H,
int level, float b,
int maxXBorder, int maxYBorder,
float *score, CvPoint **points, int *kPoints,
CvPoint ***partsDisplacement);
/*
// Computation score function at the level that exceed threshold
//
// API
// int thresholdFunctionalScoreFixedLevel(const filterObject **all_F, int n,
const featurePyramid *H,
int level, float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
float **score, CvPoint **points, int *kPoints,
CvPoint ***partsDisplacement);
// INPUT
// all_F - the set of filters (the first element is root filter,
the other - part filters)
// n - the number of part filters
// H - feature pyramid
// level - feature pyramid level for computation maximum score
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// scoreThreshold - score threshold
// OUTPUT
// score - score function at the level that exceed threshold
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// kPoints - number of root filter positions
// partsDisplacement - displacement of part filters (in the block space)
// RESULT
// Error status
*/
int thresholdFunctionalScoreFixedLevel(const filterObject **all_F, int n,
const featurePyramid *H,
int level, float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
float **score, CvPoint **points, int *kPoints,
CvPoint ***partsDisplacement);
/*
// Computation the maximum of the score function
//
// API
// int maxFunctionalScore(const filterObject **all_F, int n,
const featurePyramid *H, float b,
int maxXBorder, int maxYBorder,
float *score,
CvPoint **points, int **levels, int *kPoints,
CvPoint ***partsDisplacement);
// INPUT
// all_F - the set of filters (the first element is root filter,
the other - part filters)
// n - the number of part filters
// H - feature pyramid
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// score - the maximum of the score function
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// kPoints - number of root filter positions
// partsDisplacement - displacement of part filters (in the block space)
// RESULT
// Error status
*/
int maxFunctionalScore(const filterObject **all_F, int n,
const featurePyramid *H, float b,
int maxXBorder, int maxYBorder,
float *score,
CvPoint **points, int **levels, int *kPoints,
CvPoint ***partsDisplacement);
/*
// Computation score function that exceed threshold
//
// API
// int thresholdFunctionalScore(const filterObject **all_F, int n,
const featurePyramid *H,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
float **score,
CvPoint **points, int **levels, int *kPoints,
CvPoint ***partsDisplacement);
// INPUT
// all_F - the set of filters (the first element is root filter,
the other - part filters)
// n - the number of part filters
// H - feature pyramid
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// scoreThreshold - score threshold
// OUTPUT
// score - score function values that exceed threshold
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// kPoints - number of root filter positions
// partsDisplacement - displacement of part filters (in the block space)
// RESULT
// Error status
*/
int thresholdFunctionalScore(const filterObject **all_F, int n,
const featurePyramid *H,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
float **score,
CvPoint **points, int **levels, int *kPoints,
CvPoint ***partsDisplacement);
/*
// Perform non-maximum suppression algorithm (described in original paper)
// to remove "similar" bounding boxes
//
// API
// int nonMaximumSuppression(int numBoxes, const CvPoint *points,
const CvPoint *oppositePoints, const float *score,
float overlapThreshold,
int *numBoxesout, CvPoint **pointsOut,
CvPoint **oppositePointsOut, float **scoreOut);
// INPUT
// numBoxes - number of bounding boxes
// points - array of left top corner coordinates
// oppositePoints - array of right bottom corner coordinates
// score - array of detection scores
// overlapThreshold - threshold: bounding box is removed if overlap part
is greater than passed value
// OUTPUT
// numBoxesOut - the number of bounding boxes algorithm returns
// pointsOut - array of left top corner coordinates
// oppositePointsOut - array of right bottom corner coordinates
// scoreOut - array of detection scores
// RESULT
// Error status
*/
#ifdef __cplusplus
extern "C"
#endif
int nonMaximumSuppression(int numBoxes, const CvPoint *points,
const CvPoint *oppositePoints, const float *score,
float overlapThreshold,
int *numBoxesOut, CvPoint **pointsOut,
CvPoint **oppositePointsOut, float **scoreOut);
#ifdef __cplusplus
extern "C"
#endif
int getMaxFilterDims(const filterObject **filters, int kComponents,
const int *kPartFilters,
unsigned int *maxXBorder, unsigned int *maxYBorder);
//}
#endif

11
modules/objdetect/src/_resizeimg.h Normal file
View File

@ -0,0 +1,11 @@
#ifndef RESIZEIMG
#define RESIZEIMG
#include "precomp.hpp"
#include "_types.h"
IplImage * resize_opencv (IplImage * img, float scale);
IplImage * resize_article_dp1(IplImage * img, float scale, const int k);
IplImage * resize_article_dp(IplImage * img, float scale, const int k);
#endif

36
modules/objdetect/src/_routine.h Normal file
View File

@ -0,0 +1,36 @@
#ifndef _ROUTINE_H
#define _ROUTINE_H
#include "precomp.hpp"
#include "_types.h"
#include "_error.h"
//////////////////////////////////////////////////////////////
// Memory management routines
// All paramaters names correspond to previous data structures description
// All "alloc" functions return allocated memory for 1 object
// with all fields including arrays
// Error status is return value
//////////////////////////////////////////////////////////////
int allocFilterObject(filterObject **obj, const int sizeX, const int sizeY,
const int p, const int xp);
int freeFilterObject (filterObject **obj);
int allocFeatureMapObject(featureMap **obj, const int sizeX, const int sizeY,
const int p, const int xp);
int freeFeatureMapObject (featureMap **obj);
#ifdef __cplusplus
extern "C"
#endif
int allocFeaturePyramidObject(featurePyramid **obj,
const int lambda, const int countLevel);
#ifdef __cplusplus
extern "C"
#endif
int freeFeaturePyramidObject (featurePyramid **obj);
int allocFFTImage(fftImage **image, int p, int dimX, int dimY);
int freeFFTImage(fftImage **image);
#endif

93
modules/objdetect/src/_types.h Normal file
View File

@ -0,0 +1,93 @@
#ifndef SVM_TYPE
#define SVM_TYPE
//#include "opencv2/core/core.hpp"
//#include "opencv2/highgui/highgui.hpp"
#include "precomp.hpp"
//#define FFT_CONV
// Çíà÷åíèå ÷èñëà PI
#define PI 3.1415926535897932384626433832795
// Òî÷íîñòü ñðàâíåíèÿ ïàðû âåùåñòâåííûõ ÷èñåë
#define EPS 0.000001
// Ìèíèìàëüíîå è ìàêñèìàëüíîå çíà÷åíèå äëÿ âåùåñòâåííîãî òèïà äàííûõ
#define F_MAX 3.402823466e+38
#define F_MIN -3.402823465e+38
// The number of elements in bin
// The number of sectors in gradient histogram building
#define CNTPARTION 9
// The number of levels in image resize procedure
// We need Lambda levels to resize image twice
#define LAMBDA 10
// Block size. Used in feature pyramid building procedure
#define SIDE_LENGTH 8
//////////////////////////////////////////////////////////////
// main data structures //
//////////////////////////////////////////////////////////////
// DataType: STRUCT featureMap
// FEATURE MAP DESCRIPTION
// Rectangular map (sizeX x sizeY),
// every cell stores feature vector (dimension = p)
// H - matrix of feature vectors
// to set and get feature vectors (i,j)
// used formula Map[(j * sizeX + i) * p + k], where
// k - component of feature vector in cell (i, j)
// END OF FEATURE MAP DESCRIPTION
// xp - auxillary parameter for internal use
// size of row in feature vectors
// (yp = (int) (p / xp); p = xp * yp)
typedef struct{
int sizeX;
int sizeY;
int p;
int xp;
float *Map;
} featureMap;
// DataType: STRUCT featurePyramid
//
// countLevel - number of levels in the feature pyramid
// lambda - resize scale coefficient
// pyramid - array of pointers to feature map at different levels
typedef struct{
int countLevel;
int lambda;
featureMap **pyramid;
} featurePyramid;
// DataType: STRUCT filterDisposition
// The structure stores preliminary results in optimization process
// with objective function D
//
// x - array with X coordinates of optimization problems solutions
// y - array with Y coordinates of optimization problems solutions
// score - array with optimal objective values
typedef struct{
float *score;
int *x;
int *y;
} filterDisposition;
// DataType: STRUCT fftImage
// The structure stores FFT image
//
// p - number of channels
// x - array of FFT images for 2d signals
// n - number of rows
// m - number of collums
typedef struct{
unsigned int p;
unsigned int dimX;
unsigned int dimY;
float **channels;
} fftImage;
#endif

395
modules/objdetect/src/distancetransform.cpp Normal file
View File

@ -0,0 +1,395 @@
#include "_distancetransform.h"
/*
// Computation the point of intersection functions
// (parabolas on the variable y)
// a(y - q1) + b(q1 - y)(q1 - y) + f[q1]
// a(y - q2) + b(q2 - y)(q2 - y) + f[q2]
//
// API
// int GetPointOfIntersection(const float *f,
const float a, const float b,
int q1, int q2, float *point);
// INPUT
// f - function on the regular grid
// a - coefficient of the function
// b - coefficient of the function
// q1 - parameter of the function
// q2 - parameter of the function
// OUTPUT
// point - point of intersection
// RESULT
// Error status
*/
int GetPointOfIntersection(const float *f,
const float a, const float b,
int q1, int q2, float *point)
{
if (q1 == q2)
{
return DISTANCE_TRANSFORM_EQUAL_POINTS;
} /* if (q1 == q2) */
(*point) = ( (f[q2] - a * q2 + b *q2 * q2) -
(f[q1] - a * q1 + b * q1 * q1) ) / (2 * b * (q2 - q1));
return DISTANCE_TRANSFORM_OK;
}
/*
// Decision of one dimensional problem generalized distance transform
// on the regular grid at all points
// min (a(y' - y) + b(y' - y)(y' - y) + f(y')) (on y')
//
// API
// int DistanceTransformOneDimensionalProblem(const float *f, const int n,
const float a, const float b,
float *distanceTransform,
int *points);
// INPUT
// f - function on the regular grid
// n - grid dimension
// a - coefficient of optimizable function
// b - coefficient of optimizable function
// OUTPUT
// distanceTransform - values of generalized distance transform
// points - arguments that corresponds to the optimal value of function
// RESULT
// Error status
*/
int DistanceTransformOneDimensionalProblem(const float *f, const int n,
const float a, const float b,
float *distanceTransform,
int *points)
{
int i, k;
int tmp;
int diff;
float pointIntersection;
int *v;
float *z;
k = 0;
// Allocation memory (must be free in this function)
v = (int *)malloc (sizeof(int) * n);
z = (float *)malloc (sizeof(float) * (n + 1));
v[0] = 0;
z[0] = (float)F_MIN; // left border of envelope
z[1] = (float)F_MAX; // right border of envelope
for (i = 1; i < n; i++)
{
tmp = GetPointOfIntersection(f, a, b, v[k], i, &pointIntersection);
if (tmp != DISTANCE_TRANSFORM_OK)
{
free(v);
free(z);
return DISTANCE_TRANSFORM_GET_INTERSECTION_ERROR;
} /* if (tmp != DISTANCE_TRANSFORM_OK) */
if (pointIntersection <= z[k])
{
// Envelope doesn't contain current parabola
do
{
k--;
tmp = GetPointOfIntersection(f, a, b, v[k], i, &pointIntersection);
if (tmp != DISTANCE_TRANSFORM_OK)
{
free(v);
free(z);
return DISTANCE_TRANSFORM_GET_INTERSECTION_ERROR;
} /* if (tmp != DISTANCE_TRANSFORM_OK) */
}while (pointIntersection <= z[k]);
// Addition parabola to the envelope
k++;
v[k] = i;
z[k] = pointIntersection;
z[k + 1] = (float)F_MAX;
}
else
{
// Addition parabola to the envelope
k++;
v[k] = i;
z[k] = pointIntersection;
z[k + 1] = (float)F_MAX;
} /* if (pointIntersection <= z[k]) */
}
// Computation values of generalized distance transform at all grid points
k = 0;
for (i = 0; i < n; i++)
{
while (z[k + 1] < i)
{
k++;
}
points[i] = v[k];
diff = i - v[k];
distanceTransform[i] = a * diff + b * diff * diff + f[v[k]];
}
// Release allocated memory
free(v);
free(z);
return DISTANCE_TRANSFORM_OK;
}
/*
// Computation next cycle element
//
// API
// int GetNextCycleElement(int k, int n, int q);
// INPUT
// k - index of the previous cycle element
// n - number of matrix rows
// q - parameter that equal
(number_of_rows * number_of_columns - 1)
// OUTPUT
// None
// RESULT
// Next cycle element
*/
int GetNextCycleElement(int k, int n, int q)
{
return ((k * n) % q);
}
/*
// Transpose cycle elements
//
// API
// void TransposeCycleElements(float *a, int *cycle, int cycle_len)
// INPUT
// a - initial matrix
// cycle - indeces array of cycle
// cycle_len - number of elements in the cycle
// OUTPUT
// a - matrix with transposed elements
// RESULT
// Error status
*/
void TransposeCycleElements(float *a, int *cycle, int cycle_len)
{
int i;
float buf;
for (i = cycle_len - 1; i > 0 ; i--)
{
buf = a[ cycle[i] ];
a[ cycle[i] ] = a[ cycle[i - 1] ];
a[ cycle[i - 1] ] = buf;
}
}
/*
// Transpose cycle elements
//
// API
// void TransposeCycleElements(int *a, int *cycle, int cycle_len)
// INPUT
// a - initial matrix
// cycle - indeces array of cycle
// cycle_len - number of elements in the cycle
// OUTPUT
// a - matrix with transposed elements
// RESULT
// Error status
*/
void TransposeCycleElements_int(int *a, int *cycle, int cycle_len)
{
int i;
int buf;
for (i = cycle_len - 1; i > 0 ; i--)
{
buf = a[ cycle[i] ];
a[ cycle[i] ] = a[ cycle[i - 1] ];
a[ cycle[i - 1] ] = buf;
}
}
/*
// Getting transposed matrix
//
// API
// void Transpose(float *a, int n, int m);
// INPUT
// a - initial matrix
// n - number of rows
// m - number of columns
// OUTPUT
// a - transposed matrix
// RESULT
// None
*/
void Transpose(float *a, int n, int m)
{
int *cycle;
int i, k, q, cycle_len;
int max_cycle_len;
max_cycle_len = n * m;
// Allocation memory (must be free in this function)
cycle = (int *)malloc(sizeof(int) * max_cycle_len);
cycle_len = 0;
q = n * m - 1;
for (i = 1; i < q; i++)
{
k = GetNextCycleElement(i, n, q);
cycle[cycle_len] = i;
cycle_len++;
while (k > i)
{
cycle[cycle_len] = k;
cycle_len++;
k = GetNextCycleElement(k, n, q);
}
if (k == i)
{
TransposeCycleElements(a, cycle, cycle_len);
} /* if (k == i) */
cycle_len = 0;
}
// Release allocated memory
free(cycle);
}
/*
// Getting transposed matrix
//
// API
// void Transpose_int(int *a, int n, int m);
// INPUT
// a - initial matrix
// n - number of rows
// m - number of columns
// OUTPUT
// a - transposed matrix
// RESULT
// None
*/
void Transpose_int(int *a, int n, int m)
{
int *cycle;
int i, k, q, cycle_len;
int max_cycle_len;
max_cycle_len = n * m;
// Allocation memory (must be free in this function)
cycle = (int *)malloc(sizeof(int) * max_cycle_len);
cycle_len = 0;
q = n * m - 1;
for (i = 1; i < q; i++)
{
k = GetNextCycleElement(i, n, q);
cycle[cycle_len] = i;
cycle_len++;
while (k > i)
{
cycle[cycle_len] = k;
cycle_len++;
k = GetNextCycleElement(k, n, q);
}
if (k == i)
{
TransposeCycleElements_int(a, cycle, cycle_len);
} /* if (k == i) */
cycle_len = 0;
}
// Release allocated memory
free(cycle);
}
/*
// Decision of two dimensional problem generalized distance transform
// on the regular grid at all points
// min{d2(y' - y) + d4(y' - y)(y' - y) +
min(d1(x' - x) + d3(x' - x)(x' - x) + f(x',y'))} (on x', y')
//
// API
// int DistanceTransformTwoDimensionalProblem(const float *f,
const int n, const int m,
const float coeff[4],
float *distanceTransform,
int *pointsX, int *pointsY);
// INPUT
// f - function on the regular grid
// n - number of rows
// m - number of columns
// coeff - coefficients of optimizable function
coeff[0] = d1, coeff[1] = d2,
coeff[2] = d3, coeff[3] = d4
// OUTPUT
// distanceTransform - values of generalized distance transform
// pointsX - arguments x' that correspond to the optimal value
// pointsY - arguments y' that correspond to the optimal value
// RESULT
// Error status
*/
int DistanceTransformTwoDimensionalProblem(const float *f,
const int n, const int m,
const float coeff[4],
float *distanceTransform,
int *pointsX, int *pointsY)
{
int i, j, tmp;
int resOneDimProblem;
float *internalDistTrans;
int *internalPointsX;
int size = n * m;
// Allocation memory (must be free in this function)
internalDistTrans = (float *)malloc(sizeof(float) * size);
internalPointsX = (int *)malloc(sizeof(int) * size);
for (i = 0; i < n; i++)
{
resOneDimProblem = DistanceTransformOneDimensionalProblem(
f + i * m, m,
coeff[0], coeff[2],
internalDistTrans + i * m,
internalPointsX + i * m);
if (resOneDimProblem != DISTANCE_TRANSFORM_OK)
{
free(internalDistTrans);
return DISTANCE_TRANSFORM_ERROR;
} /* if (resOneDimProblem != DISTANCE_TRANSFORM_OK) */
}
Transpose(internalDistTrans, n, m);
for (j = 0; j < m; j++)
{
resOneDimProblem = DistanceTransformOneDimensionalProblem(
internalDistTrans + j * n, n,
coeff[1], coeff[3],
distanceTransform + j * n,
pointsY + j * n);
if (resOneDimProblem != DISTANCE_TRANSFORM_OK)
{
free(internalDistTrans);
return DISTANCE_TRANSFORM_ERROR;
} /* if (resOneDimProblem != DISTANCE_TRANSFORM_OK) */
}
Transpose(distanceTransform, m, n);
Transpose_int(pointsY, m, n);
for (i = 0; i < n; i++)
{
for (j = 0; j < m; j++)
{
tmp = pointsY[i * m + j];
pointsX[i * m + j] = internalPointsX[tmp * m + j];
}
}
// Release allocated memory
free(internalDistTrans);
free(internalPointsX);
return DISTANCE_TRANSFORM_OK;
}

576
modules/objdetect/src/featurepyramid.cpp Normal file
View File

@ -0,0 +1,576 @@
#include "_latentsvm.h"
#include "_resizeimg.h"
#ifndef max
#define max(a,b) (((a) > (b)) ? (a) : (b))
#endif
#ifndef min
#define min(a,b) (((a) < (b)) ? (a) : (b))
#endif
int sign(float r){
if(r > 0.0001f) return 1;
if(r < -0.0001f) return -1;
return 0;
}
/*
// Getting feature map for the selected subimage
//
// API
// int getFeatureMaps(const IplImage * image, const int k, featureMap **map);
// INPUT
// image - selected subimage
// k - size of cells
// OUTPUT
// map - feature map
// RESULT
// Error status
*/
int getFeatureMaps_dp(const IplImage * image,const int k, featureMap **map)
{
int sizeX, sizeY;
int p, px, strsz;
int height, width, channels;
int i, j, kk, c, ii, jj, d;
float * datadx, * datady;
float tmp, x, y, tx, ty;
IplImage * dx, * dy;
int *nearest_x, *nearest_y;
float *w, a_x, b_x;
float kernel[3] = {-1.f, 0.f, 1.f};
CvMat kernel_dx = cvMat(1, 3, CV_32F, kernel);
CvMat kernel_dy = cvMat(3, 1, CV_32F, kernel);
float * r;
int * alfa;
float boundary_x[CNTPARTION+1];
float boundary_y[CNTPARTION+1];
float max, tmp_scal;
int maxi;
height = image->height;
width = image->width ;
channels = image->nChannels;
dx = cvCreateImage(cvSize(image->width , image->height) , IPL_DEPTH_32F , 3);
dy = cvCreateImage(cvSize(image->width , image->height) , IPL_DEPTH_32F , 3);
sizeX = width / k;
sizeY = height / k;
px = CNTPARTION + 2 * CNTPARTION; // êîíòðàñòíîå è íå êîíòðàñòíîå èçîáðàæåíèå
p = px;
strsz = sizeX * p;
allocFeatureMapObject(map, sizeX, sizeY, p, px);
cvFilter2D(image, dx, &kernel_dx, cvPoint(-1, 0));
cvFilter2D(image, dy, &kernel_dy, cvPoint(0, -1));
for(i = 0; i <= CNTPARTION; i++)
{
boundary_x[i] = cosf((((float)i) * (((float)PI) / (float) (CNTPARTION))));
boundary_y[i] = sinf((((float)i) * (((float)PI) / (float) (CNTPARTION))));
}/*for(i = 0; i <= CNTPARTION; i++) */
r = (float *)malloc( sizeof(float) * (width * height));
alfa = (int *)malloc( sizeof(int ) * (width * height * 2));
for(j = 1; j < height-1; j++)
{
datadx = (float*)(dx->imageData + dx->widthStep *j);
datady = (float*)(dy->imageData + dy->widthStep *j);
for(i = 1; i < width-1; i++)
{
c = 0;
x = (datadx[i*channels+c]);
y = (datady[i*channels+c]);
r[j * width + i] =sqrtf(x*x + y*y);
for(kk = 1; kk < channels; kk++)
{
tx = (datadx[i*channels+kk]);
ty = (datady[i*channels+kk]);
tmp =sqrtf(tx*tx + ty*ty);
if(tmp > r[j * width + i])
{
r[j * width + i] = tmp;
c = kk;
x = tx;
y = ty;
}
}/*for(kk = 1; kk < channels; kk++)*/
max = boundary_x[0]*x + boundary_y[0]*y;
maxi = 0;
for (kk = 0; kk < CNTPARTION; kk++) {
tmp_scal = boundary_x[kk]*x + boundary_y[kk]*y;
if (tmp_scal> max) {
max = tmp_scal;
maxi = kk;
}else if (-tmp_scal> max) {
max = -tmp_scal;
maxi = kk + CNTPARTION;
}
}
alfa[j * width * 2 + i * 2 ] = maxi % CNTPARTION;
alfa[j * width * 2 + i * 2 + 1] = maxi;
}/*for(i = 0; i < width; i++)*/
}/*for(j = 0; j < height; j++)*/
//ïîäñ÷åò âåñîâ è ñìåùåíèé
nearest_x = (int *)malloc(sizeof(int) * k);
nearest_y = (int *)malloc(sizeof(int) * k);
w = (float*)malloc(sizeof(float) * (k * 2));
for(i = 0; i < k / 2; i++)
{
nearest_x[i] = -1;
nearest_y[i] = -1;
}/*for(i = 0; i < k / 2; i++)*/
for(i = k / 2; i < k; i++)
{
nearest_x[i] = 1;
nearest_y[i] = 1;
}/*for(i = k / 2; i < k; i++)*/
for(j = 0; j < k / 2; j++)
{
b_x = k / 2 + j + 0.5f;
a_x = k / 2 - j - 0.5f;
w[j * 2 ] = 1.0f/a_x * ((a_x * b_x) / ( a_x + b_x));
w[j * 2 + 1] = 1.0f/b_x * ((a_x * b_x) / ( a_x + b_x));
}/*for(j = 0; j < k / 2; j++)*/
for(j = k / 2; j < k; j++)
{
a_x = j - k / 2 + 0.5f;
b_x =-j + k / 2 - 0.5f + k;
w[j * 2 ] = 1.0f/a_x * ((a_x * b_x) / ( a_x + b_x));
w[j * 2 + 1] = 1.0f/b_x * ((a_x * b_x) / ( a_x + b_x));
}/*for(j = k / 2; j < k; j++)*/
//èíòåðïîëÿöèÿ
for(i = 0; i < sizeY; i++)
{
for(j = 0; j < sizeX; j++)
{
for(ii = 0; ii < k; ii++)
{
for(jj = 0; jj < k; jj++)
{
if ((i * k + ii > 0) && (i * k + ii < height - 1) && (j * k + jj > 0) && (j * k + jj < width - 1))
{
d = (k*i + ii)* width + (j*k + jj);
(*map)->Map[(i ) * strsz + (j ) * (*map)->p + alfa[d * 2 ] ] +=
r[d] * w[ii * 2 ] * w[jj * 2 ];
(*map)->Map[(i ) * strsz + (j ) * (*map)->p + alfa[d * 2 + 1] + CNTPARTION] +=
r[d] * w[ii * 2 ] * w[jj * 2 ];
if ((i + nearest_y[ii] >= 0) && (i + nearest_y[ii] <= sizeY - 1))
{
(*map)->Map[(i + nearest_y[ii]) * strsz + (j ) * (*map)->p + alfa[d * 2 ] ] +=
r[d] * w[ii * 2 + 1] * w[jj * 2 ];
(*map)->Map[(i + nearest_y[ii]) * strsz + (j ) * (*map)->p + alfa[d * 2 + 1] + CNTPARTION] +=
r[d] * w[ii * 2 + 1] * w[jj * 2 ];
}
if ((j + nearest_x[jj] >= 0) && (j + nearest_x[jj] <= sizeX - 1))
{
(*map)->Map[(i ) * strsz + (j + nearest_x[jj]) * (*map)->p + alfa[d * 2 ] ] +=
r[d] * w[ii * 2 ] * w[jj * 2 + 1];
(*map)->Map[(i ) * strsz + (j + nearest_x[jj]) * (*map)->p + alfa[d * 2 + 1] + CNTPARTION] +=
r[d] * w[ii * 2 ] * w[jj * 2 + 1];
}
if ((i + nearest_y[ii] >= 0) && (i + nearest_y[ii] <= sizeY - 1) && (j + nearest_x[jj] >= 0) && (j + nearest_x[jj] <= sizeX - 1))
{
(*map)->Map[(i + nearest_y[ii]) * strsz + (j + nearest_x[jj]) * (*map)->p + alfa[d * 2 ] ] +=
r[d] * w[ii * 2 + 1] * w[jj * 2 + 1];
(*map)->Map[(i + nearest_y[ii]) * strsz + (j + nearest_x[jj]) * (*map)->p + alfa[d * 2 + 1] + CNTPARTION] +=
r[d] * w[ii * 2 + 1] * w[jj * 2 + 1];
}
}
}/*for(jj = 0; jj < k; jj++)*/
}/*for(ii = 0; ii < k; ii++)*/
}/*for(j = 1; j < sizeX - 1; j++)*/
}/*for(i = 1; i < sizeY - 1; i++)*/
cvReleaseImage(&dx);
cvReleaseImage(&dy);
free(w);
free(nearest_x);
free(nearest_y);
free(r);
free(alfa);
return LATENT_SVM_OK;
}
/*
// Feature map Normalization and Truncation
//
// API
// int normalizationAndTruncationFeatureMaps(featureMap *map, const float alfa);
// INPUT
// map - feature map
// alfa - truncation threshold
// OUTPUT
// map - truncated and normalized feature map
// RESULT
// Error status
*/
int normalizationAndTruncationFeatureMaps(featureMap *map, const float alfa)
{
int i,j, ii;
int sizeX, sizeY, p, pos, pp, xp, pos1, pos2;
float * part_noma; // norm of C(i, j)
float * new_data;
float norm_val;
sizeX = map->sizeX;
sizeY = map->sizeY;
part_noma = (float *)malloc (sizeof(float) * (sizeX * sizeY));
p = map->xp / 3;
for(i = 0; i < sizeX * sizeY; i++)
{
norm_val = 0.0;
pos = i * map->p;
for(j = 0; j < p; j++)
{
norm_val += map->Map[pos + j] * map->Map[pos + j];
}/*for(j = 0; j < p; j++)*/
part_noma[i] = norm_val;
}/*for(i = 0; i < sizeX * sizeY; i++)*/
xp = map->xp;
pp = xp * 4;
sizeX -= 2;
sizeY -= 2;
new_data = (float *)malloc (sizeof(float) * (sizeX * sizeY * pp));
//normalization
for(i = 1; i <= sizeY; i++)
{
for(j = 1; j <= sizeX; j++)
{
norm_val = sqrtf(
part_noma[(i )*(sizeX + 2) + (j )] +
part_noma[(i )*(sizeX + 2) + (j + 1)] +
part_noma[(i + 1)*(sizeX + 2) + (j )] +
part_noma[(i + 1)*(sizeX + 2) + (j + 1)]);
pos1 = (i ) * (sizeX + 2) * xp + (j ) * xp;
pos2 = (i-1) * (sizeX ) * pp + (j-1) * pp;
for(ii = 0; ii < p; ii++)
{
new_data[pos2 + ii ] = map->Map[pos1 + ii ] / norm_val;
}/*for(ii = 0; ii < p; ii++)*/
for(ii = 0; ii < 2 * p; ii++)
{
new_data[pos2 + ii + p * 4] = map->Map[pos1 + ii + p] / norm_val;
}/*for(ii = 0; ii < 2 * p; ii++)*/
norm_val = sqrtf(
part_noma[(i )*(sizeX + 2) + (j )] +
part_noma[(i )*(sizeX + 2) + (j + 1)] +
part_noma[(i - 1)*(sizeX + 2) + (j )] +
part_noma[(i - 1)*(sizeX + 2) + (j + 1)]);
for(ii = 0; ii < p; ii++)
{
new_data[pos2 + ii + p ] = map->Map[pos1 + ii ] / norm_val;
}/*for(ii = 0; ii < p; ii++)*/
for(ii = 0; ii < 2 * p; ii++)
{
new_data[pos2 + ii + p * 6] = map->Map[pos1 + ii + p] / norm_val;
}/*for(ii = 0; ii < 2 * p; ii++)*/
norm_val = sqrtf(
part_noma[(i )*(sizeX + 2) + (j )] +
part_noma[(i )*(sizeX + 2) + (j - 1)] +
part_noma[(i + 1)*(sizeX + 2) + (j )] +
part_noma[(i + 1)*(sizeX + 2) + (j - 1)]);
for(ii = 0; ii < p; ii++)
{
new_data[pos2 + ii + p * 2] = map->Map[pos1 + ii ] / norm_val;
}/*for(ii = 0; ii < p; ii++)*/
for(ii = 0; ii < 2 * p; ii++)
{
new_data[pos2 + ii + p * 8] = map->Map[pos1 + ii + p] / norm_val;
}/*for(ii = 0; ii < 2 * p; ii++)*/
norm_val = sqrtf(
part_noma[(i )*(sizeX + 2) + (j )] +
part_noma[(i )*(sizeX + 2) + (j - 1)] +
part_noma[(i - 1)*(sizeX + 2) + (j )] +
part_noma[(i - 1)*(sizeX + 2) + (j - 1)]);
for(ii = 0; ii < p; ii++)
{
new_data[pos2 + ii + p * 3 ] = map->Map[pos1 + ii ] / norm_val;
}/*for(ii = 0; ii < p; ii++)*/
for(ii = 0; ii < 2 * p; ii++)
{
new_data[pos2 + ii + p * 10] = map->Map[pos1 + ii + p] / norm_val;
}/*for(ii = 0; ii < 2 * p; ii++)*/
}/*for(j = 1; j <= sizeX; j++)*/
}/*for(i = 1; i <= sizeY; i++)*/
//truncation
for(i = 0; i < sizeX * sizeY * pp; i++)
{
if(new_data [i] > alfa) new_data [i] = alfa;
}/*for(i = 0; i < sizeX * sizeY * pp; i++)*/
//swop data
map->p = pp;
map->xp = xp;
map->sizeX = sizeX;
map->sizeY = sizeY;
free (map->Map);
free (part_noma);
map->Map = new_data;
return LATENT_SVM_OK;
}
/*
// Feature map reduction
// In each cell we reduce dimension of the feature vector
// according to original paper special procedure
//
// API
// int PCAFeatureMaps(featureMap *map)
// INPUT
// map - feature map
// OUTPUT
// map - feature map
// RESULT
// Error status
*/
int PCAFeatureMaps(featureMap *map)
{
int i,j, ii, jj, k;
int sizeX, sizeY, p, pp, xp, yp, pos1, pos2;
float * new_data;
float val;
float nx, ny;
sizeX = map->sizeX;
sizeY = map->sizeY;
p = map->p;
pp = map->xp + 4;
yp = 4;
xp = (map->xp / 3);
nx = 1.0f / sqrtf((float)(xp * 2));
ny = 1.0f / sqrtf((float)(yp ));
new_data = (float *)malloc (sizeof(float) * (sizeX * sizeY * pp));
for(i = 0; i < sizeY; i++)
{
for(j = 0; j < sizeX; j++)
{
pos1 = ((i)*sizeX + j)*p;
pos2 = ((i)*sizeX + j)*pp;
k = 0;
for(jj = 0; jj < xp * 2; jj++)
{
val = 0;
for(ii = 0; ii < yp; ii++)
{
val += map->Map[pos1 + yp * xp + ii * xp * 2 + jj];
}/*for(ii = 0; ii < yp; ii++)*/
new_data[pos2 + k] = val * ny;
k++;
}/*for(jj = 0; jj < xp * 2; jj++)*/
for(jj = 0; jj < xp; jj++)
{
val = 0;
for(ii = 0; ii < yp; ii++)
{
val += map->Map[pos1 + ii * xp + jj];
}/*for(ii = 0; ii < yp; ii++)*/
new_data[pos2 + k] = val * ny;
k++;
}/*for(jj = 0; jj < xp; jj++)*/
for(ii = 0; ii < yp; ii++)
{
val = 0;
for(jj = 0; jj < 2 * xp; jj++)
{
val += map->Map[pos1 + yp * xp + ii * xp * 2 + jj];
}/*for(jj = 0; jj < xp; jj++)*/
new_data[pos2 + k] = val * nx;
k++;
} /*for(ii = 0; ii < yp; ii++)*/
}/*for(j = 0; j < sizeX; j++)*/
}/*for(i = 0; i < sizeY; i++)*/
//swop data
map->p = pp;
map->xp = pp;
free (map->Map);
map->Map = new_data;
return LATENT_SVM_OK;
}
/*
// Getting feature pyramid
//
// API
// int getFeaturePyramid(IplImage * image, const filterObject **all_F,
const int n_f,
const int lambda, const int k,
const int startX, const int startY,
const int W, const int H, featurePyramid **maps);
// INPUT
// image - image
// lambda - resize scale
// k - size of cells
// startX - X coordinate of the image rectangle to search
// startY - Y coordinate of the image rectangle to search
// W - width of the image rectangle to search
// H - height of the image rectangle to search
// OUTPUT
// maps - feature maps for all levels
// RESULT
// Error status
*/
int getFeaturePyramid(IplImage * image,
const int lambda, const int k,
const int startX, const int startY,
const int W, const int H, featurePyramid **maps)
{
IplImage *img2, *imgTmp, *imgResize;
float step, tmp;
int cntStep;
int maxcall;
int i;
int err;
featureMap *map;
//geting subimage
cvSetImageROI(image, cvRect(startX, startY, W, H));
img2 = cvCreateImage(cvGetSize(image), image->depth, image->nChannels);
cvCopy(image, img2, NULL);
cvResetImageROI(image);
if(img2->depth != IPL_DEPTH_32F)
{
imgResize = cvCreateImage(cvSize(img2->width , img2->height) , IPL_DEPTH_32F , 3);
cvConvert(img2, imgResize);
}
else
{
imgResize = img2;
}
step = powf(2.0f, 1.0f/ ((float)lambda));
maxcall = W/k;
if( maxcall > H/k )
{
maxcall = H/k;
}
cntStep = (int)(logf((float)maxcall/(5.0f))/logf(step)) + 1;
//printf("Count step: %f %d\n", step, cntStep);
allocFeaturePyramidObject(maps, lambda, cntStep + lambda);
for(i = 0; i < lambda; i++)
{
tmp = 1.0f / powf(step, (float)i);
imgTmp = resize_opencv (imgResize, tmp);
//imgTmp = resize_article_dp(img2, tmp, 4);
err = getFeatureMaps_dp(imgTmp, 4, &map);
err = normalizationAndTruncationFeatureMaps(map, 0.2f);
err = PCAFeatureMaps(map);
(*maps)->pyramid[i] = map;
//printf("%d, %d\n", map->sizeY, map->sizeX);
cvReleaseImage(&imgTmp);
}
/**********************************one**************/
for(i = 0; i < cntStep; i++)
{
tmp = 1.0f / powf(step, (float)i);
imgTmp = resize_opencv (imgResize, tmp);
//imgTmp = resize_article_dp(imgResize, tmp, 8);
err = getFeatureMaps_dp(imgTmp, 8, &map);
err = normalizationAndTruncationFeatureMaps(map, 0.2f);
err = PCAFeatureMaps(map);
(*maps)->pyramid[i + lambda] = map;
//printf("%d, %d\n", map->sizeY, map->sizeX);
cvReleaseImage(&imgTmp);
}/*for(i = 0; i < cntStep; i++)*/
if(img2->depth != IPL_DEPTH_32F)
{
cvReleaseImage(&imgResize);
}
cvReleaseImage(&img2);
return LATENT_SVM_OK;
}
/*
// add zero border to feature map
//
// API
// int addBordersToFeatureMaps(featureMap *map, const int bX, const int bY);
// INPUT
// map - feature map
// bX - border size in x
// bY - border size in y
// OUTPUT
// map - feature map
// RESULT
// Error status
*/
int addBordersToFeatureMaps(featureMap *map, const int bX, const int bY){
int i,j, jj;
int sizeX, sizeY, p, pos1, pos2;
float * new_data;
sizeX = map->sizeX;
sizeY = map->sizeY;
p = map->p;
new_data = (float *)malloc (sizeof(float) * ((sizeX + 2 * bX) * (sizeY + 2 * bY) * p));
for(i = 0; i < ((sizeX + 2 * bX) * (sizeY + 2 * bY) * p); i++)
{
new_data[i] = (float)0;
}/*for(i = 0; i < ((sizeX + 2 * bX) * (sizeY + 2 * bY) * p); i++)*/
for(i = 0; i < sizeY; i++)
{
for(j = 0; j < sizeX; j++)
{
pos1 = ((i )*sizeX + (j )) * p;
pos2 = ((i + bY)*(sizeX + 2 * bX) + (j + bX)) * p;
for(jj = 0; jj < p; jj++)
{
new_data[pos2 + jj] = map->Map[pos1 + jj];
}/*for(jj = 0; jj < p; jj++)*/
}/*for(j = 0; j < sizeX; j++)*/
}/*for(i = 0; i < sizeY; i++)*/
//swop data
map->sizeX = sizeX + 2 * bX;
map->sizeY = sizeY + 2 * bY;
free (map->Map);
map->Map = new_data;
return LATENT_SVM_OK;
}

246
modules/objdetect/src/fft.cpp Normal file
View File

@ -0,0 +1,246 @@
#include "_fft.h"
int getEntireRes(int number, int divisor, int *entire, int *res)
{
*entire = number / divisor;
*res = number % divisor;
return FFT_OK;
}
int getMultipliers(int n, int *n1, int *n2)
{
int multiplier, i;
if (n == 1)
{
*n1 = 1;
*n2 = 1;
return FFT_ERROR; // n = 1
}
multiplier = n / 2;
for (i = multiplier; i >= 2; i--)
{
if (n % i == 0)
{
*n1 = i;
*n2 = n / i;
return FFT_OK; // n = n1 * n2
}
}
*n1 = 1;
*n2 = n;
return FFT_ERROR; // n - prime number
}
/*
// 1-dimensional FFT
//
// API
// int fft(float *x_in, float *x_out, int n, int shift);
// INPUT
// x_in - input signal
// n - number of elements for searching Fourier image
// shift - shift between input elements
// OUTPUT
// x_out - output signal (contains 2n elements in order
Re(x_in[0]), Im(x_in[0]), Re(x_in[1]), Im(x_in[1]) and etc.)
// RESULT
// Error status
*/
int fft(float *x_in, float *x_out, int n, int shift)
{
int n1, n2, res, k1, k2, m1, m2, index, idx;
float alpha, beta, gamma, angle, cosAngle, sinAngle;
float tmpGamma, tmpAlpha, tmpBeta;
float tmpRe, tmpIm, phaseRe, phaseIm;
res = getMultipliers(n, &n1, &n2);
if (res == FFT_OK)
{
fft(x_in, x_out, n1, shift);
fft(x_in, x_out, n2, shift);
}
alpha = (float)(2.0 * PI / ((float)n));
beta = (float)(2.0 * PI / ((float)n1));
gamma = (float)(2.0 * PI / ((float)n2));
for (k1 = 0; k1 < n1; k1++)
{
tmpBeta = beta * k1;
for (k2 = 0; k2 < n2; k2++)
{
idx = shift * (n2 * k1 + k2);
x_out[idx] = 0.0;
x_out[idx + 1] = 0.0;
tmpGamma = gamma * k2;
tmpAlpha = alpha * k2;
for (m1 = 0; m1 < n1; m1++)
{
tmpRe = 0.0;
tmpIm = 0.0;
for (m2 = 0; m2 < n2; m2++)
{
angle = tmpGamma * m2;
index = shift * (n1 * m2 + m1);
cosAngle = cosf(angle);
sinAngle = sinf(angle);
tmpRe += x_in[index] * cosAngle + x_in[index + 1] * sinAngle;
tmpIm += x_in[index + 1] * cosAngle - x_in[index] * sinAngle;
}
angle = tmpAlpha * m1;
cosAngle = cosf(angle);
sinAngle = sinf(angle);
phaseRe = cosAngle * tmpRe + sinAngle * tmpIm;
phaseIm = cosAngle * tmpIm - sinAngle * tmpRe;
angle = tmpBeta * m1;
cosAngle = cosf(angle);
sinAngle = sinf(angle);
x_out[idx] += (cosAngle * phaseRe + sinAngle * phaseIm);
x_out[idx + 1] += (cosAngle * phaseIm - sinAngle * phaseRe);
}
}
}
return FFT_OK;
}
/*
// Inverse 1-dimensional FFT
//
// API
// int fftInverse(float *x_in, float *x_out, int n, int shift);
// INPUT
// x_in - Fourier image of 1d input signal(contains 2n elements
in order Re(x_in[0]), Im(x_in[0]),
Re(x_in[1]), Im(x_in[1]) and etc.)
// n - number of elements for searching counter FFT image
// shift - shift between input elements
// OUTPUT
// x_in - input signal (contains n elements)
// RESULT
// Error status
*/
int fftInverse(float *x_in, float *x_out, int n, int shift)
{
int n1, n2, res, k1, k2, m1, m2, index, idx;
float alpha, beta, gamma, angle, cosAngle, sinAngle;
float tmpRe, tmpIm, phaseRe, phaseIm;
res = getMultipliers(n, &n1, &n2);
if (res == FFT_OK)
{
fftInverse(x_in, x_out, n1, shift);
fftInverse(x_in, x_out, n2, shift);
}
alpha = (float)(2.0f * PI / ((float)n));
beta = (float)(2.0f * PI / ((float)n1));
gamma = (float)(2.0f * PI / ((float)n2));
for (m1 = 0; m1 < n1; m1++)
{
for (m2 = 0; m2 < n2; m2++)
{
idx = (n1 * m2 + m1) * shift;
x_out[idx] = 0.0;
x_out[idx + 1] = 0.0;
for (k2 = 0; k2 < n2; k2++)
{
tmpRe = 0.0;
tmpIm = 0.0;
for (k1 = 0; k1 < n1; k1++)
{
angle = beta * k1 * m1;
index = shift *(n2 * k1 + k2);
sinAngle = sinf(angle);
cosAngle = cosf(angle);
tmpRe += x_in[index] * cosAngle - x_in[index + 1] * sinAngle;
tmpIm += x_in[index] * sinAngle + x_in[index + 1] * cosAngle;
}
angle = alpha * m1 * k2;
sinAngle = sinf(angle);
cosAngle = cosf(angle);
phaseRe = cosAngle * tmpRe - sinAngle * tmpIm;
phaseIm = cosAngle * tmpIm + sinAngle * tmpRe;
angle = gamma * k2 * m2;
sinAngle = sinf(angle);
cosAngle = cosf(angle);
x_out[idx] += cosAngle * phaseRe - sinAngle * phaseIm;
x_out[idx + 1] += cosAngle * phaseIm + sinAngle * phaseRe;
}
x_out[idx] /= n;
x_out[idx + 1] /= n;
}
}
return FFT_OK;
}
/*
// 2-dimensional FFT
//
// API
// int fft2d(float *x_in, float *x_out, int numRows, int numColls);
// INPUT
// x_in - input signal (matrix, launched by rows)
// numRows - number of rows
// numColls - number of collumns
// OUTPUT
// x_out - output signal (contains (2 * numRows * numColls) elements
in order Re(x_in[0][0]), Im(x_in[0][0]),
Re(x_in[0][1]), Im(x_in[0][1]) and etc.)
// RESULT
// Error status
*/
int fft2d(float *x_in, float *x_out, int numRows, int numColls)
{
int i, size;
float *x_outTmp;
size = numRows * numColls;
x_outTmp = (float *)malloc(sizeof(float) * (2 * size));
for (i = 0; i < numRows; i++)
{
fft(x_in + i * 2 * numColls,
x_outTmp + i * 2 * numColls,
numColls, 2);
}
for (i = 0; i < numColls; i++)
{
fft(x_outTmp + 2 * i,
x_out + 2 * i,
numRows, 2 * numColls);
}
free(x_outTmp);
return FFT_OK;
}
/*
// Inverse 2-dimensional FFT
//
// API
// int fftInverse2d(float *x_in, float *x_out, int numRows, int numColls);
// INPUT
// x_in - Fourier image of matrix (contains (2 * numRows * numColls)
elements in order Re(x_in[0][0]), Im(x_in[0][0]),
Re(x_in[0][1]), Im(x_in[0][1]) and etc.)
// numRows - number of rows
// numColls - number of collumns
// OUTPUT
// x_out - initial signal (matrix, launched by rows)
// RESULT
// Error status
*/
int fftInverse2d(float *x_in, float *x_out, int numRows, int numColls)
{
int i, size;
float *x_outTmp;
size = numRows * numColls;
x_outTmp = (float *)malloc(sizeof(float) * (2 * size));
for (i = 0; i < numRows; i++)
{
fftInverse(x_in + i * 2 * numColls,
x_outTmp + i * 2 * numColls,
numColls, 2);
}
for (i = 0; i < numColls; i++)
{
fftInverse(x_outTmp + 2 * i,
x_out + 2 * i,
numRows, 2 * numColls);
}
free(x_outTmp);
return FFT_OK;
}

611
modules/objdetect/src/latentsvm.cpp Normal file
View File

@ -0,0 +1,611 @@
#include "_latentsvm.h"
#include "_matching.h"
/*
// Transformation filter displacement from the block space
// to the space of pixels at the initial image
//
// API
// int convertPoints(int countLevel, CvPoint *points, int *levels,
CvPoint **partsDisplacement, int kPoints, int n);
// INPUT
// countLevel - the number of levels in the feature pyramid
// points - the set of root filter positions (in the block space)
// levels - the set of levels
// partsDisplacement - displacement of part filters (in the block space)
// kPoints - number of root filter positions
// n - number of part filters
// initialImageLevel - level that contains features for initial image
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// points - the set of root filter positions (in the space of pixels)
// partsDisplacement - displacement of part filters (in the space of pixels)
// RESULT
// Error status
*/
int convertPoints(int countLevel, int lambda,
int initialImageLevel,
CvPoint *points, int *levels,
CvPoint **partsDisplacement, int kPoints, int n,
int maxXBorder,
int maxYBorder)
{
int i, j, bx, by;
float step, scale;
step = powf( 2.0f, 1.0f / ((float)lambda) );
computeBorderSize(maxXBorder, maxYBorder, &bx, &by);
for (i = 0; i < kPoints; i++)
{
// scaling factor for root filter
scale = SIDE_LENGTH * powf(step, (float)(levels[i] - initialImageLevel));
points[i].x = (int)((points[i].x - bx + 1) * scale);
points[i].y = (int)((points[i].y - by + 1) * scale);
// scaling factor for part filters
scale = SIDE_LENGTH * powf(step, (float)(levels[i] - lambda - initialImageLevel));
for (j = 0; j < n; j++)
{
partsDisplacement[i][j].x = (int)((partsDisplacement[i][j].x -
2 * bx + 1) * scale);
partsDisplacement[i][j].y = (int)((partsDisplacement[i][j].y -
2 * by + 1) * scale);
}
}
return LATENT_SVM_OK;
}
/*
// Elimination boxes that are outside the image boudaries
//
// API
// int clippingBoxes(int width, int height,
CvPoint *points, int kPoints);
// INPUT
// width - image wediht
// height - image heigth
// points - a set of points (coordinates of top left or
bottom right corners)
// kPoints - points number
// OUTPUT
// points - updated points (if coordinates less than zero then
set zero coordinate, if coordinates more than image
size then set coordinates equal image size)
// RESULT
// Error status
*/
int clippingBoxes(int width, int height,
CvPoint *points, int kPoints)
{
int i;
for (i = 0; i < kPoints; i++)
{
if (points[i].x > width - 1)
{
points[i].x = width - 1;
}
if (points[i].x < 0)
{
points[i].x = 0;
}
if (points[i].y > height - 1)
{
points[i].y = height - 1;
}
if (points[i].y < 0)
{
points[i].y = 0;
}
}
return LATENT_SVM_OK;
}
/*
// Creation feature pyramid with nullable border
//
// API
// featurePyramid* createFeaturePyramidWithBorder(const IplImage *image,
int maxXBorder, int maxYBorder);
// INPUT
// image - initial image
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// RESULT
// Feature pyramid with nullable border
*/
featurePyramid* createFeaturePyramidWithBorder(IplImage *image,
int maxXBorder, int maxYBorder)
{
int opResult;
int bx, by;
int level;
featurePyramid *H;
// Obtaining feature pyramid
opResult = getFeaturePyramid(image, LAMBDA, SIDE_LENGTH, 0, 0,
image->width, image->height, &H);
if (opResult != LATENT_SVM_OK)
{
freeFeaturePyramidObject(&H);
return NULL;
} /* if (opResult != LATENT_SVM_OK) */
// Addition nullable border for each feature map
// the size of the border for root filters
computeBorderSize(maxXBorder, maxYBorder, &bx, &by);
for (level = 0; level < H->countLevel; level++)
{
addNullableBorder(H->pyramid[level], bx, by);
}
return H;
}
/*
// Computation of the root filter displacement and values of score function
//
// API
// int searchObject(const featurePyramid *H, const filterObject **all_F, int n,
float b,
int maxXBorder,
int maxYBorder,
CvPoint **points, int **levels, int *kPoints, float *score,
CvPoint ***partsDisplacement);
// INPUT
// image - initial image for searhing object
// all_F - the set of filters (the first element is root filter,
other elements - part filters)
// n - the number of part filters
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// OUTPUT
// points - positions (x, y) of the upper-left corner
of root filter frame
// levels - levels that correspond to each position
// kPoints - number of positions
// score - value of the score function
// partsDisplacement - part filters displacement for each position
of the root filter
// RESULT
// Error status
*/
int searchObject(const featurePyramid *H, const filterObject **all_F,
int n, float b,
int maxXBorder,
int maxYBorder,
CvPoint **points, int **levels, int *kPoints, float *score,
CvPoint ***partsDisplacement)
{
int opResult;
// Matching
opResult = maxFunctionalScore(all_F, n, H, b, maxXBorder, maxYBorder,
score, points, levels,
kPoints, partsDisplacement);
if (opResult != LATENT_SVM_OK)
{
return LATENT_SVM_SEARCH_OBJECT_FAILED;
}
// Transformation filter displacement from the block space
// to the space of pixels at the initial image
// that settles at the level number LAMBDA
convertPoints(H->countLevel, H->lambda, LAMBDA, (*points),
(*levels), (*partsDisplacement), (*kPoints), n,
maxXBorder, maxYBorder);
return LATENT_SVM_OK;
}
/*
// Computation right bottom corners coordinates of bounding boxes
//
// API
// int estimateBoxes(CvPoint *points, int *levels, int kPoints,
int sizeX, int sizeY, CvPoint **oppositePoints);
// INPUT
// points - left top corners coordinates of bounding boxes
// levels - levels of feature pyramid where points were found
// (sizeX, sizeY) - size of root filter
// OUTPUT
// oppositePoins - right bottom corners coordinates of bounding boxes
// RESULT
// Error status
*/
int estimateBoxes(CvPoint *points, int *levels, int kPoints,
int sizeX, int sizeY, CvPoint **oppositePoints)
{
int i;
float step;
step = powf( 2.0f, 1.0f / ((float)(LAMBDA)));
*oppositePoints = (CvPoint *)malloc(sizeof(CvPoint) * kPoints);
for (i = 0; i < kPoints; i++)
{
getOppositePoint(points[i], sizeX, sizeY, step, levels[i] - LAMBDA, &((*oppositePoints)[i]));
}
return LATENT_SVM_OK;
}
/*
// Computation of the root filter displacement and values of score function
//
// API
// int searchObjectThreshold(const featurePyramid *H,
const filterObject **all_F, int n,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
CvPoint **points, int **levels, int *kPoints,
float **score, CvPoint ***partsDisplacement);
// INPUT
// H - feature pyramid
// all_F - the set of filters (the first element is root filter,
other elements - part filters)
// n - the number of part filters
// b - linear term of the score function
// maxXBorder - the largest root filter size (X-direction)
// maxYBorder - the largest root filter size (Y-direction)
// scoreThreshold - score threshold
// OUTPUT
// points - positions (x, y) of the upper-left corner
of root filter frame
// levels - levels that correspond to each position
// kPoints - number of positions
// score - values of the score function
// partsDisplacement - part filters displacement for each position
of the root filter
// RESULT
// Error status
*/
int searchObjectThreshold(const featurePyramid *H,
const filterObject **all_F, int n,
float b,
int maxXBorder, int maxYBorder,
float scoreThreshold,
CvPoint **points, int **levels, int *kPoints,
float **score, CvPoint ***partsDisplacement)
{
int opResult;
// Matching
opResult = thresholdFunctionalScore(all_F, n, H, b,
maxXBorder, maxYBorder,
scoreThreshold,
score, points, levels,
kPoints, partsDisplacement);
if (opResult != LATENT_SVM_OK)
{
return LATENT_SVM_SEARCH_OBJECT_FAILED;
}
// Transformation filter displacement from the block space
// to the space of pixels at the initial image
// that settles at the level number LAMBDA
convertPoints(H->countLevel, H->lambda, LAMBDA, (*points),
(*levels), (*partsDisplacement), (*kPoints), n,
maxXBorder, maxYBorder);
return LATENT_SVM_OK;
}
/*
// Compute opposite point for filter box
//
// API
// int getOppositePoint(CvPoint point,
int sizeX, int sizeY,
float step, int degree,
CvPoint *oppositePoint);
// INPUT
// point - coordinates of filter top left corner
(in the space of pixels)
// (sizeX, sizeY) - filter dimension in the block space
// step - scaling factor
// degree - degree of the scaling factor
// OUTPUT
// oppositePoint - coordinates of filter bottom corner
(in the space of pixels)
// RESULT
// Error status
*/
int getOppositePoint(CvPoint point,
int sizeX, int sizeY,
float step, int degree,
CvPoint *oppositePoint)
{
float scale;
scale = SIDE_LENGTH * powf(step, (float)degree);
oppositePoint->x = (int)(point.x + sizeX * scale);
oppositePoint->y = (int)(point.y + sizeY * scale);
return LATENT_SVM_OK;
}
/*
// Drawing root filter boxes
//
// API
// int showRootFilterBoxes(const IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
// INPUT
// image - initial image
// filter - root filter object
// points - a set of points
// levels - levels of feature pyramid
// kPoints - number of points
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// window contained initial image and filter boxes
// RESULT
// Error status
*/
int showRootFilterBoxes(IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift)
{
int i;
float step;
CvPoint oppositePoint;
step = powf( 2.0f, 1.0f / ((float)LAMBDA));
for (i = 0; i < kPoints; i++)
{
// Drawing rectangle for filter
getOppositePoint(points[i], filter->sizeX, filter->sizeY,
step, levels[i] - LAMBDA, &oppositePoint);
cvRectangle(image, points[i], oppositePoint,
color, thickness, line_type, shift);
}
cvShowImage("Initial image", image);
return LATENT_SVM_OK;
}
/*
// Drawing part filter boxes
//
// API
// int showPartFilterBoxes(const IplImage *image,
const filterObject *filter,
CvPoint *points, int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift);
// INPUT
// image - initial image
// filters - a set of part filters
// n - number of part filters
// partsDisplacement - a set of points
// levels - levels of feature pyramid
// kPoints - number of foot filter positions
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// window contained initial image and filter boxes
// RESULT
// Error status
*/
int showPartFilterBoxes(IplImage *image,
const filterObject **filters,
int n, CvPoint **partsDisplacement,
int *levels, int kPoints,
CvScalar color, int thickness,
int line_type, int shift)
{
int i, j;
float step;
CvPoint oppositePoint;
step = powf( 2.0f, 1.0f / ((float)LAMBDA));
for (i = 0; i < kPoints; i++)
{
for (j = 0; j < n; j++)
{
// Drawing rectangles for part filters
getOppositePoint(partsDisplacement[i][j],
filters[j + 1]->sizeX, filters[j + 1]->sizeY,
step, levels[i] - 2 * LAMBDA, &oppositePoint);
cvRectangle(image, partsDisplacement[i][j], oppositePoint,
color, thickness, line_type, shift);
}
}
cvShowImage("Initial image", image);
return LATENT_SVM_OK;
}
/*
// Drawing boxes
//
// API
// int showBoxes(const IplImage *img,
const CvPoint *points, const CvPoint *oppositePoints, int kPoints,
CvScalar color, int thickness, int line_type, int shift);
// INPUT
// img - initial image
// points - top left corner coordinates
// oppositePoints - right bottom corner coordinates
// kPoints - points number
// color - line color for each box
// thickness - line thickness
// line_type - line type
// shift - shift
// OUTPUT
// RESULT
// Error status
*/
int showBoxes(IplImage *img,
const CvPoint *points, const CvPoint *oppositePoints, int kPoints,
CvScalar color, int thickness, int line_type, int shift)
{
int i;
for (i = 0; i < kPoints; i++)
{
cvRectangle(img, points[i], oppositePoints[i],
color, thickness, line_type, shift);
}
cvShowImage("Initial image", img);
return LATENT_SVM_OK;
}
/*
// Computation maximum filter size for each dimension
//
// API
// int getMaxFilterDims(const filterObject **filters, int kComponents,
const int *kPartFilters,
unsigned int *maxXBorder, unsigned int *maxYBorder);
// INPUT
// filters - a set of filters (at first root filter, then part filters
and etc. for all components)
// kComponents - number of components
// kPartFilters - number of part filters for each component
// OUTPUT
// maxXBorder - maximum of filter size at the horizontal dimension
// maxYBorder - maximum of filter size at the vertical dimension
// RESULT
// Error status
*/
int getMaxFilterDims(const filterObject **filters, int kComponents,
const int *kPartFilters,
unsigned int *maxXBorder, unsigned int *maxYBorder)
{
int i, componentIndex;
*maxXBorder = filters[0]->sizeX;
*maxYBorder = filters[0]->sizeY;
componentIndex = kPartFilters[0] + 1;
for (i = 1; i < kComponents; i++)
{
if (filters[componentIndex]->sizeX > *maxXBorder)
{
*maxXBorder = filters[componentIndex]->sizeX;
}
if (filters[componentIndex]->sizeY > *maxYBorder)
{
*maxYBorder = filters[componentIndex]->sizeY;
}
componentIndex += (kPartFilters[i] + 1);
}
return LATENT_SVM_OK;
}
/*
// Computation root filters displacement and values of score function
//
// API
// int searchObjectThresholdSomeComponents(const featurePyramid *H,
const filterObject **filters,
int kComponents, const int *kPartFilters,
const float *b, float scoreThreshold,
CvPoint **points, CvPoint **oppPoints,
float **score, int *kPoints);
// INPUT
// H - feature pyramid
// filters - filters (root filter then it's part filters, etc.)
// kComponents - root filters number
// kPartFilters - array of part filters number for each component
// b - array of linear terms
// scoreThreshold - score threshold
// OUTPUT
// points - root filters displacement (top left corners)
// oppPoints - root filters displacement (bottom right corners)
// score - array of score values
// kPoints - number of boxes
// RESULT
// Error status
*/
int searchObjectThresholdSomeComponents(const featurePyramid *H,
const filterObject **filters,
int kComponents, const int *kPartFilters,
const float *b, float scoreThreshold,
CvPoint **points, CvPoint **oppPoints,
float **score, int *kPoints)
{
int error = 0;
int i, j, s, f, componentIndex;
unsigned int maxXBorder, maxYBorder;
CvPoint **pointsArr, **oppPointsArr, ***partsDisplacementArr;
float **scoreArr;
int *kPointsArr, **levelsArr;
// Allocation memory
pointsArr = (CvPoint **)malloc(sizeof(CvPoint *) * kComponents);
oppPointsArr = (CvPoint **)malloc(sizeof(CvPoint *) * kComponents);
scoreArr = (float **)malloc(sizeof(float *) * kComponents);
kPointsArr = (int *)malloc(sizeof(int) * kComponents);
levelsArr = (int **)malloc(sizeof(int *) * kComponents);
partsDisplacementArr = (CvPoint ***)malloc(sizeof(CvPoint **) * kComponents);
// Getting maximum filter dimensions
error = getMaxFilterDims(filters, kComponents, kPartFilters, &maxXBorder, &maxYBorder);
componentIndex = 0;
*kPoints = 0;
// For each component perform searching
for (i = 0; i < kComponents; i++)
{
searchObjectThreshold(H, &(filters[componentIndex]), kPartFilters[i],
b[i], maxXBorder, maxYBorder, scoreThreshold,
&(pointsArr[i]), &(levelsArr[i]), &(kPointsArr[i]),
&(scoreArr[i]), &(partsDisplacementArr[i]));
estimateBoxes(pointsArr[i], levelsArr[i], kPointsArr[i],
filters[componentIndex]->sizeX, filters[componentIndex]->sizeY, &(oppPointsArr[i]));
componentIndex += (kPartFilters[i] + 1);
*kPoints += kPointsArr[i];
}
*points = (CvPoint *)malloc(sizeof(CvPoint) * (*kPoints));
*oppPoints = (CvPoint *)malloc(sizeof(CvPoint) * (*kPoints));
*score = (float *)malloc(sizeof(float) * (*kPoints));
s = 0;
for (i = 0; i < kComponents; i++)
{
f = s + kPointsArr[i];
for (j = s; j < f; j++)
{
(*points)[j].x = pointsArr[i][j - s].x;
(*points)[j].y = pointsArr[i][j - s].y;
(*oppPoints)[j].x = oppPointsArr[i][j - s].x;
(*oppPoints)[j].y = oppPointsArr[i][j - s].y;
(*score)[j] = scoreArr[i][j - s];
}
s = f;
}
// Release allocated memory
for (i = 0; i < kComponents; i++)
{
free(pointsArr[i]);
free(oppPointsArr[i]);
free(scoreArr[i]);
free(levelsArr[i]);
for (j = 0; j < kPointsArr[i]; j++)
{
free(partsDisplacementArr[i][j]);
}
free(partsDisplacementArr[i]);
}
free(pointsArr);
free(oppPointsArr);
free(scoreArr);
free(kPointsArr);
free(levelsArr);
free(partsDisplacementArr);
return LATENT_SVM_OK;
}

134
modules/objdetect/src/latentsvmdetector.cpp Normal file
View File

@ -0,0 +1,134 @@
#include "precomp.hpp"
#include "_lsvmparser.h"
#include "_matching.h"
/*
// load trained detector from a file
//
// API
// CvLatentSvmDetector* cvLoadLatentSvmDetector(const char* filename);
// INPUT
// filename - path to the file containing the parameters of
- trained Latent SVM detector
// OUTPUT
// trained Latent SVM detector in internal representation
*/
CvLatentSvmDetector* cvLoadLatentSvmDetector(const char* filename)
{
CvLatentSvmDetector* detector = 0;
filterObject** filters = 0;
int kFilters = 0;
int kComponents = 0;
int* kPartFilters = 0;
float* b = 0;
float scoreThreshold = 0.f;
loadModel(filename, &filters, &kFilters, &kComponents, &kPartFilters, &b, &scoreThreshold);
detector = (CvLatentSvmDetector*)malloc(sizeof(CvLatentSvmDetector));
detector->filters = filters;
detector->b = b;
detector->num_components = kComponents;
detector->num_filters = kFilters;
detector->num_part_filters = kPartFilters;
detector->score_threshold = scoreThreshold;
return detector;
}
/*
// release memory allocated for CvLatentSvmDetector structure
//
// API
// void cvReleaseLatentSvmDetector(CvLatentSvmDetector** detector);
// INPUT
// detector - CvLatentSvmDetector structure to be released
// OUTPUT
*/
void cvReleaseLatentSvmDetector(CvLatentSvmDetector** detector)
{
free((*detector)->b);
free((*detector)->num_part_filters);
for (int i = 0; i < (*detector)->num_filters; i++)
{
free((*detector)->filters[i]->H);
free((*detector)->filters[i]);
}
free((*detector)->filters);
free((*detector));
*detector = 0;
}
/*
// find rectangular regions in the given image that are likely
// to contain objects and corresponding confidence levels
//
// API
// CvSeq* cvLatentSvmDetectObjects(const IplImage* image,
// CvLatentSvmDetector* detector,
// CvMemStorage* storage,
// float overlap_threshold = 0.5f);
// INPUT
// image - image to detect objects in
// detector - Latent SVM detector in internal representation
// storage - memory storage to store the resultant sequence
// of the object candidate rectangles
// overlap_threshold - threshold for the non-maximum suppression algorithm [here will be the reference to original paper]
// OUTPUT
// sequence of detected objects (bounding boxes and confidence levels stored in CvObjectDetection structures)
*/
CvSeq* cvLatentSvmDetectObjects(IplImage* image,
CvLatentSvmDetector* detector,
CvMemStorage* storage,
float overlap_threshold)
{
featurePyramid *H = 0;
CvPoint *points = 0, *oppPoints = 0;
int kPoints = 0;
float *score = 0;
unsigned int maxXBorder = 0, maxYBorder = 0;
int numBoxesOut = 0;
CvPoint *pointsOut = 0;
CvPoint *oppPointsOut = 0;
float *scoreOut = 0;
CvSeq* result_seq = 0;
cvConvertImage(image, image, CV_CVTIMG_SWAP_RB);
// Getting maximum filter dimensions
getMaxFilterDims((const filterObject**)(detector->filters), detector->num_components, detector->num_part_filters, &maxXBorder, &maxYBorder);
// Create feature pyramid with nullable border
H = createFeaturePyramidWithBorder(image, maxXBorder, maxYBorder);
// Search object
searchObjectThresholdSomeComponents(H, (const filterObject**)(detector->filters), detector->num_components,
detector->num_part_filters, detector->b, detector->score_threshold,
&points, &oppPoints, &score, &kPoints);
// Clipping boxes
clippingBoxes(image->width, image->height, points, kPoints);
clippingBoxes(image->width, image->height, oppPoints, kPoints);
// NMS procedure
nonMaximumSuppression(kPoints, points, oppPoints, score, overlap_threshold,
&numBoxesOut, &pointsOut, &oppPointsOut, &scoreOut);
result_seq = cvCreateSeq( 0, sizeof(CvSeq), sizeof(CvObjectDetection), storage );
for (int i = 0; i < numBoxesOut; i++)
{
CvObjectDetection detection = {{0, 0, 0, 0}, 0};
detection.score = scoreOut[i];
CvRect bounding_box = {0, 0, 0, 0};
bounding_box.x = pointsOut[i].x;
bounding_box.y = pointsOut[i].y;
bounding_box.width = oppPointsOut[i].x - pointsOut[i].x;
bounding_box.height = oppPointsOut[i].y - pointsOut[i].y;
detection.rect = bounding_box;
cvSeqPush(result_seq, &detection);
}
cvConvertImage(image, image, CV_CVTIMG_SWAP_RB);
freeFeaturePyramidObject(&H);
free(points);
free(oppPoints);
free(score);
return result_seq;
}

800
modules/objdetect/src/lsvmparser.cpp Normal file
View File

@ -0,0 +1,800 @@
#include <stdio.h>
#include "string.h"
#include "_lsvmparser.h"
int isMODEL (char *str){
char stag [] = "<Model>";
char etag [] = "</Model>";
if(strcmp(stag, str) == 0)return MODEL;
if(strcmp(etag, str) == 0)return EMODEL;
return 0;
}
int isP (char *str){
char stag [] = "<P>";
char etag [] = "</P>";
if(strcmp(stag, str) == 0)return P;
if(strcmp(etag, str) == 0)return EP;
return 0;
}
int isSCORE (char *str){
char stag [] = "<ScoreThreshold>";
char etag [] = "</ScoreThreshold>";
if(strcmp(stag, str) == 0)return SCORE;
if(strcmp(etag, str) == 0)return ESCORE;
return 0;
}
int isCOMP (char *str){
char stag [] = "<Component>";
char etag [] = "</Component>";
if(strcmp(stag, str) == 0)return COMP;
if(strcmp(etag, str) == 0)return ECOMP;
return 0;
}
int isRFILTER (char *str){
char stag [] = "<RootFilter>";
char etag [] = "</RootFilter>";
if(strcmp(stag, str) == 0)return RFILTER;
if(strcmp(etag, str) == 0)return ERFILTER;
return 0;
}
int isPFILTERs (char *str){
char stag [] = "<PartFilters>";
char etag [] = "</PartFilters>";
if(strcmp(stag, str) == 0)return PFILTERs;
if(strcmp(etag, str) == 0)return EPFILTERs;
return 0;
}
int isPFILTER (char *str){
char stag [] = "<PartFilter>";
char etag [] = "</PartFilter>";
if(strcmp(stag, str) == 0)return PFILTER;
if(strcmp(etag, str) == 0)return EPFILTER;
return 0;
}
int isSIZEX (char *str){
char stag [] = "<sizeX>";
char etag [] = "</sizeX>";
if(strcmp(stag, str) == 0)return SIZEX;
if(strcmp(etag, str) == 0)return ESIZEX;
return 0;
}
int isSIZEY (char *str){
char stag [] = "<sizeY>";
char etag [] = "</sizeY>";
if(strcmp(stag, str) == 0)return SIZEY;
if(strcmp(etag, str) == 0)return ESIZEY;
return 0;
}
int isWEIGHTS (char *str){
char stag [] = "<Weights>";
char etag [] = "</Weights>";
if(strcmp(stag, str) == 0)return WEIGHTS;
if(strcmp(etag, str) == 0)return EWEIGHTS;
return 0;
}
int isV (char *str){
char stag [] = "<V>";
char etag [] = "</V>";
if(strcmp(stag, str) == 0)return TAGV;
if(strcmp(etag, str) == 0)return ETAGV;
return 0;
}
int isVx (char *str){
char stag [] = "<Vx>";
char etag [] = "</Vx>";
if(strcmp(stag, str) == 0)return Vx;
if(strcmp(etag, str) == 0)return EVx;
return 0;
}
int isVy (char *str){
char stag [] = "<Vy>";
char etag [] = "</Vy>";
if(strcmp(stag, str) == 0)return Vy;
if(strcmp(etag, str) == 0)return EVy;
return 0;
}
int isD (char *str){
char stag [] = "<Penalty>";
char etag [] = "</Penalty>";
if(strcmp(stag, str) == 0)return TAGD;
if(strcmp(etag, str) == 0)return ETAGD;
return 0;
}
int isDx (char *str){
char stag [] = "<dx>";
char etag [] = "</dx>";
if(strcmp(stag, str) == 0)return Dx;
if(strcmp(etag, str) == 0)return EDx;
return 0;
}
int isDy (char *str){
char stag [] = "<dy>";
char etag [] = "</dy>";
if(strcmp(stag, str) == 0)return Dy;
if(strcmp(etag, str) == 0)return EDy;
return 0;
}
int isDxx (char *str){
char stag [] = "<dxx>";
char etag [] = "</dxx>";
if(strcmp(stag, str) == 0)return Dxx;
if(strcmp(etag, str) == 0)return EDxx;
return 0;
}
int isDyy (char *str){
char stag [] = "<dyy>";
char etag [] = "</dyy>";
if(strcmp(stag, str) == 0)return Dyy;
if(strcmp(etag, str) == 0)return EDyy;
return 0;
}
int isB (char *str){
char stag [] = "<LinearTerm>";
char etag [] = "</LinearTerm>";
if(strcmp(stag, str) == 0)return BTAG;
if(strcmp(etag, str) == 0)return EBTAG;
return 0;
}
int getTeg(char *str){
int sum = 0;
sum = isMODEL (str)+
isP (str)+
isSCORE (str)+
isCOMP (str)+
isRFILTER (str)+
isPFILTERs (str)+
isPFILTER (str)+
isSIZEX (str)+
isSIZEY (str)+
isWEIGHTS (str)+
isV (str)+
isVx (str)+
isVy (str)+
isD (str)+
isDx (str)+
isDy (str)+
isDxx (str)+
isDyy (str)+
isB (str);
return sum;
}
void addFilter(filterObject *** model, int *last, int *max){
filterObject ** nmodel;
int i;
(*last) ++;
if((*last) >= (*max)){
(*max) += 10;
nmodel = (filterObject **)malloc(sizeof(filterObject *) * (*max));
for(i = 0; i < *last; i++){
nmodel[i] = (* model)[i];
}
free(* model);
(*model) = nmodel;
}
(*model) [(*last)] = (filterObject *)malloc(sizeof(filterObject));
}
void parserRFilter (FILE * xmlf, int p, filterObject * model, float *b){
int st = 0;
int sizeX, sizeY;
int tag;
int tagVal;
char ch;
int i,j,ii;
char buf[1024];
char tagBuf[1024];
double *data;
//printf("<RootFilter>\n");
model->V.x = 0;
model->V.y = 0;
model->V.l = 0;
model->fineFunction[0] = 0.0;
model->fineFunction[1] = 0.0;
model->fineFunction[2] = 0.0;
model->fineFunction[3] = 0.0;
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == ERFILTER){
//printf("</RootFilter>\n");
return;
}
if(tagVal == SIZEX){
st = 1;
i = 0;
}
if(tagVal == ESIZEX){
st = 0;
buf[i] = '\0';
sizeX = atoi(buf);
model->sizeX = sizeX;
//printf("<sizeX>%d</sizeX>\n", sizeX);
}
if(tagVal == SIZEY){
st = 1;
i = 0;
}
if(tagVal == ESIZEY){
st = 0;
buf[i] = '\0';
sizeY = atoi(buf);
model->sizeY = sizeY;
//printf("<sizeY>%d</sizeY>\n", sizeY);
}
if(tagVal == WEIGHTS){
data = (double *)malloc( sizeof(double) * p * sizeX * sizeY);
fread(data, sizeof(double), p * sizeX * sizeY, xmlf);
model->H = (float *)malloc(sizeof(float)* p * sizeX * sizeY);
for(ii = 0; ii < p * sizeX * sizeY; ii++){
model->H[ii] = (float)data[ii];
}
free(data);
}
if(tagVal == EWEIGHTS){
//printf("WEIGHTS OK\n");
}
if(tagVal == BTAG){
st = 1;
i = 0;
}
if(tagVal == EBTAG){
st = 0;
buf[i] = '\0';
*b =(float) atof(buf);
//printf("<B>%f</B>\n", *b);
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserV (FILE * xmlf, int p, filterObject * model){
int st = 0;
int tag;
int tagVal;
char ch;
int i,j;
char buf[1024];
char tagBuf[1024];
//printf(" <V>\n");
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == ETAGV){
//printf(" </V>\n");
return;
}
if(tagVal == Vx){
st = 1;
i = 0;
}
if(tagVal == EVx){
st = 0;
buf[i] = '\0';
model->V.x = atoi(buf);
//printf(" <Vx>%d</Vx>\n", model->V.x);
}
if(tagVal == Vy){
st = 1;
i = 0;
}
if(tagVal == EVy){
st = 0;
buf[i] = '\0';
model->V.y = atoi(buf);
//printf(" <Vy>%d</Vy>\n", model->V.y);
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserD (FILE * xmlf, int p, filterObject * model){
int st = 0;
int tag;
int tagVal;
char ch;
int i,j;
char buf[1024];
char tagBuf[1024];
//printf(" <D>\n");
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == ETAGD){
//printf(" </D>\n");
return;
}
if(tagVal == Dx){
st = 1;
i = 0;
}
if(tagVal == EDx){
st = 0;
buf[i] = '\0';
model->fineFunction[0] = (float)atof(buf);
//printf(" <Dx>%f</Dx>\n", model->fineFunction[0]);
}
if(tagVal == Dy){
st = 1;
i = 0;
}
if(tagVal == EDy){
st = 0;
buf[i] = '\0';
model->fineFunction[1] = (float)atof(buf);
//printf(" <Dy>%f</Dy>\n", model->fineFunction[1]);
}
if(tagVal == Dxx){
st = 1;
i = 0;
}
if(tagVal == EDxx){
st = 0;
buf[i] = '\0';
model->fineFunction[2] = (float)atof(buf);
//printf(" <Dxx>%f</Dxx>\n", model->fineFunction[2]);
}
if(tagVal == Dyy){
st = 1;
i = 0;
}
if(tagVal == EDyy){
st = 0;
buf[i] = '\0';
model->fineFunction[3] = (float)atof(buf);
//printf(" <Dyy>%f</Dyy>\n", model->fineFunction[3]);
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserPFilter (FILE * xmlf, int p, int N_path, filterObject * model){
int st = 0;
int sizeX, sizeY;
int tag;
int tagVal;
char ch;
int i,j, ii;
char buf[1024];
char tagBuf[1024];
double *data;
//printf("<PathFilter> (%d)\n", N_path);
model->V.x = 0;
model->V.y = 0;
model->V.l = 0;
model->fineFunction[0] = 0.0f;
model->fineFunction[1] = 0.0f;
model->fineFunction[2] = 0.0f;
model->fineFunction[3] = 0.0f;
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == EPFILTER){
//printf("</PathFilter>\n");
return;
}
if(tagVal == TAGV){
parserV(xmlf, p, model);
}
if(tagVal == TAGD){
parserD(xmlf, p, model);
}
if(tagVal == SIZEX){
st = 1;
i = 0;
}
if(tagVal == ESIZEX){
st = 0;
buf[i] = '\0';
sizeX = atoi(buf);
model->sizeX = sizeX;
//printf("<sizeX>%d</sizeX>\n", sizeX);
}
if(tagVal == SIZEY){
st = 1;
i = 0;
}
if(tagVal == ESIZEY){
st = 0;
buf[i] = '\0';
sizeY = atoi(buf);
model->sizeY = sizeY;
//printf("<sizeY>%d</sizeY>\n", sizeY);
}
if(tagVal == WEIGHTS){
data = (double *)malloc( sizeof(double) * p * sizeX * sizeY);
fread(data, sizeof(double), p * sizeX * sizeY, xmlf);
model->H = (float *)malloc(sizeof(float)* p * sizeX * sizeY);
for(ii = 0; ii < p * sizeX * sizeY; ii++){
model->H[ii] = (float)data[ii];
}
free(data);
}
if(tagVal == EWEIGHTS){
//printf("WEIGHTS OK\n");
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserPFilterS (FILE * xmlf, int p, filterObject *** model, int *last, int *max){
int st = 0;
int N_path = 0;
int tag;
int tagVal;
char ch;
int i,j;
char buf[1024];
char tagBuf[1024];
//printf("<PartFilters>\n");
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == EPFILTERs){
//printf("</PartFilters>\n");
return;
}
if(tagVal == PFILTER){
addFilter(model, last, max);
parserPFilter (xmlf, p, N_path, (*model)[*last]);
N_path++;
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserComp (FILE * xmlf, int p, int *N_comp, filterObject *** model, float *b, int *last, int *max){
int st = 0;
int tag;
int tagVal;
char ch;
int i,j;
char buf[1024];
char tagBuf[1024];
//printf("<Component> %d\n", *N_comp);
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == ECOMP){
(*N_comp) ++;
return;
}
if(tagVal == RFILTER){
addFilter(model, last, max);
parserRFilter (xmlf, p, (*model)[*last],b);
}
if(tagVal == PFILTERs){
parserPFilterS (xmlf, p, model, last, max);
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void parserModel(FILE * xmlf, filterObject *** model, int *last, int *max, int **comp, float **b, int *count, float * score){
int p = 0;
int N_comp = 0;
int * cmp;
float *bb;
int st = 0;
int tag;
int tagVal;
char ch;
int i,j, ii = 0;
char buf[1024];
char tagBuf[1024];
//printf("<Model>\n");
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
tagVal = getTeg(tagBuf);
if(tagVal == EMODEL){
//printf("</Model>\n");
for(ii = 0; ii <= *last; ii++){
(*model)[ii]->p = p;
(*model)[ii]->xp = 9;
}
* count = N_comp;
return;
}
if(tagVal == COMP){
if(N_comp == 0){
cmp = (int *)malloc(sizeof(int));
bb = (float *)malloc(sizeof(float));
* comp = cmp;
* b = bb;
* count = N_comp + 1;
} else {
cmp = (int *)malloc(sizeof(int) * (N_comp + 1));
bb = (float *)malloc(sizeof(float) * (N_comp + 1));
for(ii = 0; ii < N_comp; ii++){
cmp[i] = (* comp)[ii];
bb [i] = (* b )[ii];
}
free(* comp);
free(* b );
* comp = cmp;
* b = bb;
* count = N_comp + 1;
}
parserComp(xmlf, p, &N_comp, model, &((*b)[N_comp]), last, max);
cmp[N_comp - 1] = *last;
}
if(tagVal == P){
st = 1;
i = 0;
}
if(tagVal == EP){
st = 0;
buf[i] = '\0';
p = atoi(buf);
//printf("<P>%d</P>\n", p);
}
if(tagVal == SCORE){
st = 1;
i = 0;
}
if(tagVal == ESCORE){
st = 0;
buf[i] = '\0';
*score = (float)atof(buf);
//printf("<ScoreThreshold>%f</ScoreThreshold>\n", score);
}
tag = 0;
i = 0;
}else{
if((tag == 0)&& (st == 1)){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
void LSVMparser(const char * filename, filterObject *** model, int *last, int *max, int **comp, float **b, int *count, float * score){
int st = 0;
int tag;
char ch;
int i,j;
FILE *xmlf;
char buf[1024];
char tagBuf[1024];
(*max) = 10;
(*last) = -1;
(*model) = (filterObject ** )malloc((sizeof(filterObject * )) * (*max));
//printf("parse : %s\n", filename);
xmlf = fopen(filename, "rb");
i = 0;
j = 0;
st = 0;
tag = 0;
while(!feof(xmlf)){
ch = fgetc( xmlf );
if(ch == '<'){
tag = 1;
j = 1;
tagBuf[j - 1] = ch;
}else {
if(ch == '>'){
tag = 0;
i = 0;
tagBuf[j ] = ch;
tagBuf[j + 1] = '\0';
if(getTeg(tagBuf) == MODEL){
parserModel(xmlf, model, last, max, comp, b, count, score);
}
}else{
if(tag == 0){
buf[i] = ch; i++;
}else{
tagBuf[j] = ch; j++;
}
}
}
}
}
int loadModel(
// Âõîäíûå ïàðàìåòðû
const char *modelPath,// - ïóòü äî ôàéëà ñ ìîäåëüþ
// Âûõîäíûå ïàðàìåòðû
filterObject ***filters,// - ìàññèâ óêàçàòåëåé íà ôèëüòðû êîìïîíåíò
int *kFilters, //- îáùåå êîëè÷åñòâî ôèëüòðîâ âî âñåõ ìîäåëÿõ
int *kComponents, //- êîëè÷åñòâî êîìïîíåíò
int **kPartFilters, //- ìàññèâ, ñîäåðæàùèé êîëè÷åñòâî òî÷íûõ ôèëüòðîâ â êàæäîé êîìïîíåíòå
float **b, //- ìàññèâ ëèíåéíûõ ÷ëåíîâ â îöåíî÷íîé ôóíêöèè
float *scoreThreshold){ //- ïîðîã äëÿ score)
int last;
int max;
int *comp;
int count;
int i;
float score;
//printf("start_parse\n\n");
LSVMparser(modelPath, filters, &last, &max, &comp, b, &count, &score);
(*kFilters) = last + 1;
(*kComponents) = count;
(*scoreThreshold) = (float) score;
(*kPartFilters) = (int *)malloc(sizeof(int) * count);
for(i = 1; i < count;i++){
(*kPartFilters)[i] = (comp[i] - comp[i - 1]) - 1;
}
(*kPartFilters)[0] = comp[0];
//printf("end_parse\n");
return 0;
}

1462
modules/objdetect/src/matching.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

2
modules/objdetect/src/precomp.hpp
View File

@ -54,6 +54,8 @@
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/imgproc/imgproc_c.h"
#include "opencv2/core/core_c.h"
#include "opencv2/highgui/highgui_c.h"
#include "opencv2/core/internal.hpp"
#endif

244
modules/objdetect/src/resizeimg.cpp Normal file
View File

@ -0,0 +1,244 @@
#include "_resizeimg.h"
#include <stdio.h>
#include <assert.h>
#include <math.h>
IplImage * resize_opencv (IplImage * img, float scale){
IplImage * imgTmp;
int W, H, tW, tH;
W = img->width;
H = img->height;
tW = (int)(((float)W) * scale + 0.5);
tH = (int)(((float)H) * scale + 0.5);
imgTmp = cvCreateImage(cvSize(tW , tH), img->depth, img->nChannels);
cvResize(
img,
imgTmp,
CV_INTER_AREA
);
return imgTmp;
}
//
///*
// * Fast image subsampling.
// * This is used to construct the feature pyramid.
// */
//
//// struct used for caching interpolation values
//typedef struct {
// int si, di;
// float alpha;
//}alphainfo;
//
//// copy src into dst using pre-computed interpolation values
//void alphacopy(float *src, float *dst, alphainfo *ofs, int n) {
// int i;
// for(i = 0; i < n; i++){
// dst[ofs[i].di] += ofs[i].alpha * src[ofs[i].si];
// }
//}
//
//int round(float val){
// return (int)(val + 0.5);
//}
//void bzero(float * arr, int cnt){
// int i;
// for(i = 0; i < cnt; i++){
// arr[i] = 0.0f;
// }
//}
//// resize along each column
//// result is transposed, so we can apply it twice for a complete resize
//void resize1dtran(float *src, int sheight, float *dst, int dheight,
// int width, int chan) {
// alphainfo *ofs;
// float scale = (float)dheight/(float)sheight;
// float invscale = (float)sheight/(float)dheight;
//
// // we cache the interpolation values since they can be
// // shared among different columns
// int len = (int)ceilf(dheight*invscale) + 2*dheight;
// int k = 0;
// int dy;
// float fsy1;
// float fsy2;
// int sy1;
// int sy2;
// int sy;
// int c, x;
// float *s, *d;
//
// ofs = (alphainfo *) malloc (sizeof(alphainfo) * len);
// for (dy = 0; dy < dheight; dy++) {
// fsy1 = dy * invscale;
// fsy2 = fsy1 + invscale;
// sy1 = (int)ceilf(fsy1);
// sy2 = (int)floorf(fsy2);
//
// if (sy1 - fsy1 > 1e-3) {
// assert(k < len);
// assert(sy1 - 1 >= 0);
// ofs[k].di = dy*width;
// ofs[k].si = sy1-1;
// ofs[k++].alpha = (sy1 - fsy1) * scale;
// }
//
// for (sy = sy1; sy < sy2; sy++) {
// assert(k < len);
// assert(sy < sheight);
// ofs[k].di = dy*width;
// ofs[k].si = sy;
// ofs[k++].alpha = scale;
// }
//
// if (fsy2 - sy2 > 1e-3) {
// assert(k < len);
// assert(sy2 < sheight);
// ofs[k].di = dy*width;
// ofs[k].si = sy2;
// ofs[k++].alpha = (fsy2 - sy2) * scale;
// }
// }
//
// // resize each column of each color channel
// bzero(dst, chan*width*dheight);
// for (c = 0; c < chan; c++) {
// for (x = 0; x < width; x++) {
// s = src + c*width*sheight + x*sheight;
// d = dst + c*width*dheight + x;
// alphacopy(s, d, ofs, k);
// }
// }
// free(ofs);
//}
//
//IplImage * resize_article_dp(IplImage * img, float scale, const int k){
// IplImage * imgTmp;
// float W, H;
// unsigned char *dataSrc;
// float * dataf;
// float *src, *dst, *tmp;
// int i, j, kk, channels;
// int index;
// int widthStep;
// int tW, tH;
//
// W = (float)img->width;
// H = (float)img->height;
// channels = img->nChannels;
// widthStep = img->widthStep;
//
// tW = (int)(((float)W) * scale + 0.5f);
// tH = (int)(((float)H) * scale + 0.5f);
//
// src = (float *)malloc(sizeof(float) * (int)(W * H * 3));
//
// dataSrc = (unsigned char*)(img->imageData);
// index = 0;
// for (kk = 0; kk < channels; kk++)
// {
// for (i = 0; i < W; i++)
// {
// for (j = 0; j < H; j++)
// {
// src[index++] = (float)dataSrc[j * widthStep + i * channels + kk];
// }
// }
// }
//
// imgTmp = cvCreateImage(cvSize(tW , tH), IPL_DEPTH_32F, channels);
//
// dst = (float *)malloc(sizeof(float) * (int)(tH * tW) * channels);
// tmp = (float *)malloc(sizeof(float) * (int)(tH * W) * channels);
//
// resize1dtran(src, (int)H, tmp, (int)tH, (int)W , 3);
//
// resize1dtran(tmp, (int)W, dst, (int)tW, (int)tH, 3);
//
// index = 0;
// //dataf = (float*)imgTmp->imageData;
// for (kk = 0; kk < channels; kk++)
// {
// for (i = 0; i < tW; i++)
// {
// for (j = 0; j < tH; j++)
// {
// dataf = (float*)(imgTmp->imageData + j * imgTmp->widthStep);
// dataf[ i * channels + kk] = dst[index++];
// }
// }
// }
//
// free(src);
// free(dst);
// free(tmp);
// return imgTmp;
//}
//
//IplImage * resize_article_dp1(IplImage * img, float scale, const int k){
// IplImage * imgTmp;
// float W, H;
// float * dataf;
// float *src, *dst, *tmp;
// int i, j, kk, channels;
// int index;
// int widthStep;
// int tW, tH;
//
// W = (float)img->width;
// H = (float)img->height;
// channels = img->nChannels;
// widthStep = img->widthStep;
//
// tW = (int)(((float)W) * scale + 0.5f);
// tH = (int)(((float)H) * scale + 0.5f);
//
// src = (float *)malloc(sizeof(float) * (int)(W * H) * 3);
//
// index = 0;
// for (kk = 0; kk < channels; kk++)
// {
// for (i = 0; i < W; i++)
// {
// for (j = 0; j < H; j++)
// {
// src[index++] = (float)(*( (float *)(img->imageData + j * widthStep) + i * channels + kk));
// }
// }
// }
//
// imgTmp = cvCreateImage(cvSize(tW , tH), IPL_DEPTH_32F, channels);
//
// dst = (float *)malloc(sizeof(float) * (int)(tH * tW) * channels);
// tmp = (float *)malloc(sizeof(float) * (int)(tH * W) * channels);
//
// resize1dtran(src, (int)H, tmp, (int)tH, (int)W , 3);
//
// resize1dtran(tmp, (int)W, dst, (int)tW, (int)tH, 3);
//
// index = 0;
// for (kk = 0; kk < channels; kk++)
// {
// for (i = 0; i < tW; i++)
// {
// for (j = 0; j < tH; j++)
// {
// dataf = (float *)(imgTmp->imageData + j * imgTmp->widthStep);
// dataf[ i * channels + kk] = dst[index++];
// }
// }
// }
//
// free(src);
// free(dst);
// free(tmp);
// return imgTmp;
//}

103
modules/objdetect/src/routine.cpp Normal file
View File

@ -0,0 +1,103 @@
#include "_routine.h"
int allocFilterObject(filterObject **obj, const int sizeX, const int sizeY, const int p, const int xp){
int i;
(*obj) = (filterObject *)malloc(sizeof(filterObject));
(*obj)->sizeX = sizeX;
(*obj)->sizeY = sizeY;
(*obj)->p = p ;
(*obj)->xp = xp ;
(*obj)->fineFunction[0] = 0.0f;
(*obj)->fineFunction[1] = 0.0f;
(*obj)->fineFunction[2] = 0.0f;
(*obj)->fineFunction[3] = 0.0f;
(*obj)->V.x = 0;
(*obj)->V.y = 0;
(*obj)->V.l = 0;
(*obj)->H = (float *) malloc(sizeof (float) * (sizeX * sizeY * p));
for(i = 0; i < sizeX * sizeY * p; i++){
(*obj)->H[i] = 0.0f;
}
return LATENT_SVM_OK;
}
int freeFilterObject (filterObject **obj){
if(*obj == NULL) return 0;
free((*obj)->H);
free(*obj);
(*obj) = NULL;
return LATENT_SVM_OK;
}
int allocFeatureMapObject(featureMap **obj, const int sizeX, const int sizeY, const int p, const int xp){
int i;
(*obj) = (featureMap *)malloc(sizeof(featureMap));
(*obj)->sizeX = sizeX;
(*obj)->sizeY = sizeY;
(*obj)->p = p ;
(*obj)->xp = xp ;
(*obj)->Map = (float *) malloc(sizeof (float) * (sizeX * sizeY * p));
for(i = 0; i < sizeX * sizeY * p; i++){
(*obj)->Map[i] = 0.0;
}
return LATENT_SVM_OK;
}
int freeFeatureMapObject (featureMap **obj){
if(*obj == NULL) return 0;
free((*obj)->Map);
free(*obj);
(*obj) = NULL;
return LATENT_SVM_OK;
}
int allocFeaturePyramidObject(featurePyramid **obj, const int lambda, const int countLevel){
(*obj) = (featurePyramid *)malloc(sizeof(featurePyramid));
(*obj)->countLevel = countLevel;
(*obj)->pyramid = (featureMap **)malloc(sizeof(featureMap *) * countLevel);
(*obj)->lambda = lambda;
return LATENT_SVM_OK;
}
int freeFeaturePyramidObject (featurePyramid **obj){
int i;
if(*obj == NULL) return 0;
for(i = 0; i < (*obj)->countLevel; i++)
freeFeatureMapObject(&((*obj)->pyramid[i]));
free((*obj)->pyramid);
free(*obj);
(*obj) = NULL;
return LATENT_SVM_OK;
}
int allocFFTImage(fftImage **image, int p, int dimX, int dimY)
{
int i, j, size;
*image = (fftImage *)malloc(sizeof(fftImage));
(*image)->p = p;
(*image)->dimX = dimX;
(*image)->dimY = dimY;
(*image)->channels = (float **)malloc(sizeof(float *) * p);
size = 2 * dimX * dimY;
for (i = 0; i < p; i++)
{
(*image)->channels[i] = (float *)malloc(sizeof(float) * size);
for (j = 0; j < size; j++)
{
(*image)->channels[i][j] = 0.0;
}
}
return LATENT_SVM_OK;
}
int freeFFTImage(fftImage **image)
{
unsigned int i;
if (*image == NULL) return LATENT_SVM_OK;
for (i = 0; i < (*image)->p; i++)
{
free((*image)->channels[i]);
(*image)->channels[i] = NULL;
}
free((*image)->channels);
(*image)->channels = NULL;
return LATENT_SVM_OK;
}

BIN
samples/c/000028.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 64 KiB

BIN
samples/c/cat.xml Normal file
View File

Binary file not shown.

49
samples/c/latentsvmdetect.cpp Normal file
View File

@ -0,0 +1,49 @@
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/core/core_c.h"
#include "opencv2/highgui/highgui_c.h"
#include <stdio.h>
using namespace cv;
const char* model_filename = "cat.xml";
const char* image_filename = "000028.jpg";
void detect_and_draw_objects( IplImage* image, CvLatentSvmDetector* detector)
{
CvMemStorage* storage = cvCreateMemStorage(0);
CvSeq* detections = 0;
int i = 0;
int64 start = 0, finish = 0;
start = cvGetTickCount();
detections = cvLatentSvmDetectObjects(image, detector, storage);
finish = cvGetTickCount();
printf("detection time = %.3f\n", (float)(finish - start) / (float)(cvGetTickFrequency() * 1000000.0));
for( i = 0; i < detections->total; i++ )
{
CvObjectDetection detection = *(CvObjectDetection*)cvGetSeqElem( detections, i );
CvRect bounding_box = detection.rect;
cvRectangle( image, cvPoint(bounding_box.x, bounding_box.y),
cvPoint(bounding_box.x + bounding_box.width,
bounding_box.y + bounding_box.height),
CV_RGB(255,0,0), 3 );
}
cvReleaseMemStorage( &storage );
}
int main(int argc, char* argv[])
{
IplImage* image = cvLoadImage(image_filename);
CvLatentSvmDetector* detector = cvLoadLatentSvmDetector(model_filename);
detect_and_draw_objects( image, detector );
cvNamedWindow( "test", 0 );
cvShowImage( "test", image );
cvWaitKey(0);
cvReleaseLatentSvmDetector( &detector );
cvReleaseImage( &image );
cvDestroyAllWindows();
return 0;
}