mirror of https://github.com/opencv/opencv.git
Merge pull request #803 from taka-no-me:split_c_cpp3
Andrey Kamaev
12 years ago
committed by
OpenCV Buildbot
commit
b0933dd473
181 changed files with 2363 additions and 2205 deletions
@ -0,0 +1,413 @@ |
||||
/*M///////////////////////////////////////////////////////////////////////////////////////
|
||||
//
|
||||
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
|
||||
//
|
||||
// By downloading, copying, installing or using the software you agree to this license.
|
||||
// If you do not agree to this license, do not download, install,
|
||||
// copy or use the software.
|
||||
//
|
||||
//
|
||||
// License Agreement
|
||||
// For Open Source Computer Vision Library
|
||||
//
|
||||
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
|
||||
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
|
||||
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
|
||||
// Third party copyrights are property of their respective owners.
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without modification,
|
||||
// are permitted provided that the following conditions are met:
|
||||
//
|
||||
// * Redistribution's of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
//
|
||||
// * Redistribution's in binary form must reproduce the above copyright notice,
|
||||
// this list of conditions and the following disclaimer in the documentation
|
||||
// and/or other materials provided with the distribution.
|
||||
//
|
||||
// * The name of the copyright holders may not be used to endorse or promote products
|
||||
// derived from this software without specific prior written permission.
|
||||
//
|
||||
// This software is provided by the copyright holders and contributors "as is" and
|
||||
// any express or implied warranties, including, but not limited to, the implied
|
||||
// warranties of merchantability and fitness for a particular purpose are disclaimed.
|
||||
// In no event shall the Intel Corporation or contributors be liable for any direct,
|
||||
// indirect, incidental, special, exemplary, or consequential damages
|
||||
// (including, but not limited to, procurement of substitute goods or services;
|
||||
// loss of use, data, or profits; or business interruption) however caused
|
||||
// and on any theory of liability, whether in contract, strict liability,
|
||||
// or tort (including negligence or otherwise) arising in any way out of
|
||||
// the use of this software, even if advised of the possibility of such damage.
|
||||
//
|
||||
//M*/
|
||||
|
||||
#ifndef __OPENCV_CALIB3D_C_H__ |
||||
#define __OPENCV_CALIB3D_C_H__ |
||||
|
||||
#include "opencv2/core/core_c.h" |
||||
|
||||
#ifdef __cplusplus |
||||
extern "C" { |
||||
#endif |
||||
|
||||
/****************************************************************************************\
|
||||
* Camera Calibration, Pose Estimation and Stereo * |
||||
\****************************************************************************************/ |
||||
|
||||
typedef struct CvPOSITObject CvPOSITObject; |
||||
|
||||
/* Allocates and initializes CvPOSITObject structure before doing cvPOSIT */ |
||||
CVAPI(CvPOSITObject*) cvCreatePOSITObject( CvPoint3D32f* points, int point_count ); |
||||
|
||||
|
||||
/* Runs POSIT (POSe from ITeration) algorithm for determining 3d position of
|
||||
an object given its model and projection in a weak-perspective case */ |
||||
CVAPI(void) cvPOSIT( CvPOSITObject* posit_object, CvPoint2D32f* image_points, |
||||
double focal_length, CvTermCriteria criteria, |
||||
float* rotation_matrix, float* translation_vector); |
||||
|
||||
/* Releases CvPOSITObject structure */ |
||||
CVAPI(void) cvReleasePOSITObject( CvPOSITObject** posit_object ); |
||||
|
||||
/* updates the number of RANSAC iterations */ |
||||
CVAPI(int) cvRANSACUpdateNumIters( double p, double err_prob, |
||||
int model_points, int max_iters ); |
||||
|
||||
CVAPI(void) cvConvertPointsHomogeneous( const CvMat* src, CvMat* dst ); |
||||
|
||||
/* Calculates fundamental matrix given a set of corresponding points */ |
||||
#define CV_FM_7POINT 1 |
||||
#define CV_FM_8POINT 2 |
||||
|
||||
#define CV_LMEDS 4 |
||||
#define CV_RANSAC 8 |
||||
|
||||
#define CV_FM_LMEDS_ONLY CV_LMEDS |
||||
#define CV_FM_RANSAC_ONLY CV_RANSAC |
||||
#define CV_FM_LMEDS CV_LMEDS |
||||
#define CV_FM_RANSAC CV_RANSAC |
||||
|
||||
enum |
||||
{ |
||||
CV_ITERATIVE = 0, |
||||
CV_EPNP = 1, // F.Moreno-Noguer, V.Lepetit and P.Fua "EPnP: Efficient Perspective-n-Point Camera Pose Estimation"
|
||||
CV_P3P = 2 // X.S. Gao, X.-R. Hou, J. Tang, H.-F. Chang; "Complete Solution Classification for the Perspective-Three-Point Problem"
|
||||
}; |
||||
|
||||
CVAPI(int) cvFindFundamentalMat( const CvMat* points1, const CvMat* points2, |
||||
CvMat* fundamental_matrix, |
||||
int method CV_DEFAULT(CV_FM_RANSAC), |
||||
double param1 CV_DEFAULT(3.), double param2 CV_DEFAULT(0.99), |
||||
CvMat* status CV_DEFAULT(NULL) ); |
||||
|
||||
/* For each input point on one of images
|
||||
computes parameters of the corresponding |
||||
epipolar line on the other image */ |
||||
CVAPI(void) cvComputeCorrespondEpilines( const CvMat* points, |
||||
int which_image, |
||||
const CvMat* fundamental_matrix, |
||||
CvMat* correspondent_lines ); |
||||
|
||||
/* Triangulation functions */ |
||||
|
||||
CVAPI(void) cvTriangulatePoints(CvMat* projMatr1, CvMat* projMatr2, |
||||
CvMat* projPoints1, CvMat* projPoints2, |
||||
CvMat* points4D); |
||||
|
||||
CVAPI(void) cvCorrectMatches(CvMat* F, CvMat* points1, CvMat* points2, |
||||
CvMat* new_points1, CvMat* new_points2); |
||||
|
||||
|
||||
/* Computes the optimal new camera matrix according to the free scaling parameter alpha:
|
||||
alpha=0 - only valid pixels will be retained in the undistorted image |
||||
alpha=1 - all the source image pixels will be retained in the undistorted image |
||||
*/ |
||||
CVAPI(void) cvGetOptimalNewCameraMatrix( const CvMat* camera_matrix, |
||||
const CvMat* dist_coeffs, |
||||
CvSize image_size, double alpha, |
||||
CvMat* new_camera_matrix, |
||||
CvSize new_imag_size CV_DEFAULT(cvSize(0,0)), |
||||
CvRect* valid_pixel_ROI CV_DEFAULT(0), |
||||
int center_principal_point CV_DEFAULT(0)); |
||||
|
||||
/* Converts rotation vector to rotation matrix or vice versa */ |
||||
CVAPI(int) cvRodrigues2( const CvMat* src, CvMat* dst, |
||||
CvMat* jacobian CV_DEFAULT(0) ); |
||||
|
||||
/* Finds perspective transformation between the object plane and image (view) plane */ |
||||
CVAPI(int) cvFindHomography( const CvMat* src_points, |
||||
const CvMat* dst_points, |
||||
CvMat* homography, |
||||
int method CV_DEFAULT(0), |
||||
double ransacReprojThreshold CV_DEFAULT(3), |
||||
CvMat* mask CV_DEFAULT(0)); |
||||
|
||||
/* Computes RQ decomposition for 3x3 matrices */ |
||||
CVAPI(void) cvRQDecomp3x3( const CvMat *matrixM, CvMat *matrixR, CvMat *matrixQ, |
||||
CvMat *matrixQx CV_DEFAULT(NULL), |
||||
CvMat *matrixQy CV_DEFAULT(NULL), |
||||
CvMat *matrixQz CV_DEFAULT(NULL), |
||||
CvPoint3D64f *eulerAngles CV_DEFAULT(NULL)); |
||||
|
||||
/* Computes projection matrix decomposition */ |
||||
CVAPI(void) cvDecomposeProjectionMatrix( const CvMat *projMatr, CvMat *calibMatr, |
||||
CvMat *rotMatr, CvMat *posVect, |
||||
CvMat *rotMatrX CV_DEFAULT(NULL), |
||||
CvMat *rotMatrY CV_DEFAULT(NULL), |
||||
CvMat *rotMatrZ CV_DEFAULT(NULL), |
||||
CvPoint3D64f *eulerAngles CV_DEFAULT(NULL)); |
||||
|
||||
/* Computes d(AB)/dA and d(AB)/dB */ |
||||
CVAPI(void) cvCalcMatMulDeriv( const CvMat* A, const CvMat* B, CvMat* dABdA, CvMat* dABdB ); |
||||
|
||||
/* Computes r3 = rodrigues(rodrigues(r2)*rodrigues(r1)),
|
||||
t3 = rodrigues(r2)*t1 + t2 and the respective derivatives */ |
||||
CVAPI(void) cvComposeRT( const CvMat* _rvec1, const CvMat* _tvec1, |
||||
const CvMat* _rvec2, const CvMat* _tvec2, |
||||
CvMat* _rvec3, CvMat* _tvec3, |
||||
CvMat* dr3dr1 CV_DEFAULT(0), CvMat* dr3dt1 CV_DEFAULT(0), |
||||
CvMat* dr3dr2 CV_DEFAULT(0), CvMat* dr3dt2 CV_DEFAULT(0), |
||||
CvMat* dt3dr1 CV_DEFAULT(0), CvMat* dt3dt1 CV_DEFAULT(0), |
||||
CvMat* dt3dr2 CV_DEFAULT(0), CvMat* dt3dt2 CV_DEFAULT(0) ); |
||||
|
||||
/* Projects object points to the view plane using
|
||||
the specified extrinsic and intrinsic camera parameters */ |
||||
CVAPI(void) cvProjectPoints2( const CvMat* object_points, const CvMat* rotation_vector, |
||||
const CvMat* translation_vector, const CvMat* camera_matrix, |
||||
const CvMat* distortion_coeffs, CvMat* image_points, |
||||
CvMat* dpdrot CV_DEFAULT(NULL), CvMat* dpdt CV_DEFAULT(NULL), |
||||
CvMat* dpdf CV_DEFAULT(NULL), CvMat* dpdc CV_DEFAULT(NULL), |
||||
CvMat* dpddist CV_DEFAULT(NULL), |
||||
double aspect_ratio CV_DEFAULT(0)); |
||||
|
||||
/* Finds extrinsic camera parameters from
|
||||
a few known corresponding point pairs and intrinsic parameters */ |
||||
CVAPI(void) cvFindExtrinsicCameraParams2( const CvMat* object_points, |
||||
const CvMat* image_points, |
||||
const CvMat* camera_matrix, |
||||
const CvMat* distortion_coeffs, |
||||
CvMat* rotation_vector, |
||||
CvMat* translation_vector, |
||||
int use_extrinsic_guess CV_DEFAULT(0) ); |
||||
|
||||
/* Computes initial estimate of the intrinsic camera parameters
|
||||
in case of planar calibration target (e.g. chessboard) */ |
||||
CVAPI(void) cvInitIntrinsicParams2D( const CvMat* object_points, |
||||
const CvMat* image_points, |
||||
const CvMat* npoints, CvSize image_size, |
||||
CvMat* camera_matrix, |
||||
double aspect_ratio CV_DEFAULT(1.) ); |
||||
|
||||
#define CV_CALIB_CB_ADAPTIVE_THRESH 1 |
||||
#define CV_CALIB_CB_NORMALIZE_IMAGE 2 |
||||
#define CV_CALIB_CB_FILTER_QUADS 4 |
||||
#define CV_CALIB_CB_FAST_CHECK 8 |
||||
|
||||
// Performs a fast check if a chessboard is in the input image. This is a workaround to
|
||||
// a problem of cvFindChessboardCorners being slow on images with no chessboard
|
||||
// - src: input image
|
||||
// - size: chessboard size
|
||||
// Returns 1 if a chessboard can be in this image and findChessboardCorners should be called,
|
||||
// 0 if there is no chessboard, -1 in case of error
|
||||
CVAPI(int) cvCheckChessboard(IplImage* src, CvSize size); |
||||
|
||||
/* Detects corners on a chessboard calibration pattern */ |
||||
CVAPI(int) cvFindChessboardCorners( const void* image, CvSize pattern_size, |
||||
CvPoint2D32f* corners, |
||||
int* corner_count CV_DEFAULT(NULL), |
||||
int flags CV_DEFAULT(CV_CALIB_CB_ADAPTIVE_THRESH+CV_CALIB_CB_NORMALIZE_IMAGE) ); |
||||
|
||||
/* Draws individual chessboard corners or the whole chessboard detected */ |
||||
CVAPI(void) cvDrawChessboardCorners( CvArr* image, CvSize pattern_size, |
||||
CvPoint2D32f* corners, |
||||
int count, int pattern_was_found ); |
||||
|
||||
#define CV_CALIB_USE_INTRINSIC_GUESS 1 |
||||
#define CV_CALIB_FIX_ASPECT_RATIO 2 |
||||
#define CV_CALIB_FIX_PRINCIPAL_POINT 4 |
||||
#define CV_CALIB_ZERO_TANGENT_DIST 8 |
||||
#define CV_CALIB_FIX_FOCAL_LENGTH 16 |
||||
#define CV_CALIB_FIX_K1 32 |
||||
#define CV_CALIB_FIX_K2 64 |
||||
#define CV_CALIB_FIX_K3 128 |
||||
#define CV_CALIB_FIX_K4 2048 |
||||
#define CV_CALIB_FIX_K5 4096 |
||||
#define CV_CALIB_FIX_K6 8192 |
||||
#define CV_CALIB_RATIONAL_MODEL 16384 |
||||
#define CV_CALIB_THIN_PRISM_MODEL 32768 |
||||
#define CV_CALIB_FIX_S1_S2_S3_S4 65536 |
||||
|
||||
|
||||
/* Finds intrinsic and extrinsic camera parameters
|
||||
from a few views of known calibration pattern */ |
||||
CVAPI(double) cvCalibrateCamera2( const CvMat* object_points, |
||||
const CvMat* image_points, |
||||
const CvMat* point_counts, |
||||
CvSize image_size, |
||||
CvMat* camera_matrix, |
||||
CvMat* distortion_coeffs, |
||||
CvMat* rotation_vectors CV_DEFAULT(NULL), |
||||
CvMat* translation_vectors CV_DEFAULT(NULL), |
||||
int flags CV_DEFAULT(0), |
||||
CvTermCriteria term_crit CV_DEFAULT(cvTermCriteria( |
||||
CV_TERMCRIT_ITER+CV_TERMCRIT_EPS,30,DBL_EPSILON)) ); |
||||
|
||||
/* Computes various useful characteristics of the camera from the data computed by
|
||||
cvCalibrateCamera2 */ |
||||
CVAPI(void) cvCalibrationMatrixValues( const CvMat *camera_matrix, |
||||
CvSize image_size, |
||||
double aperture_width CV_DEFAULT(0), |
||||
double aperture_height CV_DEFAULT(0), |
||||
double *fovx CV_DEFAULT(NULL), |
||||
double *fovy CV_DEFAULT(NULL), |
||||
double *focal_length CV_DEFAULT(NULL), |
||||
CvPoint2D64f *principal_point CV_DEFAULT(NULL), |
||||
double *pixel_aspect_ratio CV_DEFAULT(NULL)); |
||||
|
||||
#define CV_CALIB_FIX_INTRINSIC 256 |
||||
#define CV_CALIB_SAME_FOCAL_LENGTH 512 |
||||
|
||||
/* Computes the transformation from one camera coordinate system to another one
|
||||
from a few correspondent views of the same calibration target. Optionally, calibrates |
||||
both cameras */ |
||||
CVAPI(double) cvStereoCalibrate( const CvMat* object_points, const CvMat* image_points1, |
||||
const CvMat* image_points2, const CvMat* npoints, |
||||
CvMat* camera_matrix1, CvMat* dist_coeffs1, |
||||
CvMat* camera_matrix2, CvMat* dist_coeffs2, |
||||
CvSize image_size, CvMat* R, CvMat* T, |
||||
CvMat* E CV_DEFAULT(0), CvMat* F CV_DEFAULT(0), |
||||
CvTermCriteria term_crit CV_DEFAULT(cvTermCriteria( |
||||
CV_TERMCRIT_ITER+CV_TERMCRIT_EPS,30,1e-6)), |
||||
int flags CV_DEFAULT(CV_CALIB_FIX_INTRINSIC)); |
||||
|
||||
#define CV_CALIB_ZERO_DISPARITY 1024 |
||||
|
||||
/* Computes 3D rotations (+ optional shift) for each camera coordinate system to make both
|
||||
views parallel (=> to make all the epipolar lines horizontal or vertical) */ |
||||
CVAPI(void) cvStereoRectify( const CvMat* camera_matrix1, const CvMat* camera_matrix2, |
||||
const CvMat* dist_coeffs1, const CvMat* dist_coeffs2, |
||||
CvSize image_size, const CvMat* R, const CvMat* T, |
||||
CvMat* R1, CvMat* R2, CvMat* P1, CvMat* P2, |
||||
CvMat* Q CV_DEFAULT(0), |
||||
int flags CV_DEFAULT(CV_CALIB_ZERO_DISPARITY), |
||||
double alpha CV_DEFAULT(-1), |
||||
CvSize new_image_size CV_DEFAULT(cvSize(0,0)), |
||||
CvRect* valid_pix_ROI1 CV_DEFAULT(0), |
||||
CvRect* valid_pix_ROI2 CV_DEFAULT(0)); |
||||
|
||||
/* Computes rectification transformations for uncalibrated pair of images using a set
|
||||
of point correspondences */ |
||||
CVAPI(int) cvStereoRectifyUncalibrated( const CvMat* points1, const CvMat* points2, |
||||
const CvMat* F, CvSize img_size, |
||||
CvMat* H1, CvMat* H2, |
||||
double threshold CV_DEFAULT(5)); |
||||
|
||||
|
||||
|
||||
/* stereo correspondence parameters and functions */ |
||||
|
||||
#define CV_STEREO_BM_NORMALIZED_RESPONSE 0 |
||||
#define CV_STEREO_BM_XSOBEL 1 |
||||
|
||||
/* Block matching algorithm structure */ |
||||
typedef struct CvStereoBMState |
||||
{ |
||||
// pre-filtering (normalization of input images)
|
||||
int preFilterType; // =CV_STEREO_BM_NORMALIZED_RESPONSE now
|
||||
int preFilterSize; // averaging window size: ~5x5..21x21
|
||||
int preFilterCap; // the output of pre-filtering is clipped by [-preFilterCap,preFilterCap]
|
||||
|
||||
// correspondence using Sum of Absolute Difference (SAD)
|
||||
int SADWindowSize; // ~5x5..21x21
|
||||
int minDisparity; // minimum disparity (can be negative)
|
||||
int numberOfDisparities; // maximum disparity - minimum disparity (> 0)
|
||||
|
||||
// post-filtering
|
||||
int textureThreshold; // the disparity is only computed for pixels
|
||||
// with textured enough neighborhood
|
||||
int uniquenessRatio; // accept the computed disparity d* only if
|
||||
// SAD(d) >= SAD(d*)*(1 + uniquenessRatio/100.)
|
||||
// for any d != d*+/-1 within the search range.
|
||||
int speckleWindowSize; // disparity variation window
|
||||
int speckleRange; // acceptable range of variation in window
|
||||
|
||||
int trySmallerWindows; // if 1, the results may be more accurate,
|
||||
// at the expense of slower processing
|
||||
CvRect roi1, roi2; |
||||
int disp12MaxDiff; |
||||
|
||||
// temporary buffers
|
||||
CvMat* preFilteredImg0; |
||||
CvMat* preFilteredImg1; |
||||
CvMat* slidingSumBuf; |
||||
CvMat* cost; |
||||
CvMat* disp; |
||||
} CvStereoBMState; |
||||
|
||||
#define CV_STEREO_BM_BASIC 0 |
||||
#define CV_STEREO_BM_FISH_EYE 1 |
||||
#define CV_STEREO_BM_NARROW 2 |
||||
|
||||
CVAPI(CvStereoBMState*) cvCreateStereoBMState(int preset CV_DEFAULT(CV_STEREO_BM_BASIC), |
||||
int numberOfDisparities CV_DEFAULT(0)); |
||||
|
||||
CVAPI(void) cvReleaseStereoBMState( CvStereoBMState** state ); |
||||
|
||||
CVAPI(void) cvFindStereoCorrespondenceBM( const CvArr* left, const CvArr* right, |
||||
CvArr* disparity, CvStereoBMState* state ); |
||||
|
||||
CVAPI(CvRect) cvGetValidDisparityROI( CvRect roi1, CvRect roi2, int minDisparity, |
||||
int numberOfDisparities, int SADWindowSize ); |
||||
|
||||
CVAPI(void) cvValidateDisparity( CvArr* disparity, const CvArr* cost, |
||||
int minDisparity, int numberOfDisparities, |
||||
int disp12MaxDiff CV_DEFAULT(1) ); |
||||
|
||||
/* Reprojects the computed disparity image to the 3D space using the specified 4x4 matrix */ |
||||
CVAPI(void) cvReprojectImageTo3D( const CvArr* disparityImage, |
||||
CvArr* _3dImage, const CvMat* Q, |
||||
int handleMissingValues CV_DEFAULT(0) ); |
||||
|
||||
#ifdef __cplusplus |
||||
} // extern "C"
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////////////////////
|
||||
class CV_EXPORTS CvLevMarq |
||||
{ |
||||
public: |
||||
CvLevMarq(); |
||||
CvLevMarq( int nparams, int nerrs, CvTermCriteria criteria= |
||||
cvTermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER,30,DBL_EPSILON), |
||||
bool completeSymmFlag=false ); |
||||
~CvLevMarq(); |
||||
void init( int nparams, int nerrs, CvTermCriteria criteria= |
||||
cvTermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER,30,DBL_EPSILON), |
||||
bool completeSymmFlag=false ); |
||||
bool update( const CvMat*& param, CvMat*& J, CvMat*& err ); |
||||
bool updateAlt( const CvMat*& param, CvMat*& JtJ, CvMat*& JtErr, double*& errNorm ); |
||||
|
||||
void clear(); |
||||
void step(); |
||||
enum { DONE=0, STARTED=1, CALC_J=2, CHECK_ERR=3 }; |
||||
|
||||
cv::Ptr<CvMat> mask; |
||||
cv::Ptr<CvMat> prevParam; |
||||
cv::Ptr<CvMat> param; |
||||
cv::Ptr<CvMat> J; |
||||
cv::Ptr<CvMat> err; |
||||
cv::Ptr<CvMat> JtJ; |
||||
cv::Ptr<CvMat> JtJN; |
||||
cv::Ptr<CvMat> JtErr; |
||||
cv::Ptr<CvMat> JtJV; |
||||
cv::Ptr<CvMat> JtJW; |
||||
double prevErrNorm, errNorm; |
||||
int lambdaLg10; |
||||
CvTermCriteria criteria; |
||||
int state; |
||||
int iters; |
||||
bool completeSymmFlag; |
||||
}; |
||||
|
||||
#endif |
||||
|
||||
#endif /* __OPENCV_CALIB3D_C_H__ */ |
||||
@ -0,0 +1,455 @@ |
||||
/*M///////////////////////////////////////////////////////////////////////////////////////
|
||||
//
|
||||
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
|
||||
//
|
||||
// By downloading, copying, installing or using the software you agree to this license.
|
||||
// If you do not agree to this license, do not download, install,
|
||||
// copy or use the software.
|
||||
//
|
||||
//
|
||||
// License Agreement
|
||||
// For Open Source Computer Vision Library
|
||||
//
|
||||
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
|
||||
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
|
||||
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
|
||||
// Third party copyrights are property of their respective owners.
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without modification,
|
||||
// are permitted provided that the following conditions are met:
|
||||
//
|
||||
// * Redistribution's of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
//
|
||||
// * Redistribution's in binary form must reproduce the above copyright notice,
|
||||
// this list of conditions and the following disclaimer in the documentation
|
||||
// and/or other materials provided with the distribution.
|
||||
//
|
||||
// * The name of the copyright holders may not be used to endorse or promote products
|
||||
// derived from this software without specific prior written permission.
|
||||
//
|
||||
// This software is provided by the copyright holders and contributors "as is" and
|
||||
// any express or implied warranties, including, but not limited to, the implied
|
||||
// warranties of merchantability and fitness for a particular purpose are disclaimed.
|
||||
// In no event shall the Intel Corporation or contributors be liable for any direct,
|
||||
// indirect, incidental, special, exemplary, or consequential damages
|
||||
// (including, but not limited to, procurement of substitute goods or services;
|
||||
// loss of use, data, or profits; or business interruption) however caused
|
||||
// and on any theory of liability, whether in contract, strict liability,
|
||||
// or tort (including negligence or otherwise) arising in any way out of
|
||||
// the use of this software, even if advised of the possibility of such damage.
|
||||
//
|
||||
//M*/
|
||||
|
||||
#ifndef __OPENCV_OBJDETECT_LINEMOD_HPP__ |
||||
#define __OPENCV_OBJDETECT_LINEMOD_HPP__ |
||||
|
||||
#include "opencv2/core.hpp" |
||||
#include <map> |
||||
|
||||
/****************************************************************************************\
|
||||
* LINE-MOD * |
||||
\****************************************************************************************/ |
||||
|
||||
namespace cv { |
||||
namespace linemod { |
||||
|
||||
/// @todo Convert doxy comments to rst
|
||||
|
||||
/**
|
||||
* \brief Discriminant feature described by its location and label. |
||||
*/ |
||||
struct CV_EXPORTS Feature |
||||
{ |
||||
int x; ///< x offset
|
||||
int y; ///< y offset
|
||||
int label; ///< Quantization
|
||||
|
||||
Feature() : x(0), y(0), label(0) {} |
||||
Feature(int x, int y, int label); |
||||
|
||||
void read(const FileNode& fn); |
||||
void write(FileStorage& fs) const; |
||||
}; |
||||
|
||||
inline Feature::Feature(int _x, int _y, int _label) : x(_x), y(_y), label(_label) {} |
||||
|
||||
struct CV_EXPORTS Template |
||||
{ |
||||
int width; |
||||
int height; |
||||
int pyramid_level; |
||||
std::vector<Feature> features; |
||||
|
||||
void read(const FileNode& fn); |
||||
void write(FileStorage& fs) const; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Represents a modality operating over an image pyramid. |
||||
*/ |
||||
class QuantizedPyramid |
||||
{ |
||||
public: |
||||
// Virtual destructor
|
||||
virtual ~QuantizedPyramid() {} |
||||
|
||||
/**
|
||||
* \brief Compute quantized image at current pyramid level for online detection. |
||||
* |
||||
* \param[out] dst The destination 8-bit image. For each pixel at most one bit is set, |
||||
* representing its classification. |
||||
*/ |
||||
virtual void quantize(Mat& dst) const =0; |
||||
|
||||
/**
|
||||
* \brief Extract most discriminant features at current pyramid level to form a new template. |
||||
* |
||||
* \param[out] templ The new template. |
||||
*/ |
||||
virtual bool extractTemplate(Template& templ) const =0; |
||||
|
||||
/**
|
||||
* \brief Go to the next pyramid level. |
||||
* |
||||
* \todo Allow pyramid scale factor other than 2 |
||||
*/ |
||||
virtual void pyrDown() =0; |
||||
|
||||
protected: |
||||
/// Candidate feature with a score
|
||||
struct Candidate |
||||
{ |
||||
Candidate(int x, int y, int label, float score); |
||||
|
||||
/// Sort candidates with high score to the front
|
||||
bool operator<(const Candidate& rhs) const |
||||
{ |
||||
return score > rhs.score; |
||||
} |
||||
|
||||
Feature f; |
||||
float score; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Choose candidate features so that they are not bunched together. |
||||
* |
||||
* \param[in] candidates Candidate features sorted by score. |
||||
* \param[out] features Destination vector of selected features. |
||||
* \param[in] num_features Number of candidates to select. |
||||
* \param[in] distance Hint for desired distance between features. |
||||
*/ |
||||
static void selectScatteredFeatures(const std::vector<Candidate>& candidates, |
||||
std::vector<Feature>& features, |
||||
size_t num_features, float distance); |
||||
}; |
||||
|
||||
inline QuantizedPyramid::Candidate::Candidate(int x, int y, int label, float _score) : f(x, y, label), score(_score) {} |
||||
|
||||
/**
|
||||
* \brief Interface for modalities that plug into the LINE template matching representation. |
||||
* |
||||
* \todo Max response, to allow optimization of summing (255/MAX) features as uint8 |
||||
*/ |
||||
class CV_EXPORTS Modality |
||||
{ |
||||
public: |
||||
// Virtual destructor
|
||||
virtual ~Modality() {} |
||||
|
||||
/**
|
||||
* \brief Form a quantized image pyramid from a source image. |
||||
* |
||||
* \param[in] src The source image. Type depends on the modality. |
||||
* \param[in] mask Optional mask. If not empty, unmasked pixels are set to zero |
||||
* in quantized image and cannot be extracted as features. |
||||
*/ |
||||
Ptr<QuantizedPyramid> process(const Mat& src, |
||||
const Mat& mask = Mat()) const |
||||
{ |
||||
return processImpl(src, mask); |
||||
} |
||||
|
||||
virtual String name() const =0; |
||||
|
||||
virtual void read(const FileNode& fn) =0; |
||||
virtual void write(FileStorage& fs) const =0; |
||||
|
||||
/**
|
||||
* \brief Create modality by name. |
||||
* |
||||
* The following modality types are supported: |
||||
* - "ColorGradient" |
||||
* - "DepthNormal" |
||||
*/ |
||||
static Ptr<Modality> create(const String& modality_type); |
||||
|
||||
/**
|
||||
* \brief Load a modality from file. |
||||
*/ |
||||
static Ptr<Modality> create(const FileNode& fn); |
||||
|
||||
protected: |
||||
// Indirection is because process() has a default parameter.
|
||||
virtual Ptr<QuantizedPyramid> processImpl(const Mat& src, |
||||
const Mat& mask) const =0; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Modality that computes quantized gradient orientations from a color image. |
||||
*/ |
||||
class CV_EXPORTS ColorGradient : public Modality |
||||
{ |
||||
public: |
||||
/**
|
||||
* \brief Default constructor. Uses reasonable default parameter values. |
||||
*/ |
||||
ColorGradient(); |
||||
|
||||
/**
|
||||
* \brief Constructor. |
||||
* |
||||
* \param weak_threshold When quantizing, discard gradients with magnitude less than this. |
||||
* \param num_features How many features a template must contain. |
||||
* \param strong_threshold Consider as candidate features only gradients whose norms are |
||||
* larger than this. |
||||
*/ |
||||
ColorGradient(float weak_threshold, size_t num_features, float strong_threshold); |
||||
|
||||
virtual String name() const; |
||||
|
||||
virtual void read(const FileNode& fn); |
||||
virtual void write(FileStorage& fs) const; |
||||
|
||||
float weak_threshold; |
||||
size_t num_features; |
||||
float strong_threshold; |
||||
|
||||
protected: |
||||
virtual Ptr<QuantizedPyramid> processImpl(const Mat& src, |
||||
const Mat& mask) const; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Modality that computes quantized surface normals from a dense depth map. |
||||
*/ |
||||
class CV_EXPORTS DepthNormal : public Modality |
||||
{ |
||||
public: |
||||
/**
|
||||
* \brief Default constructor. Uses reasonable default parameter values. |
||||
*/ |
||||
DepthNormal(); |
||||
|
||||
/**
|
||||
* \brief Constructor. |
||||
* |
||||
* \param distance_threshold Ignore pixels beyond this distance. |
||||
* \param difference_threshold When computing normals, ignore contributions of pixels whose |
||||
* depth difference with the central pixel is above this threshold. |
||||
* \param num_features How many features a template must contain. |
||||
* \param extract_threshold Consider as candidate feature only if there are no differing |
||||
* orientations within a distance of extract_threshold. |
||||
*/ |
||||
DepthNormal(int distance_threshold, int difference_threshold, size_t num_features, |
||||
int extract_threshold); |
||||
|
||||
virtual String name() const; |
||||
|
||||
virtual void read(const FileNode& fn); |
||||
virtual void write(FileStorage& fs) const; |
||||
|
||||
int distance_threshold; |
||||
int difference_threshold; |
||||
size_t num_features; |
||||
int extract_threshold; |
||||
|
||||
protected: |
||||
virtual Ptr<QuantizedPyramid> processImpl(const Mat& src, |
||||
const Mat& mask) const; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Debug function to colormap a quantized image for viewing. |
||||
*/ |
||||
void colormap(const Mat& quantized, Mat& dst); |
||||
|
||||
/**
|
||||
* \brief Represents a successful template match. |
||||
*/ |
||||
struct CV_EXPORTS Match |
||||
{ |
||||
Match() |
||||
{ |
||||
} |
||||
|
||||
Match(int x, int y, float similarity, const String& class_id, int template_id); |
||||
|
||||
/// Sort matches with high similarity to the front
|
||||
bool operator<(const Match& rhs) const |
||||
{ |
||||
// Secondarily sort on template_id for the sake of duplicate removal
|
||||
if (similarity != rhs.similarity) |
||||
return similarity > rhs.similarity; |
||||
else |
||||
return template_id < rhs.template_id; |
||||
} |
||||
|
||||
bool operator==(const Match& rhs) const |
||||
{ |
||||
return x == rhs.x && y == rhs.y && similarity == rhs.similarity && class_id == rhs.class_id; |
||||
} |
||||
|
||||
int x; |
||||
int y; |
||||
float similarity; |
||||
String class_id; |
||||
int template_id; |
||||
}; |
||||
|
||||
inline |
||||
Match::Match(int _x, int _y, float _similarity, const String& _class_id, int _template_id) |
||||
: x(_x), y(_y), similarity(_similarity), class_id(_class_id), template_id(_template_id) |
||||
{} |
||||
|
||||
/**
|
||||
* \brief Object detector using the LINE template matching algorithm with any set of |
||||
* modalities. |
||||
*/ |
||||
class CV_EXPORTS Detector |
||||
{ |
||||
public: |
||||
/**
|
||||
* \brief Empty constructor, initialize with read(). |
||||
*/ |
||||
Detector(); |
||||
|
||||
/**
|
||||
* \brief Constructor. |
||||
* |
||||
* \param modalities Modalities to use (color gradients, depth normals, ...). |
||||
* \param T_pyramid Value of the sampling step T at each pyramid level. The |
||||
* number of pyramid levels is T_pyramid.size(). |
||||
*/ |
||||
Detector(const std::vector< Ptr<Modality> >& modalities, const std::vector<int>& T_pyramid); |
||||
|
||||
/**
|
||||
* \brief Detect objects by template matching. |
||||
* |
||||
* Matches globally at the lowest pyramid level, then refines locally stepping up the pyramid. |
||||
* |
||||
* \param sources Source images, one for each modality. |
||||
* \param threshold Similarity threshold, a percentage between 0 and 100. |
||||
* \param[out] matches Template matches, sorted by similarity score. |
||||
* \param class_ids If non-empty, only search for the desired object classes. |
||||
* \param[out] quantized_images Optionally return vector<Mat> of quantized images. |
||||
* \param masks The masks for consideration during matching. The masks should be CV_8UC1 |
||||
* where 255 represents a valid pixel. If non-empty, the vector must be |
||||
* the same size as sources. Each element must be |
||||
* empty or the same size as its corresponding source. |
||||
*/ |
||||
void match(const std::vector<Mat>& sources, float threshold, std::vector<Match>& matches, |
||||
const std::vector<String>& class_ids = std::vector<String>(), |
||||
OutputArrayOfArrays quantized_images = noArray(), |
||||
const std::vector<Mat>& masks = std::vector<Mat>()) const; |
||||
|
||||
/**
|
||||
* \brief Add new object template. |
||||
* |
||||
* \param sources Source images, one for each modality. |
||||
* \param class_id Object class ID. |
||||
* \param object_mask Mask separating object from background. |
||||
* \param[out] bounding_box Optionally return bounding box of the extracted features. |
||||
* |
||||
* \return Template ID, or -1 if failed to extract a valid template. |
||||
*/ |
||||
int addTemplate(const std::vector<Mat>& sources, const String& class_id, |
||||
const Mat& object_mask, Rect* bounding_box = NULL); |
||||
|
||||
/**
|
||||
* \brief Add a new object template computed by external means. |
||||
*/ |
||||
int addSyntheticTemplate(const std::vector<Template>& templates, const String& class_id); |
||||
|
||||
/**
|
||||
* \brief Get the modalities used by this detector. |
||||
* |
||||
* You are not permitted to add/remove modalities, but you may dynamic_cast them to |
||||
* tweak parameters. |
||||
*/ |
||||
const std::vector< Ptr<Modality> >& getModalities() const { return modalities; } |
||||
|
||||
/**
|
||||
* \brief Get sampling step T at pyramid_level. |
||||
*/ |
||||
int getT(int pyramid_level) const { return T_at_level[pyramid_level]; } |
||||
|
||||
/**
|
||||
* \brief Get number of pyramid levels used by this detector. |
||||
*/ |
||||
int pyramidLevels() const { return pyramid_levels; } |
||||
|
||||
/**
|
||||
* \brief Get the template pyramid identified by template_id. |
||||
* |
||||
* For example, with 2 modalities (Gradient, Normal) and two pyramid levels |
||||
* (L0, L1), the order is (GradientL0, NormalL0, GradientL1, NormalL1). |
||||
*/ |
||||
const std::vector<Template>& getTemplates(const String& class_id, int template_id) const; |
||||
|
||||
int numTemplates() const; |
||||
int numTemplates(const String& class_id) const; |
||||
int numClasses() const { return static_cast<int>(class_templates.size()); } |
||||
|
||||
std::vector<String> classIds() const; |
||||
|
||||
void read(const FileNode& fn); |
||||
void write(FileStorage& fs) const; |
||||
|
||||
String readClass(const FileNode& fn, const String &class_id_override = ""); |
||||
void writeClass(const String& class_id, FileStorage& fs) const; |
||||
|
||||
void readClasses(const std::vector<String>& class_ids, |
||||
const String& format = "templates_%s.yml.gz"); |
||||
void writeClasses(const String& format = "templates_%s.yml.gz") const; |
||||
|
||||
protected: |
||||
std::vector< Ptr<Modality> > modalities; |
||||
int pyramid_levels; |
||||
std::vector<int> T_at_level; |
||||
|
||||
typedef std::vector<Template> TemplatePyramid; |
||||
typedef std::map<String, std::vector<TemplatePyramid> > TemplatesMap; |
||||
TemplatesMap class_templates; |
||||
|
||||
typedef std::vector<Mat> LinearMemories; |
||||
// Indexed as [pyramid level][modality][quantized label]
|
||||
typedef std::vector< std::vector<LinearMemories> > LinearMemoryPyramid; |
||||
|
||||
void matchClass(const LinearMemoryPyramid& lm_pyramid, |
||||
const std::vector<Size>& sizes, |
||||
float threshold, std::vector<Match>& matches, |
||||
const String& class_id, |
||||
const std::vector<TemplatePyramid>& template_pyramids) const; |
||||
}; |
||||
|
||||
/**
|
||||
* \brief Factory function for detector using LINE algorithm with color gradients. |
||||
* |
||||
* Default parameter settings suitable for VGA images. |
||||
*/ |
||||
CV_EXPORTS Ptr<Detector> getDefaultLINE(); |
||||
|
||||
/**
|
||||
* \brief Factory function for detector using LINE-MOD algorithm with color gradients |
||||
* and depth normals. |
||||
* |
||||
* Default parameter settings suitable for VGA images. |
||||
*/ |
||||
CV_EXPORTS Ptr<Detector> getDefaultLINEMOD(); |
||||
|
||||
} // namespace linemod
|
||||
} // namespace cv
|
||||
|
||||
#endif // __OPENCV_OBJDETECT_LINEMOD_HPP__
|
||||
@ -0,0 +1,289 @@ |
||||
/*M///////////////////////////////////////////////////////////////////////////////////////
|
||||
//
|
||||
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
|
||||
//
|
||||
// By downloading, copying, installing or using the software you agree to this license.
|
||||
// If you do not agree to this license, do not download, install,
|
||||
// copy or use the software.
|
||||
//
|
||||
//
|
||||
// License Agreement
|
||||
// For Open Source Computer Vision Library
|
||||
//
|
||||
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
|
||||
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
|
||||
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
|
||||
// Third party copyrights are property of their respective owners.
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without modification,
|
||||
// are permitted provided that the following conditions are met:
|
||||
//
|
||||
// * Redistribution's of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
//
|
||||
// * Redistribution's in binary form must reproduce the above copyright notice,
|
||||
// this list of conditions and the following disclaimer in the documentation
|
||||
// and/or other materials provided with the distribution.
|
||||
//
|
||||
// * The name of the copyright holders may not be used to endorse or promote products
|
||||
// derived from this software without specific prior written permission.
|
||||
//
|
||||
// This software is provided by the copyright holders and contributors "as is" and
|
||||
// any express or implied warranties, including, but not limited to, the implied
|
||||
// warranties of merchantability and fitness for a particular purpose are disclaimed.
|
||||
// In no event shall the Intel Corporation or contributors be liable for any direct,
|
||||
// indirect, incidental, special, exemplary, or consequential damages
|
||||
// (including, but not limited to, procurement of substitute goods or services;
|
||||
// loss of use, data, or profits; or business interruption) however caused
|
||||
// and on any theory of liability, whether in contract, strict liability,
|
||||
// or tort (including negligence or otherwise) arising in any way out of
|
||||
// the use of this software, even if advised of the possibility of such damage.
|
||||
//
|
||||
//M*/
|
||||
|
||||
#ifndef __OPENCV_OBJDETECT_C_H__ |
||||
#define __OPENCV_OBJDETECT_C_H__ |
||||
|
||||
#include "opencv2/core/core_c.h" |
||||
|
||||
#ifdef __cplusplus |
||||
#include <deque> |
||||
#include <vector> |
||||
|
||||
extern "C" { |
||||
#endif |
||||
|
||||
/****************************************************************************************\
|
||||
* Haar-like Object Detection functions * |
||||
\****************************************************************************************/ |
||||
|
||||
#define CV_HAAR_MAGIC_VAL 0x42500000 |
||||
#define CV_TYPE_NAME_HAAR "opencv-haar-classifier" |
||||
|
||||
#define CV_IS_HAAR_CLASSIFIER( haar ) \ |
||||
((haar) != NULL && \
|
||||
(((const CvHaarClassifierCascade*)(haar))->flags & CV_MAGIC_MASK)==CV_HAAR_MAGIC_VAL) |
||||
|
||||
#define CV_HAAR_FEATURE_MAX 3 |
||||
|
||||
typedef struct CvHaarFeature |
||||
{ |
||||
int tilted; |
||||
struct |
||||
{ |
||||
CvRect r; |
||||
float weight; |
||||
} rect[CV_HAAR_FEATURE_MAX]; |
||||
} CvHaarFeature; |
||||
|
||||
typedef struct CvHaarClassifier |
||||
{ |
||||
int count; |
||||
CvHaarFeature* haar_feature; |
||||
float* threshold; |
||||
int* left; |
||||
int* right; |
||||
float* alpha; |
||||
} CvHaarClassifier; |
||||
|
||||
typedef struct CvHaarStageClassifier |
||||
{ |
||||
int count; |
||||
float threshold; |
||||
CvHaarClassifier* classifier; |
||||
|
||||
int next; |
||||
int child; |
||||
int parent; |
||||
} CvHaarStageClassifier; |
||||
|
||||
typedef struct CvHidHaarClassifierCascade CvHidHaarClassifierCascade; |
||||
|
||||
typedef struct CvHaarClassifierCascade |
||||
{ |
||||
int flags; |
||||
int count; |
||||
CvSize orig_window_size; |
||||
CvSize real_window_size; |
||||
double scale; |
||||
CvHaarStageClassifier* stage_classifier; |
||||
CvHidHaarClassifierCascade* hid_cascade; |
||||
} CvHaarClassifierCascade; |
||||
|
||||
typedef struct CvAvgComp |
||||
{ |
||||
CvRect rect; |
||||
int neighbors; |
||||
} CvAvgComp; |
||||
|
||||
/* Loads haar classifier cascade from a directory.
|
||||
It is obsolete: convert your cascade to xml and use cvLoad instead */ |
||||
CVAPI(CvHaarClassifierCascade*) cvLoadHaarClassifierCascade( |
||||
const char* directory, CvSize orig_window_size); |
||||
|
||||
CVAPI(void) cvReleaseHaarClassifierCascade( CvHaarClassifierCascade** cascade ); |
||||
|
||||
#define CV_HAAR_DO_CANNY_PRUNING 1 |
||||
#define CV_HAAR_SCALE_IMAGE 2 |
||||
#define CV_HAAR_FIND_BIGGEST_OBJECT 4 |
||||
#define CV_HAAR_DO_ROUGH_SEARCH 8 |
||||
|
||||
CVAPI(CvSeq*) cvHaarDetectObjects( const CvArr* image, |
||||
CvHaarClassifierCascade* cascade, CvMemStorage* storage, |
||||
double scale_factor CV_DEFAULT(1.1), |
||||
int min_neighbors CV_DEFAULT(3), int flags CV_DEFAULT(0), |
||||
CvSize min_size CV_DEFAULT(cvSize(0,0)), CvSize max_size CV_DEFAULT(cvSize(0,0))); |
||||
|
||||
/* sets images for haar classifier cascade */ |
||||
CVAPI(void) cvSetImagesForHaarClassifierCascade( CvHaarClassifierCascade* cascade, |
||||
const CvArr* sum, const CvArr* sqsum, |
||||
const CvArr* tilted_sum, double scale ); |
||||
|
||||
/* runs the cascade on the specified window */ |
||||
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 CvLSVMFilterPosition |
||||
{ |
||||
int x; |
||||
int y; |
||||
int l; |
||||
} CvLSVMFilterPosition; |
||||
|
||||
// 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
|
||||
typedef struct CvLSVMFilterObject{ |
||||
CvLSVMFilterPosition V; |
||||
float fineFunction[4]; |
||||
int sizeX; |
||||
int sizeY; |
||||
int numFeatures; |
||||
float *H; |
||||
} CvLSVMFilterObject; |
||||
|
||||
// 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; |
||||
CvLSVMFilterObject** 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,
|
||||
// int numThreads = -1);
|
||||
// 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), |
||||
int numThreads CV_DEFAULT(-1)); |
||||
|
||||
#ifdef __cplusplus |
||||
} |
||||
|
||||
CV_EXPORTS CvSeq* cvHaarDetectObjectsForROC( const CvArr* image, |
||||
CvHaarClassifierCascade* cascade, CvMemStorage* storage, |
||||
std::vector<int>& rejectLevels, std::vector<double>& levelWeightds, |
||||
double scale_factor = 1.1, |
||||
int min_neighbors = 3, int flags = 0, |
||||
CvSize min_size = cvSize(0, 0), CvSize max_size = cvSize(0, 0), |
||||
bool outputRejectLevels = false ); |
||||
|
||||
struct CvDataMatrixCode |
||||
{ |
||||
char msg[4]; |
||||
CvMat* original; |
||||
CvMat* corners; |
||||
}; |
||||
|
||||
CV_EXPORTS std::deque<CvDataMatrixCode> cvFindDataMatrix(CvMat *im); |
||||
|
||||
#endif |
||||
|
||||
|
||||
#endif /* __OPENCV_OBJDETECT_C_H__ */ |
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue