storytold/LiveScan3D
2
0
Fork 0
mirror of https://github.com/storytold/LiveScan3D.git synced 2026-10-17 00:23:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Moved to Visual Studio 2015, OpenCV 3.2.0, x64

Browse Source
This commit is contained in:
MarekKowalski
2017-02-28 11:30:27 +01:00
parent 44f9a1da22
commit 98bfe298ab
244 changed files with 56126 additions and 68481 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/opencv2/video/background_segm.hpp
+224 -180
View File
@@ -7,11 +7,12 @@
// copy or use the software.
//
//
// License Agreement
// 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,
@@ -40,223 +41,266 @@
//
//M*/
#ifndef __OPENCV_BACKGROUND_SEGM_HPP__
#define __OPENCV_BACKGROUND_SEGM_HPP__
#ifndef OPENCV_BACKGROUND_SEGM_HPP
#define OPENCV_BACKGROUND_SEGM_HPP
#include "opencv2/core.hpp"
#include "opencv2/core/core.hpp"
#include <list>
namespace cv
{
/*!
The Base Class for Background/Foreground Segmentation
//! @addtogroup video_motion
//! @{
The class is only used to define the common interface for
the whole family of background/foreground segmentation algorithms.
*/
/** @brief Base class for background/foreground segmentation. :
The class is only used to define the common interface for the whole family of background/foreground
segmentation algorithms.
*/
class CV_EXPORTS_W BackgroundSubtractor : public Algorithm
{
public:
//! the virtual destructor
virtual ~BackgroundSubtractor();
//! the update operator that takes the next video frame and returns the current foreground mask as 8-bit binary image.
CV_WRAP_AS(apply) virtual void operator()(InputArray image, OutputArray fgmask,
double learningRate=0);
/** @brief Computes a foreground mask.
//! computes a background image
virtual void getBackgroundImage(OutputArray backgroundImage) const;
@param image Next video frame.
@param fgmask The output foreground mask as an 8-bit binary image.
@param learningRate The value between 0 and 1 that indicates how fast the background model is
learnt. Negative parameter value makes the algorithm to use some automatically chosen learning
rate. 0 means that the background model is not updated at all, 1 means that the background model
is completely reinitialized from the last frame.
*/
CV_WRAP virtual void apply(InputArray image, OutputArray fgmask, double learningRate=-1) = 0;
/** @brief Computes a background image.
@param backgroundImage The output background image.
@note Sometimes the background image can be very blurry, as it contain the average background
statistics.
*/
CV_WRAP virtual void getBackgroundImage(OutputArray backgroundImage) const = 0;
};
/*!
Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm
/** @brief Gaussian Mixture-based Background/Foreground Segmentation Algorithm.
The class implements the following algorithm:
"An improved adaptive background mixture model for real-time tracking with shadow detection"
P. KadewTraKuPong and R. Bowden,
Proc. 2nd European Workshp on Advanced Video-Based Surveillance Systems, 2001."
http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/avbs01/avbs01.pdf
*/
class CV_EXPORTS_W BackgroundSubtractorMOG : public BackgroundSubtractor
{
public:
//! the default constructor
CV_WRAP BackgroundSubtractorMOG();
//! the full constructor that takes the length of the history, the number of gaussian mixtures, the background ratio parameter and the noise strength
CV_WRAP BackgroundSubtractorMOG(int history, int nmixtures, double backgroundRatio, double noiseSigma=0);
//! the destructor
virtual ~BackgroundSubtractorMOG();
//! the update operator
virtual void operator()(InputArray image, OutputArray fgmask, double learningRate=0);
//! re-initiaization method
virtual void initialize(Size frameSize, int frameType);
virtual AlgorithmInfo* info() const;
protected:
Size frameSize;
int frameType;
Mat bgmodel;
int nframes;
int history;
int nmixtures;
double varThreshold;
double backgroundRatio;
double noiseSigma;
};
/*!
The class implements the following algorithm:
"Improved adaptive Gausian mixture model for background subtraction"
Z.Zivkovic
International Conference Pattern Recognition, UK, August, 2004.
http://www.zoranz.net/Publications/zivkovic2004ICPR.pdf
*/
The class implements the Gaussian mixture model background subtraction described in @cite Zivkovic2004
and @cite Zivkovic2006 .
*/
class CV_EXPORTS_W BackgroundSubtractorMOG2 : public BackgroundSubtractor
{
public:
//! the default constructor
CV_WRAP BackgroundSubtractorMOG2();
//! the full constructor that takes the length of the history, the number of gaussian mixtures, the background ratio parameter and the noise strength
CV_WRAP BackgroundSubtractorMOG2(int history, float varThreshold, bool bShadowDetection=true);
//! the destructor
virtual ~BackgroundSubtractorMOG2();
//! the update operator
virtual void operator()(InputArray image, OutputArray fgmask, double learningRate=-1);
/** @brief Returns the number of last frames that affect the background model
*/
CV_WRAP virtual int getHistory() const = 0;
/** @brief Sets the number of last frames that affect the background model
*/
CV_WRAP virtual void setHistory(int history) = 0;
//! computes a background image which are the mean of all background gaussians
virtual void getBackgroundImage(OutputArray backgroundImage) const;
/** @brief Returns the number of gaussian components in the background model
*/
CV_WRAP virtual int getNMixtures() const = 0;
/** @brief Sets the number of gaussian components in the background model.
//! re-initiaization method
virtual void initialize(Size frameSize, int frameType);
The model needs to be reinitalized to reserve memory.
*/
CV_WRAP virtual void setNMixtures(int nmixtures) = 0;//needs reinitialization!
virtual AlgorithmInfo* info() const;
/** @brief Returns the "background ratio" parameter of the algorithm
protected:
Size frameSize;
int frameType;
Mat bgmodel;
Mat bgmodelUsedModes;//keep track of number of modes per pixel
int nframes;
int history;
int nmixtures;
//! here it is the maximum allowed number of mixture components.
//! Actual number is determined dynamically per pixel
double varThreshold;
// threshold on the squared Mahalanobis distance to decide if it is well described
// by the background model or not. Related to Cthr from the paper.
// This does not influence the update of the background. A typical value could be 4 sigma
// and that is varThreshold=4*4=16; Corresponds to Tb in the paper.
If a foreground pixel keeps semi-constant value for about backgroundRatio\*history frames, it's
considered background and added to the model as a center of a new component. It corresponds to TB
parameter in the paper.
*/
CV_WRAP virtual double getBackgroundRatio() const = 0;
/** @brief Sets the "background ratio" parameter of the algorithm
*/
CV_WRAP virtual void setBackgroundRatio(double ratio) = 0;
/////////////////////////
// less important parameters - things you might change but be carefull
////////////////////////
float backgroundRatio;
// corresponds to fTB=1-cf from the paper
// TB - threshold when the component becomes significant enough to be included into
// the background model. It is the TB=1-cf from the paper. So I use cf=0.1 => TB=0.
// For alpha=0.001 it means that the mode should exist for approximately 105 frames before
// it is considered foreground
// float noiseSigma;
float varThresholdGen;
//correspondts to Tg - threshold on the squared Mahalan. dist. to decide
//when a sample is close to the existing components. If it is not close
//to any a new component will be generated. I use 3 sigma => Tg=3*3=9.
//Smaller Tg leads to more generated components and higher Tg might make
//lead to small number of components but they can grow too large
float fVarInit;
float fVarMin;
float fVarMax;
//initial variance for the newly generated components.
//It will will influence the speed of adaptation. A good guess should be made.
//A simple way is to estimate the typical standard deviation from the images.
//I used here 10 as a reasonable value
// min and max can be used to further control the variance
float fCT;//CT - complexity reduction prior
//this is related to the number of samples needed to accept that a component
//actually exists. We use CT=0.05 of all the samples. By setting CT=0 you get
//the standard Stauffer&Grimson algorithm (maybe not exact but very similar)
/** @brief Returns the variance threshold for the pixel-model match
//shadow detection parameters
bool bShadowDetection;//default 1 - do shadow detection
unsigned char nShadowDetection;//do shadow detection - insert this value as the detection result - 127 default value
float fTau;
// Tau - shadow threshold. The shadow is detected if the pixel is darker
//version of the background. Tau is a threshold on how much darker the shadow can be.
//Tau= 0.5 means that if pixel is more than 2 times darker then it is not shadow
//See: Prati,Mikic,Trivedi,Cucchiarra,"Detecting Moving Shadows...",IEEE PAMI,2003.
The main threshold on the squared Mahalanobis distance to decide if the sample is well described by
the background model or not. Related to Cthr from the paper.
*/
CV_WRAP virtual double getVarThreshold() const = 0;
/** @brief Sets the variance threshold for the pixel-model match
*/
CV_WRAP virtual void setVarThreshold(double varThreshold) = 0;
/** @brief Returns the variance threshold for the pixel-model match used for new mixture component generation
Threshold for the squared Mahalanobis distance that helps decide when a sample is close to the
existing components (corresponds to Tg in the paper). If a pixel is not close to any component, it
is considered foreground or added as a new component. 3 sigma =\> Tg=3\*3=9 is default. A smaller Tg
value generates more components. A higher Tg value may result in a small number of components but
they can grow too large.
*/
CV_WRAP virtual double getVarThresholdGen() const = 0;
/** @brief Sets the variance threshold for the pixel-model match used for new mixture component generation
*/
CV_WRAP virtual void setVarThresholdGen(double varThresholdGen) = 0;
/** @brief Returns the initial variance of each gaussian component
*/
CV_WRAP virtual double getVarInit() const = 0;
/** @brief Sets the initial variance of each gaussian component
*/
CV_WRAP virtual void setVarInit(double varInit) = 0;
CV_WRAP virtual double getVarMin() const = 0;
CV_WRAP virtual void setVarMin(double varMin) = 0;
CV_WRAP virtual double getVarMax() const = 0;
CV_WRAP virtual void setVarMax(double varMax) = 0;
/** @brief Returns the complexity reduction threshold
This parameter defines the number of samples needed to accept to prove the component exists. CT=0.05
is a default value for all the samples. By setting CT=0 you get an algorithm very similar to the
standard Stauffer&Grimson algorithm.
*/
CV_WRAP virtual double getComplexityReductionThreshold() const = 0;
/** @brief Sets the complexity reduction threshold
*/
CV_WRAP virtual void setComplexityReductionThreshold(double ct) = 0;
/** @brief Returns the shadow detection flag
If true, the algorithm detects shadows and marks them. See createBackgroundSubtractorMOG2 for
details.
*/
CV_WRAP virtual bool getDetectShadows() const = 0;
/** @brief Enables or disables shadow detection
*/
CV_WRAP virtual void setDetectShadows(bool detectShadows) = 0;
/** @brief Returns the shadow value
Shadow value is the value used to mark shadows in the foreground mask. Default value is 127. Value 0
in the mask always means background, 255 means foreground.
*/
CV_WRAP virtual int getShadowValue() const = 0;
/** @brief Sets the shadow value
*/
CV_WRAP virtual void setShadowValue(int value) = 0;
/** @brief Returns the shadow threshold
A shadow is detected if pixel is a darker version of the background. The shadow threshold (Tau in
the paper) is a threshold defining how much darker the shadow can be. Tau= 0.5 means that if a pixel
is more than twice darker then it is not shadow. See Prati, Mikic, Trivedi and Cucchiarra,
*Detecting Moving Shadows...*, IEEE PAMI,2003.
*/
CV_WRAP virtual double getShadowThreshold() const = 0;
/** @brief Sets the shadow threshold
*/
CV_WRAP virtual void setShadowThreshold(double threshold) = 0;
};
/**
* Background Subtractor module. Takes a series of images and returns a sequence of mask (8UC1)
* images of the same size, where 255 indicates Foreground and 0 represents Background.
* This class implements an algorithm described in "Visual Tracking of Human Visitors under
* Variable-Lighting Conditions for a Responsive Audio Art Installation," A. Godbehere,
* A. Matsukawa, K. Goldberg, American Control Conference, Montreal, June 2012.
/** @brief Creates MOG2 Background Subtractor
@param history Length of the history.
@param varThreshold Threshold on the squared Mahalanobis distance between the pixel and the model
to decide whether a pixel is well described by the background model. This parameter does not
affect the background update.
@param detectShadows If true, the algorithm will detect shadows and mark them. It decreases the
speed a bit, so if you do not need this feature, set the parameter to false.
*/
class CV_EXPORTS BackgroundSubtractorGMG: public cv::BackgroundSubtractor
CV_EXPORTS_W Ptr<BackgroundSubtractorMOG2>
createBackgroundSubtractorMOG2(int history=500, double varThreshold=16,
bool detectShadows=true);
/** @brief K-nearest neigbours - based Background/Foreground Segmentation Algorithm.
The class implements the K-nearest neigbours background subtraction described in @cite Zivkovic2006 .
Very efficient if number of foreground pixels is low.
*/
class CV_EXPORTS_W BackgroundSubtractorKNN : public BackgroundSubtractor
{
public:
BackgroundSubtractorGMG();
virtual ~BackgroundSubtractorGMG();
virtual AlgorithmInfo* info() const;
/** @brief Returns the number of last frames that affect the background model
*/
CV_WRAP virtual int getHistory() const = 0;
/** @brief Sets the number of last frames that affect the background model
*/
CV_WRAP virtual void setHistory(int history) = 0;
/**
* Validate parameters and set up data structures for appropriate image size.
* Must call before running on data.
* @param frameSize input frame size
* @param min minimum value taken on by pixels in image sequence. Usually 0
* @param max maximum value taken on by pixels in image sequence. e.g. 1.0 or 255
/** @brief Returns the number of data samples in the background model
*/
CV_WRAP virtual int getNSamples() const = 0;
/** @brief Sets the number of data samples in the background model.
The model needs to be reinitalized to reserve memory.
*/
CV_WRAP virtual void setNSamples(int _nN) = 0;//needs reinitialization!
/** @brief Returns the threshold on the squared distance between the pixel and the sample
The threshold on the squared distance between the pixel and the sample to decide whether a pixel is
close to a data sample.
*/
void initialize(cv::Size frameSize, double min, double max);
CV_WRAP virtual double getDist2Threshold() const = 0;
/** @brief Sets the threshold on the squared distance
*/
CV_WRAP virtual void setDist2Threshold(double _dist2Threshold) = 0;
/**
* Performs single-frame background subtraction and builds up a statistical background image
* model.
* @param image Input image
* @param fgmask Output mask image representing foreground and background pixels
/** @brief Returns the number of neighbours, the k in the kNN.
K is the number of samples that need to be within dist2Threshold in order to decide that that
pixel is matching the kNN background model.
*/
virtual void operator()(InputArray image, OutputArray fgmask, double learningRate=-1.0);
CV_WRAP virtual int getkNNSamples() const = 0;
/** @brief Sets the k in the kNN. How many nearest neigbours need to match.
*/
CV_WRAP virtual void setkNNSamples(int _nkNN) = 0;
/**
* Releases all inner buffers.
/** @brief Returns the shadow detection flag
If true, the algorithm detects shadows and marks them. See createBackgroundSubtractorKNN for
details.
*/
void release();
CV_WRAP virtual bool getDetectShadows() const = 0;
/** @brief Enables or disables shadow detection
*/
CV_WRAP virtual void setDetectShadows(bool detectShadows) = 0;
//! Total number of distinct colors to maintain in histogram.
int maxFeatures;
//! Set between 0.0 and 1.0, determines how quickly features are "forgotten" from histograms.
double learningRate;
//! Number of frames of video to use to initialize histograms.
int numInitializationFrames;
//! Number of discrete levels in each channel to be used in histograms.
int quantizationLevels;
//! Prior probability that any given pixel is a background pixel. A sensitivity parameter.
double backgroundPrior;
//! Value above which pixel is determined to be FG.
double decisionThreshold;
//! Smoothing radius, in pixels, for cleaning up FG image.
int smoothingRadius;
//! Perform background model update
bool updateBackgroundModel;
/** @brief Returns the shadow value
private:
double maxVal_;
double minVal_;
Shadow value is the value used to mark shadows in the foreground mask. Default value is 127. Value 0
in the mask always means background, 255 means foreground.
*/
CV_WRAP virtual int getShadowValue() const = 0;
/** @brief Sets the shadow value
*/
CV_WRAP virtual void setShadowValue(int value) = 0;
cv::Size frameSize_;
int frameNum_;
/** @brief Returns the shadow threshold
cv::Mat_<int> nfeatures_;
cv::Mat_<unsigned int> colors_;
cv::Mat_<float> weights_;
cv::Mat buf_;
A shadow is detected if pixel is a darker version of the background. The shadow threshold (Tau in
the paper) is a threshold defining how much darker the shadow can be. Tau= 0.5 means that if a pixel
is more than twice darker then it is not shadow. See Prati, Mikic, Trivedi and Cucchiarra,
*Detecting Moving Shadows...*, IEEE PAMI,2003.
*/
CV_WRAP virtual double getShadowThreshold() const = 0;
/** @brief Sets the shadow threshold
*/
CV_WRAP virtual void setShadowThreshold(double threshold) = 0;
};
}
/** @brief Creates KNN Background Subtractor
@param history Length of the history.
@param dist2Threshold Threshold on the squared distance between the pixel and the sample to decide
whether a pixel is close to that sample. This parameter does not affect the background update.
@param detectShadows If true, the algorithm will detect shadows and mark them. It decreases the
speed a bit, so if you do not need this feature, set the parameter to false.
*/
CV_EXPORTS_W Ptr<BackgroundSubtractorKNN>
createBackgroundSubtractorKNN(int history=500, double dist2Threshold=400.0,
bool detectShadows=true);
//! @} video_motion
} // cv
#endif
include/opencv2/video/tracking.hpp
+549 -296
View File
@@ -1,7 +1,3 @@
/*! \file tracking.hpp
\brief The Object and Feature Tracking
*/
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
@@ -11,11 +7,12 @@
// copy or use the software.
//
//
// License Agreement
// 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,
@@ -44,249 +41,337 @@
//
//M*/
#ifndef __OPENCV_TRACKING_HPP__
#define __OPENCV_TRACKING_HPP__
#ifndef OPENCV_TRACKING_HPP
#define OPENCV_TRACKING_HPP
#include "opencv2/core/core.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#ifdef __cplusplus
extern "C" {
#endif
/****************************************************************************************\
* Motion Analysis *
\****************************************************************************************/
/************************************ optical flow ***************************************/
#define CV_LKFLOW_PYR_A_READY 1
#define CV_LKFLOW_PYR_B_READY 2
#define CV_LKFLOW_INITIAL_GUESSES 4
#define CV_LKFLOW_GET_MIN_EIGENVALS 8
/* It is Lucas & Kanade method, modified to use pyramids.
Also it does several iterations to get optical flow for
every point at every pyramid level.
Calculates optical flow between two images for certain set of points (i.e.
it is a "sparse" optical flow, which is opposite to the previous 3 methods) */
CVAPI(void) cvCalcOpticalFlowPyrLK( const CvArr* prev, const CvArr* curr,
CvArr* prev_pyr, CvArr* curr_pyr,
const CvPoint2D32f* prev_features,
CvPoint2D32f* curr_features,
int count,
CvSize win_size,
int level,
char* status,
float* track_error,
CvTermCriteria criteria,
int flags );
/* Modification of a previous sparse optical flow algorithm to calculate
affine flow */
CVAPI(void) cvCalcAffineFlowPyrLK( const CvArr* prev, const CvArr* curr,
CvArr* prev_pyr, CvArr* curr_pyr,
const CvPoint2D32f* prev_features,
CvPoint2D32f* curr_features,
float* matrices, int count,
CvSize win_size, int level,
char* status, float* track_error,
CvTermCriteria criteria, int flags );
/* Estimate rigid transformation between 2 images or 2 point sets */
CVAPI(int) cvEstimateRigidTransform( const CvArr* A, const CvArr* B,
CvMat* M, int full_affine );
/* Estimate optical flow for each pixel using the two-frame G. Farneback algorithm */
CVAPI(void) cvCalcOpticalFlowFarneback( const CvArr* prev, const CvArr* next,
CvArr* flow, double pyr_scale, int levels,
int winsize, int iterations, int poly_n,
double poly_sigma, int flags );
/********************************* motion templates *************************************/
/****************************************************************************************\
* All the motion template functions work only with single channel images. *
* Silhouette image must have depth IPL_DEPTH_8U or IPL_DEPTH_8S *
* Motion history image must have depth IPL_DEPTH_32F, *
* Gradient mask - IPL_DEPTH_8U or IPL_DEPTH_8S, *
* Motion orientation image - IPL_DEPTH_32F *
* Segmentation mask - IPL_DEPTH_32F *
* All the angles are in degrees, all the times are in milliseconds *
\****************************************************************************************/
/* Updates motion history image given motion silhouette */
CVAPI(void) cvUpdateMotionHistory( const CvArr* silhouette, CvArr* mhi,
double timestamp, double duration );
/* Calculates gradient of the motion history image and fills
a mask indicating where the gradient is valid */
CVAPI(void) cvCalcMotionGradient( const CvArr* mhi, CvArr* mask, CvArr* orientation,
double delta1, double delta2,
int aperture_size CV_DEFAULT(3));
/* Calculates average motion direction within a selected motion region
(region can be selected by setting ROIs and/or by composing a valid gradient mask
with the region mask) */
CVAPI(double) cvCalcGlobalOrientation( const CvArr* orientation, const CvArr* mask,
const CvArr* mhi, double timestamp,
double duration );
/* Splits a motion history image into a few parts corresponding to separate independent motions
(e.g. left hand, right hand) */
CVAPI(CvSeq*) cvSegmentMotion( const CvArr* mhi, CvArr* seg_mask,
CvMemStorage* storage,
double timestamp, double seg_thresh );
/****************************************************************************************\
* Tracking *
\****************************************************************************************/
/* Implements CAMSHIFT algorithm - determines object position, size and orientation
from the object histogram back project (extension of meanshift) */
CVAPI(int) cvCamShift( const CvArr* prob_image, CvRect window,
CvTermCriteria criteria, CvConnectedComp* comp,
CvBox2D* box CV_DEFAULT(NULL) );
/* Implements MeanShift algorithm - determines object position
from the object histogram back project */
CVAPI(int) cvMeanShift( const CvArr* prob_image, CvRect window,
CvTermCriteria criteria, CvConnectedComp* comp );
/*
standard Kalman filter (in G. Welch' and G. Bishop's notation):
x(k)=A*x(k-1)+B*u(k)+w(k) p(w)~N(0,Q)
z(k)=H*x(k)+v(k), p(v)~N(0,R)
*/
typedef struct CvKalman
{
int MP; /* number of measurement vector dimensions */
int DP; /* number of state vector dimensions */
int CP; /* number of control vector dimensions */
/* backward compatibility fields */
#if 1
float* PosterState; /* =state_pre->data.fl */
float* PriorState; /* =state_post->data.fl */
float* DynamMatr; /* =transition_matrix->data.fl */
float* MeasurementMatr; /* =measurement_matrix->data.fl */
float* MNCovariance; /* =measurement_noise_cov->data.fl */
float* PNCovariance; /* =process_noise_cov->data.fl */
float* KalmGainMatr; /* =gain->data.fl */
float* PriorErrorCovariance;/* =error_cov_pre->data.fl */
float* PosterErrorCovariance;/* =error_cov_post->data.fl */
float* Temp1; /* temp1->data.fl */
float* Temp2; /* temp2->data.fl */
#endif
CvMat* state_pre; /* predicted state (x'(k)):
x(k)=A*x(k-1)+B*u(k) */
CvMat* state_post; /* corrected state (x(k)):
x(k)=x'(k)+K(k)*(z(k)-H*x'(k)) */
CvMat* transition_matrix; /* state transition matrix (A) */
CvMat* control_matrix; /* control matrix (B)
(it is not used if there is no control)*/
CvMat* measurement_matrix; /* measurement matrix (H) */
CvMat* process_noise_cov; /* process noise covariance matrix (Q) */
CvMat* measurement_noise_cov; /* measurement noise covariance matrix (R) */
CvMat* error_cov_pre; /* priori error estimate covariance matrix (P'(k)):
P'(k)=A*P(k-1)*At + Q)*/
CvMat* gain; /* Kalman gain matrix (K(k)):
K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)*/
CvMat* error_cov_post; /* posteriori error estimate covariance matrix (P(k)):
P(k)=(I-K(k)*H)*P'(k) */
CvMat* temp1; /* temporary matrices */
CvMat* temp2;
CvMat* temp3;
CvMat* temp4;
CvMat* temp5;
} CvKalman;
/* Creates Kalman filter and sets A, B, Q, R and state to some initial values */
CVAPI(CvKalman*) cvCreateKalman( int dynam_params, int measure_params,
int control_params CV_DEFAULT(0));
/* Releases Kalman filter state */
CVAPI(void) cvReleaseKalman( CvKalman** kalman);
/* Updates Kalman filter by time (predicts future state of the system) */
CVAPI(const CvMat*) cvKalmanPredict( CvKalman* kalman,
const CvMat* control CV_DEFAULT(NULL));
/* Updates Kalman filter by measurement
(corrects state of the system and internal matrices) */
CVAPI(const CvMat*) cvKalmanCorrect( CvKalman* kalman, const CvMat* measurement );
#define cvKalmanUpdateByTime cvKalmanPredict
#define cvKalmanUpdateByMeasurement cvKalmanCorrect
#ifdef __cplusplus
}
#include "opencv2/core.hpp"
#include "opencv2/imgproc.hpp"
namespace cv
{
//! updates motion history image using the current silhouette
CV_EXPORTS_W void updateMotionHistory( InputArray silhouette, InputOutputArray mhi,
double timestamp, double duration );
//! @addtogroup video_track
//! @{
//! computes the motion gradient orientation image from the motion history image
CV_EXPORTS_W void calcMotionGradient( InputArray mhi, OutputArray mask,
OutputArray orientation,
double delta1, double delta2,
int apertureSize=3 );
enum { OPTFLOW_USE_INITIAL_FLOW = 4,
OPTFLOW_LK_GET_MIN_EIGENVALS = 8,
OPTFLOW_FARNEBACK_GAUSSIAN = 256
};
//! computes the global orientation of the selected motion history image part
CV_EXPORTS_W double calcGlobalOrientation( InputArray orientation, InputArray mask,
InputArray mhi, double timestamp,
double duration );
/** @brief Finds an object center, size, and orientation.
CV_EXPORTS_W void segmentMotion(InputArray mhi, OutputArray segmask,
CV_OUT vector<Rect>& boundingRects,
double timestamp, double segThresh);
@param probImage Back projection of the object histogram. See calcBackProject.
@param window Initial search window.
@param criteria Stop criteria for the underlying meanShift.
returns
(in old interfaces) Number of iterations CAMSHIFT took to converge
The function implements the CAMSHIFT object tracking algorithm @cite Bradski98 . First, it finds an
object center using meanShift and then adjusts the window size and finds the optimal rotation. The
function returns the rotated rectangle structure that includes the object position, size, and
orientation. The next position of the search window can be obtained with RotatedRect::boundingRect()
//! updates the object tracking window using CAMSHIFT algorithm
CV_EXPORTS_W RotatedRect CamShift( InputArray probImage, CV_OUT CV_IN_OUT Rect& window,
See the OpenCV sample camshiftdemo.c that tracks colored objects.
@note
- (Python) A sample explaining the camshift tracking algorithm can be found at
opencv_source_code/samples/python/camshift.py
*/
CV_EXPORTS_W RotatedRect CamShift( InputArray probImage, CV_IN_OUT Rect& window,
TermCriteria criteria );
//! updates the object tracking window using meanshift algorithm
CV_EXPORTS_W int meanShift( InputArray probImage, CV_OUT CV_IN_OUT Rect& window,
TermCriteria criteria );
/** @brief Finds an object on a back projection image.
/*!
Kalman filter.
@param probImage Back projection of the object histogram. See calcBackProject for details.
@param window Initial search window.
@param criteria Stop criteria for the iterative search algorithm.
returns
: Number of iterations CAMSHIFT took to converge.
The function implements the iterative object search algorithm. It takes the input back projection of
an object and the initial position. The mass center in window of the back projection image is
computed and the search window center shifts to the mass center. The procedure is repeated until the
specified number of iterations criteria.maxCount is done or until the window center shifts by less
than criteria.epsilon. The algorithm is used inside CamShift and, unlike CamShift , the search
window size or orientation do not change during the search. You can simply pass the output of
calcBackProject to this function. But better results can be obtained if you pre-filter the back
projection and remove the noise. For example, you can do this by retrieving connected components
with findContours , throwing away contours with small area ( contourArea ), and rendering the
remaining contours with drawContours.
The class implements standard Kalman filter \url{http://en.wikipedia.org/wiki/Kalman_filter}.
However, you can modify KalmanFilter::transitionMatrix, KalmanFilter::controlMatrix and
KalmanFilter::measurementMatrix to get the extended Kalman filter functionality.
*/
@note
- A mean-shift tracking sample can be found at opencv_source_code/samples/cpp/camshiftdemo.cpp
*/
CV_EXPORTS_W int meanShift( InputArray probImage, CV_IN_OUT Rect& window, TermCriteria criteria );
/** @brief Constructs the image pyramid which can be passed to calcOpticalFlowPyrLK.
@param img 8-bit input image.
@param pyramid output pyramid.
@param winSize window size of optical flow algorithm. Must be not less than winSize argument of
calcOpticalFlowPyrLK. It is needed to calculate required padding for pyramid levels.
@param maxLevel 0-based maximal pyramid level number.
@param withDerivatives set to precompute gradients for the every pyramid level. If pyramid is
constructed without the gradients then calcOpticalFlowPyrLK will calculate them internally.
@param pyrBorder the border mode for pyramid layers.
@param derivBorder the border mode for gradients.
@param tryReuseInputImage put ROI of input image into the pyramid if possible. You can pass false
to force data copying.
@return number of levels in constructed pyramid. Can be less than maxLevel.
*/
CV_EXPORTS_W int buildOpticalFlowPyramid( InputArray img, OutputArrayOfArrays pyramid,
Size winSize, int maxLevel, bool withDerivatives = true,
int pyrBorder = BORDER_REFLECT_101,
int derivBorder = BORDER_CONSTANT,
bool tryReuseInputImage = true );
/** @brief Calculates an optical flow for a sparse feature set using the iterative Lucas-Kanade method with
pyramids.
@param prevImg first 8-bit input image or pyramid constructed by buildOpticalFlowPyramid.
@param nextImg second input image or pyramid of the same size and the same type as prevImg.
@param prevPts vector of 2D points for which the flow needs to be found; point coordinates must be
single-precision floating-point numbers.
@param nextPts output vector of 2D points (with single-precision floating-point coordinates)
containing the calculated new positions of input features in the second image; when
OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input.
@param status output status vector (of unsigned chars); each element of the vector is set to 1 if
the flow for the corresponding features has been found, otherwise, it is set to 0.
@param err output vector of errors; each element of the vector is set to an error for the
corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn't
found then the error is not defined (use the status parameter to find such cases).
@param winSize size of the search window at each pyramid level.
@param maxLevel 0-based maximal pyramid level number; if set to 0, pyramids are not used (single
level), if set to 1, two levels are used, and so on; if pyramids are passed to input then
algorithm will use as many levels as pyramids have but no more than maxLevel.
@param criteria parameter, specifying the termination criteria of the iterative search algorithm
(after the specified maximum number of iterations criteria.maxCount or when the search window
moves by less than criteria.epsilon.
@param flags operation flags:
- **OPTFLOW_USE_INITIAL_FLOW** uses initial estimations, stored in nextPts; if the flag is
not set, then prevPts is copied to nextPts and is considered the initial estimate.
- **OPTFLOW_LK_GET_MIN_EIGENVALS** use minimum eigen values as an error measure (see
minEigThreshold description); if the flag is not set, then L1 distance between patches
around the original and a moved point, divided by number of pixels in a window, is used as a
error measure.
@param minEigThreshold the algorithm calculates the minimum eigen value of a 2x2 normal matrix of
optical flow equations (this matrix is called a spatial gradient matrix in @cite Bouguet00), divided
by number of pixels in a window; if this value is less than minEigThreshold, then a corresponding
feature is filtered out and its flow is not processed, so it allows to remove bad points and get a
performance boost.
The function implements a sparse iterative version of the Lucas-Kanade optical flow in pyramids. See
@cite Bouguet00 . The function is parallelized with the TBB library.
@note
- An example using the Lucas-Kanade optical flow algorithm can be found at
opencv_source_code/samples/cpp/lkdemo.cpp
- (Python) An example using the Lucas-Kanade optical flow algorithm can be found at
opencv_source_code/samples/python/lk_track.py
- (Python) An example using the Lucas-Kanade tracker for homography matching can be found at
opencv_source_code/samples/python/lk_homography.py
*/
CV_EXPORTS_W void calcOpticalFlowPyrLK( InputArray prevImg, InputArray nextImg,
InputArray prevPts, InputOutputArray nextPts,
OutputArray status, OutputArray err,
Size winSize = Size(21,21), int maxLevel = 3,
TermCriteria criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
int flags = 0, double minEigThreshold = 1e-4 );
/** @brief Computes a dense optical flow using the Gunnar Farneback's algorithm.
@param prev first 8-bit single-channel input image.
@param next second input image of the same size and the same type as prev.
@param flow computed flow image that has the same size as prev and type CV_32FC2.
@param pyr_scale parameter, specifying the image scale (\<1) to build pyramids for each image;
pyr_scale=0.5 means a classical pyramid, where each next layer is twice smaller than the previous
one.
@param levels number of pyramid layers including the initial image; levels=1 means that no extra
layers are created and only the original images are used.
@param winsize averaging window size; larger values increase the algorithm robustness to image
noise and give more chances for fast motion detection, but yield more blurred motion field.
@param iterations number of iterations the algorithm does at each pyramid level.
@param poly_n size of the pixel neighborhood used to find polynomial expansion in each pixel;
larger values mean that the image will be approximated with smoother surfaces, yielding more
robust algorithm and more blurred motion field, typically poly_n =5 or 7.
@param poly_sigma standard deviation of the Gaussian that is used to smooth derivatives used as a
basis for the polynomial expansion; for poly_n=5, you can set poly_sigma=1.1, for poly_n=7, a
good value would be poly_sigma=1.5.
@param flags operation flags that can be a combination of the following:
- **OPTFLOW_USE_INITIAL_FLOW** uses the input flow as an initial flow approximation.
- **OPTFLOW_FARNEBACK_GAUSSIAN** uses the Gaussian \f$\texttt{winsize}\times\texttt{winsize}\f$
filter instead of a box filter of the same size for optical flow estimation; usually, this
option gives z more accurate flow than with a box filter, at the cost of lower speed;
normally, winsize for a Gaussian window should be set to a larger value to achieve the same
level of robustness.
The function finds an optical flow for each prev pixel using the @cite Farneback2003 algorithm so that
\f[\texttt{prev} (y,x) \sim \texttt{next} ( y + \texttt{flow} (y,x)[1], x + \texttt{flow} (y,x)[0])\f]
@note
- An example using the optical flow algorithm described by Gunnar Farneback can be found at
opencv_source_code/samples/cpp/fback.cpp
- (Python) An example using the optical flow algorithm described by Gunnar Farneback can be
found at opencv_source_code/samples/python/opt_flow.py
*/
CV_EXPORTS_W void calcOpticalFlowFarneback( InputArray prev, InputArray next, InputOutputArray flow,
double pyr_scale, int levels, int winsize,
int iterations, int poly_n, double poly_sigma,
int flags );
/** @brief Computes an optimal affine transformation between two 2D point sets.
@param src First input 2D point set stored in std::vector or Mat, or an image stored in Mat.
@param dst Second input 2D point set of the same size and the same type as A, or another image.
@param fullAffine If true, the function finds an optimal affine transformation with no additional
restrictions (6 degrees of freedom). Otherwise, the class of transformations to choose from is
limited to combinations of translation, rotation, and uniform scaling (4 degrees of freedom).
The function finds an optimal affine transform *[A|b]* (a 2 x 3 floating-point matrix) that
approximates best the affine transformation between:
* Two point sets
* Two raster images. In this case, the function first finds some features in the src image and
finds the corresponding features in dst image. After that, the problem is reduced to the first
case.
In case of point sets, the problem is formulated as follows: you need to find a 2x2 matrix *A* and
2x1 vector *b* so that:
\f[[A^*|b^*] = arg \min _{[A|b]} \sum _i \| \texttt{dst}[i] - A { \texttt{src}[i]}^T - b \| ^2\f]
where src[i] and dst[i] are the i-th points in src and dst, respectively
\f$[A|b]\f$ can be either arbitrary (when fullAffine=true ) or have a form of
\f[\begin{bmatrix} a_{11} & a_{12} & b_1 \\ -a_{12} & a_{11} & b_2 \end{bmatrix}\f]
when fullAffine=false.
@sa
estimateAffine2D, estimateAffinePartial2D, getAffineTransform, getPerspectiveTransform, findHomography
*/
CV_EXPORTS_W Mat estimateRigidTransform( InputArray src, InputArray dst, bool fullAffine );
enum
{
MOTION_TRANSLATION = 0,
MOTION_EUCLIDEAN = 1,
MOTION_AFFINE = 2,
MOTION_HOMOGRAPHY = 3
};
/** @brief Finds the geometric transform (warp) between two images in terms of the ECC criterion @cite EP08 .
@param templateImage single-channel template image; CV_8U or CV_32F array.
@param inputImage single-channel input image which should be warped with the final warpMatrix in
order to provide an image similar to templateImage, same type as temlateImage.
@param warpMatrix floating-point \f$2\times 3\f$ or \f$3\times 3\f$ mapping matrix (warp).
@param motionType parameter, specifying the type of motion:
- **MOTION_TRANSLATION** sets a translational motion model; warpMatrix is \f$2\times 3\f$ with
the first \f$2\times 2\f$ part being the unity matrix and the rest two parameters being
estimated.
- **MOTION_EUCLIDEAN** sets a Euclidean (rigid) transformation as motion model; three
parameters are estimated; warpMatrix is \f$2\times 3\f$.
- **MOTION_AFFINE** sets an affine motion model (DEFAULT); six parameters are estimated;
warpMatrix is \f$2\times 3\f$.
- **MOTION_HOMOGRAPHY** sets a homography as a motion model; eight parameters are
estimated;\`warpMatrix\` is \f$3\times 3\f$.
@param criteria parameter, specifying the termination criteria of the ECC algorithm;
criteria.epsilon defines the threshold of the increment in the correlation coefficient between two
iterations (a negative criteria.epsilon makes criteria.maxcount the only termination criterion).
Default values are shown in the declaration above.
@param inputMask An optional mask to indicate valid values of inputImage.
The function estimates the optimum transformation (warpMatrix) with respect to ECC criterion
(@cite EP08), that is
\f[\texttt{warpMatrix} = \texttt{warpMatrix} = \arg\max_{W} \texttt{ECC}(\texttt{templateImage}(x,y),\texttt{inputImage}(x',y'))\f]
where
\f[\begin{bmatrix} x' \\ y' \end{bmatrix} = W \cdot \begin{bmatrix} x \\ y \\ 1 \end{bmatrix}\f]
(the equation holds with homogeneous coordinates for homography). It returns the final enhanced
correlation coefficient, that is the correlation coefficient between the template image and the
final warped input image. When a \f$3\times 3\f$ matrix is given with motionType =0, 1 or 2, the third
row is ignored.
Unlike findHomography and estimateRigidTransform, the function findTransformECC implements an
area-based alignment that builds on intensity similarities. In essence, the function updates the
initial transformation that roughly aligns the images. If this information is missing, the identity
warp (unity matrix) should be given as input. Note that if images undergo strong
displacements/rotations, an initial transformation that roughly aligns the images is necessary
(e.g., a simple euclidean/similarity transform that allows for the images showing the same image
content approximately). Use inverse warping in the second image to take an image close to the first
one, i.e. use the flag WARP_INVERSE_MAP with warpAffine or warpPerspective. See also the OpenCV
sample image_alignment.cpp that demonstrates the use of the function. Note that the function throws
an exception if algorithm does not converges.
@sa
estimateAffine2D, estimateAffinePartial2D, findHomography
*/
CV_EXPORTS_W double findTransformECC( InputArray templateImage, InputArray inputImage,
InputOutputArray warpMatrix, int motionType = MOTION_AFFINE,
TermCriteria criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 50, 0.001),
InputArray inputMask = noArray());
/** @brief Kalman filter class.
The class implements a standard Kalman filter <http://en.wikipedia.org/wiki/Kalman_filter>,
@cite Welch95 . However, you can modify transitionMatrix, controlMatrix, and measurementMatrix to get
an extended Kalman filter functionality. See the OpenCV sample kalman.cpp.
@note
- An example using the standard Kalman filter can be found at
opencv_source_code/samples/cpp/kalman.cpp
*/
class CV_EXPORTS_W KalmanFilter
{
public:
//! the default constructor
/** @brief The constructors.
@note In C API when CvKalman\* kalmanFilter structure is not needed anymore, it should be released
with cvReleaseKalman(&kalmanFilter)
*/
CV_WRAP KalmanFilter();
//! the full constructor taking the dimensionality of the state, of the measurement and of the control vector
CV_WRAP KalmanFilter(int dynamParams, int measureParams, int controlParams=0, int type=CV_32F);
//! re-initializes Kalman filter. The previous content is destroyed.
void init(int dynamParams, int measureParams, int controlParams=0, int type=CV_32F);
/** @overload
@param dynamParams Dimensionality of the state.
@param measureParams Dimensionality of the measurement.
@param controlParams Dimensionality of the control vector.
@param type Type of the created matrices that should be CV_32F or CV_64F.
*/
CV_WRAP KalmanFilter( int dynamParams, int measureParams, int controlParams = 0, int type = CV_32F );
//! computes predicted state
CV_WRAP const Mat& predict(const Mat& control=Mat());
//! updates the predicted state from the measurement
CV_WRAP const Mat& correct(const Mat& measurement);
/** @brief Re-initializes Kalman filter. The previous content is destroyed.
Mat statePre; //!< predicted state (x'(k)): x(k)=A*x(k-1)+B*u(k)
Mat statePost; //!< corrected state (x(k)): x(k)=x'(k)+K(k)*(z(k)-H*x'(k))
Mat transitionMatrix; //!< state transition matrix (A)
Mat controlMatrix; //!< control matrix (B) (not used if there is no control)
Mat measurementMatrix; //!< measurement matrix (H)
Mat processNoiseCov; //!< process noise covariance matrix (Q)
Mat measurementNoiseCov;//!< measurement noise covariance matrix (R)
Mat errorCovPre; //!< priori error estimate covariance matrix (P'(k)): P'(k)=A*P(k-1)*At + Q)*/
Mat gain; //!< Kalman gain matrix (K(k)): K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)
Mat errorCovPost; //!< posteriori error estimate covariance matrix (P(k)): P(k)=(I-K(k)*H)*P'(k)
@param dynamParams Dimensionality of the state.
@param measureParams Dimensionality of the measurement.
@param controlParams Dimensionality of the control vector.
@param type Type of the created matrices that should be CV_32F or CV_64F.
*/
void init( int dynamParams, int measureParams, int controlParams = 0, int type = CV_32F );
/** @brief Computes a predicted state.
@param control The optional input control
*/
CV_WRAP const Mat& predict( const Mat& control = Mat() );
/** @brief Updates the predicted state from the measurement.
@param measurement The measured system parameters
*/
CV_WRAP const Mat& correct( const Mat& measurement );
CV_PROP_RW Mat statePre; //!< predicted state (x'(k)): x(k)=A*x(k-1)+B*u(k)
CV_PROP_RW Mat statePost; //!< corrected state (x(k)): x(k)=x'(k)+K(k)*(z(k)-H*x'(k))
CV_PROP_RW Mat transitionMatrix; //!< state transition matrix (A)
CV_PROP_RW Mat controlMatrix; //!< control matrix (B) (not used if there is no control)
CV_PROP_RW Mat measurementMatrix; //!< measurement matrix (H)
CV_PROP_RW Mat processNoiseCov; //!< process noise covariance matrix (Q)
CV_PROP_RW Mat measurementNoiseCov;//!< measurement noise covariance matrix (R)
CV_PROP_RW Mat errorCovPre; //!< priori error estimate covariance matrix (P'(k)): P'(k)=A*P(k-1)*At + Q)*/
CV_PROP_RW Mat gain; //!< Kalman gain matrix (K(k)): K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)
CV_PROP_RW Mat errorCovPost; //!< posteriori error estimate covariance matrix (P(k)): P(k)=(I-K(k)*H)*P'(k)
// temporary matrices
Mat temp1;
@@ -296,78 +381,246 @@ public:
Mat temp5;
};
enum
{
OPTFLOW_USE_INITIAL_FLOW = CV_LKFLOW_INITIAL_GUESSES,
OPTFLOW_LK_GET_MIN_EIGENVALS = CV_LKFLOW_GET_MIN_EIGENVALS,
OPTFLOW_FARNEBACK_GAUSSIAN = 256
};
//! constructs a pyramid which can be used as input for calcOpticalFlowPyrLK
CV_EXPORTS_W int buildOpticalFlowPyramid(InputArray img, OutputArrayOfArrays pyramid,
Size winSize, int maxLevel, bool withDerivatives = true,
int pyrBorder = BORDER_REFLECT_101, int derivBorder = BORDER_CONSTANT,
bool tryReuseInputImage = true);
//! computes sparse optical flow using multi-scale Lucas-Kanade algorithm
CV_EXPORTS_W void calcOpticalFlowPyrLK( InputArray prevImg, InputArray nextImg,
InputArray prevPts, CV_OUT InputOutputArray nextPts,
OutputArray status, OutputArray err,
Size winSize=Size(21,21), int maxLevel=3,
TermCriteria criteria=TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
int flags=0, double minEigThreshold=1e-4);
//! computes dense optical flow using Farneback algorithm
CV_EXPORTS_W void calcOpticalFlowFarneback( InputArray prev, InputArray next,
CV_OUT InputOutputArray flow, double pyr_scale, int levels, int winsize,
int iterations, int poly_n, double poly_sigma, int flags );
//! estimates the best-fit Euqcidean, similarity, affine or perspective transformation
// that maps one 2D point set to another or one image to another.
CV_EXPORTS_W Mat estimateRigidTransform( InputArray src, InputArray dst,
bool fullAffine);
//! computes dense optical flow using Simple Flow algorithm
CV_EXPORTS_W void calcOpticalFlowSF(Mat& from,
Mat& to,
Mat& flow,
int layers,
int averaging_block_size,
int max_flow);
CV_EXPORTS_W void calcOpticalFlowSF(Mat& from,
Mat& to,
Mat& flow,
int layers,
int averaging_block_size,
int max_flow,
double sigma_dist,
double sigma_color,
int postprocess_window,
double sigma_dist_fix,
double sigma_color_fix,
double occ_thr,
int upscale_averaging_radius,
double upscale_sigma_dist,
double upscale_sigma_color,
double speed_up_thr);
class CV_EXPORTS DenseOpticalFlow : public Algorithm
class CV_EXPORTS_W DenseOpticalFlow : public Algorithm
{
public:
virtual void calc(InputArray I0, InputArray I1, InputOutputArray flow) = 0;
virtual void collectGarbage() = 0;
/** @brief Calculates an optical flow.
@param I0 first 8-bit single-channel input image.
@param I1 second input image of the same size and the same type as prev.
@param flow computed flow image that has the same size as prev and type CV_32FC2.
*/
CV_WRAP virtual void calc( InputArray I0, InputArray I1, InputOutputArray flow ) = 0;
/** @brief Releases all inner buffers.
*/
CV_WRAP virtual void collectGarbage() = 0;
};
// Implementation of the Zach, Pock and Bischof Dual TV-L1 Optical Flow method
//
// see reference:
// [1] C. Zach, T. Pock and H. Bischof, "A Duality Based Approach for Realtime TV-L1 Optical Flow".
// [2] Javier Sanchez, Enric Meinhardt-Llopis and Gabriele Facciolo. "TV-L1 Optical Flow Estimation".
CV_EXPORTS Ptr<DenseOpticalFlow> createOptFlow_DualTVL1();
/** @brief Base interface for sparse optical flow algorithms.
*/
class CV_EXPORTS_W SparseOpticalFlow : public Algorithm
{
public:
/** @brief Calculates a sparse optical flow.
}
#endif
@param prevImg First input image.
@param nextImg Second input image of the same size and the same type as prevImg.
@param prevPts Vector of 2D points for which the flow needs to be found.
@param nextPts Output vector of 2D points containing the calculated new positions of input features in the second image.
@param status Output status vector. Each element of the vector is set to 1 if the
flow for the corresponding features has been found. Otherwise, it is set to 0.
@param err Optional output vector that contains error response for each point (inverse confidence).
*/
CV_WRAP virtual void calc(InputArray prevImg, InputArray nextImg,
InputArray prevPts, InputOutputArray nextPts,
OutputArray status,
OutputArray err = cv::noArray()) = 0;
};
/** @brief "Dual TV L1" Optical Flow Algorithm.
The class implements the "Dual TV L1" optical flow algorithm described in @cite Zach2007 and
@cite Javier2012 .
Here are important members of the class that control the algorithm, which you can set after
constructing the class instance:
- member double tau
Time step of the numerical scheme.
- member double lambda
Weight parameter for the data term, attachment parameter. This is the most relevant
parameter, which determines the smoothness of the output. The smaller this parameter is,
the smoother the solutions we obtain. It depends on the range of motions of the images, so
its value should be adapted to each image sequence.
- member double theta
Weight parameter for (u - v)\^2, tightness parameter. It serves as a link between the
attachment and the regularization terms. In theory, it should have a small value in order
to maintain both parts in correspondence. The method is stable for a large range of values
of this parameter.
- member int nscales
Number of scales used to create the pyramid of images.
- member int warps
Number of warpings per scale. Represents the number of times that I1(x+u0) and grad(
I1(x+u0) ) are computed per scale. This is a parameter that assures the stability of the
method. It also affects the running time, so it is a compromise between speed and
accuracy.
- member double epsilon
Stopping criterion threshold used in the numerical scheme, which is a trade-off between
precision and running time. A small value will yield more accurate solutions at the
expense of a slower convergence.
- member int iterations
Stopping criterion iterations number used in the numerical scheme.
C. Zach, T. Pock and H. Bischof, "A Duality Based Approach for Realtime TV-L1 Optical Flow".
Javier Sanchez, Enric Meinhardt-Llopis and Gabriele Facciolo. "TV-L1 Optical Flow Estimation".
*/
class CV_EXPORTS_W DualTVL1OpticalFlow : public DenseOpticalFlow
{
public:
//! @brief Time step of the numerical scheme
/** @see setTau */
CV_WRAP virtual double getTau() const = 0;
/** @copybrief getTau @see getTau */
CV_WRAP virtual void setTau(double val) = 0;
//! @brief Weight parameter for the data term, attachment parameter
/** @see setLambda */
CV_WRAP virtual double getLambda() const = 0;
/** @copybrief getLambda @see getLambda */
CV_WRAP virtual void setLambda(double val) = 0;
//! @brief Weight parameter for (u - v)^2, tightness parameter
/** @see setTheta */
CV_WRAP virtual double getTheta() const = 0;
/** @copybrief getTheta @see getTheta */
CV_WRAP virtual void setTheta(double val) = 0;
//! @brief coefficient for additional illumination variation term
/** @see setGamma */
CV_WRAP virtual double getGamma() const = 0;
/** @copybrief getGamma @see getGamma */
CV_WRAP virtual void setGamma(double val) = 0;
//! @brief Number of scales used to create the pyramid of images
/** @see setScalesNumber */
CV_WRAP virtual int getScalesNumber() const = 0;
/** @copybrief getScalesNumber @see getScalesNumber */
CV_WRAP virtual void setScalesNumber(int val) = 0;
//! @brief Number of warpings per scale
/** @see setWarpingsNumber */
CV_WRAP virtual int getWarpingsNumber() const = 0;
/** @copybrief getWarpingsNumber @see getWarpingsNumber */
CV_WRAP virtual void setWarpingsNumber(int val) = 0;
//! @brief Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time
/** @see setEpsilon */
CV_WRAP virtual double getEpsilon() const = 0;
/** @copybrief getEpsilon @see getEpsilon */
CV_WRAP virtual void setEpsilon(double val) = 0;
//! @brief Inner iterations (between outlier filtering) used in the numerical scheme
/** @see setInnerIterations */
CV_WRAP virtual int getInnerIterations() const = 0;
/** @copybrief getInnerIterations @see getInnerIterations */
CV_WRAP virtual void setInnerIterations(int val) = 0;
//! @brief Outer iterations (number of inner loops) used in the numerical scheme
/** @see setOuterIterations */
CV_WRAP virtual int getOuterIterations() const = 0;
/** @copybrief getOuterIterations @see getOuterIterations */
CV_WRAP virtual void setOuterIterations(int val) = 0;
//! @brief Use initial flow
/** @see setUseInitialFlow */
CV_WRAP virtual bool getUseInitialFlow() const = 0;
/** @copybrief getUseInitialFlow @see getUseInitialFlow */
CV_WRAP virtual void setUseInitialFlow(bool val) = 0;
//! @brief Step between scales (<1)
/** @see setScaleStep */
CV_WRAP virtual double getScaleStep() const = 0;
/** @copybrief getScaleStep @see getScaleStep */
CV_WRAP virtual void setScaleStep(double val) = 0;
//! @brief Median filter kernel size (1 = no filter) (3 or 5)
/** @see setMedianFiltering */
CV_WRAP virtual int getMedianFiltering() const = 0;
/** @copybrief getMedianFiltering @see getMedianFiltering */
CV_WRAP virtual void setMedianFiltering(int val) = 0;
/** @brief Creates instance of cv::DualTVL1OpticalFlow*/
CV_WRAP static Ptr<DualTVL1OpticalFlow> create(
double tau = 0.25,
double lambda = 0.15,
double theta = 0.3,
int nscales = 5,
int warps = 5,
double epsilon = 0.01,
int innnerIterations = 30,
int outerIterations = 10,
double scaleStep = 0.8,
double gamma = 0.0,
int medianFiltering = 5,
bool useInitialFlow = false);
};
/** @brief Creates instance of cv::DenseOpticalFlow
*/
CV_EXPORTS_W Ptr<DualTVL1OpticalFlow> createOptFlow_DualTVL1();
/** @brief Class computing a dense optical flow using the Gunnar Farneback’s algorithm.
*/
class CV_EXPORTS_W FarnebackOpticalFlow : public DenseOpticalFlow
{
public:
CV_WRAP virtual int getNumLevels() const = 0;
CV_WRAP virtual void setNumLevels(int numLevels) = 0;
CV_WRAP virtual double getPyrScale() const = 0;
CV_WRAP virtual void setPyrScale(double pyrScale) = 0;
CV_WRAP virtual bool getFastPyramids() const = 0;
CV_WRAP virtual void setFastPyramids(bool fastPyramids) = 0;
CV_WRAP virtual int getWinSize() const = 0;
CV_WRAP virtual void setWinSize(int winSize) = 0;
CV_WRAP virtual int getNumIters() const = 0;
CV_WRAP virtual void setNumIters(int numIters) = 0;
CV_WRAP virtual int getPolyN() const = 0;
CV_WRAP virtual void setPolyN(int polyN) = 0;
CV_WRAP virtual double getPolySigma() const = 0;
CV_WRAP virtual void setPolySigma(double polySigma) = 0;
CV_WRAP virtual int getFlags() const = 0;
CV_WRAP virtual void setFlags(int flags) = 0;
CV_WRAP static Ptr<FarnebackOpticalFlow> create(
int numLevels = 5,
double pyrScale = 0.5,
bool fastPyramids = false,
int winSize = 13,
int numIters = 10,
int polyN = 5,
double polySigma = 1.1,
int flags = 0);
};
/** @brief Class used for calculating a sparse optical flow.
The class can calculate an optical flow for a sparse feature set using the
iterative Lucas-Kanade method with pyramids.
@sa calcOpticalFlowPyrLK
*/
class CV_EXPORTS_W SparsePyrLKOpticalFlow : public SparseOpticalFlow
{
public:
CV_WRAP virtual Size getWinSize() const = 0;
CV_WRAP virtual void setWinSize(Size winSize) = 0;
CV_WRAP virtual int getMaxLevel() const = 0;
CV_WRAP virtual void setMaxLevel(int maxLevel) = 0;
CV_WRAP virtual TermCriteria getTermCriteria() const = 0;
CV_WRAP virtual void setTermCriteria(TermCriteria& crit) = 0;
CV_WRAP virtual int getFlags() const = 0;
CV_WRAP virtual void setFlags(int flags) = 0;
CV_WRAP virtual double getMinEigThreshold() const = 0;
CV_WRAP virtual void setMinEigThreshold(double minEigThreshold) = 0;
CV_WRAP static Ptr<SparsePyrLKOpticalFlow> create(
Size winSize = Size(21, 21),
int maxLevel = 3, TermCriteria crit =
TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
int flags = 0,
double minEigThreshold = 1e-4);
};
//! @} video_track
} // cv
#endif
include/opencv2/video/tracking_c.h
+232
View File
@@ -0,0 +1,232 @@
/*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_TRACKING_C_H
#define OPENCV_TRACKING_C_H
#include "opencv2/imgproc/types_c.h"
#ifdef __cplusplus
extern "C" {
#endif
/** @addtogroup video_c
@{
*/
/****************************************************************************************\
* Motion Analysis *
\****************************************************************************************/
/************************************ optical flow ***************************************/
#define CV_LKFLOW_PYR_A_READY 1
#define CV_LKFLOW_PYR_B_READY 2
#define CV_LKFLOW_INITIAL_GUESSES 4
#define CV_LKFLOW_GET_MIN_EIGENVALS 8
/* It is Lucas & Kanade method, modified to use pyramids.
Also it does several iterations to get optical flow for
every point at every pyramid level.
Calculates optical flow between two images for certain set of points (i.e.
it is a "sparse" optical flow, which is opposite to the previous 3 methods) */
CVAPI(void) cvCalcOpticalFlowPyrLK( const CvArr* prev, const CvArr* curr,
CvArr* prev_pyr, CvArr* curr_pyr,
const CvPoint2D32f* prev_features,
CvPoint2D32f* curr_features,
int count,
CvSize win_size,
int level,
char* status,
float* track_error,
CvTermCriteria criteria,
int flags );
/* Modification of a previous sparse optical flow algorithm to calculate
affine flow */
CVAPI(void) cvCalcAffineFlowPyrLK( const CvArr* prev, const CvArr* curr,
CvArr* prev_pyr, CvArr* curr_pyr,
const CvPoint2D32f* prev_features,
CvPoint2D32f* curr_features,
float* matrices, int count,
CvSize win_size, int level,
char* status, float* track_error,
CvTermCriteria criteria, int flags );
/* Estimate rigid transformation between 2 images or 2 point sets */
CVAPI(int) cvEstimateRigidTransform( const CvArr* A, const CvArr* B,
CvMat* M, int full_affine );
/* Estimate optical flow for each pixel using the two-frame G. Farneback algorithm */
CVAPI(void) cvCalcOpticalFlowFarneback( const CvArr* prev, const CvArr* next,
CvArr* flow, double pyr_scale, int levels,
int winsize, int iterations, int poly_n,
double poly_sigma, int flags );
/********************************* motion templates *************************************/
/****************************************************************************************\
* All the motion template functions work only with single channel images. *
* Silhouette image must have depth IPL_DEPTH_8U or IPL_DEPTH_8S *
* Motion history image must have depth IPL_DEPTH_32F, *
* Gradient mask - IPL_DEPTH_8U or IPL_DEPTH_8S, *
* Motion orientation image - IPL_DEPTH_32F *
* Segmentation mask - IPL_DEPTH_32F *
* All the angles are in degrees, all the times are in milliseconds *
\****************************************************************************************/
/* Updates motion history image given motion silhouette */
CVAPI(void) cvUpdateMotionHistory( const CvArr* silhouette, CvArr* mhi,
double timestamp, double duration );
/* Calculates gradient of the motion history image and fills
a mask indicating where the gradient is valid */
CVAPI(void) cvCalcMotionGradient( const CvArr* mhi, CvArr* mask, CvArr* orientation,
double delta1, double delta2,
int aperture_size CV_DEFAULT(3));
/* Calculates average motion direction within a selected motion region
(region can be selected by setting ROIs and/or by composing a valid gradient mask
with the region mask) */
CVAPI(double) cvCalcGlobalOrientation( const CvArr* orientation, const CvArr* mask,
const CvArr* mhi, double timestamp,
double duration );
/* Splits a motion history image into a few parts corresponding to separate independent motions
(e.g. left hand, right hand) */
CVAPI(CvSeq*) cvSegmentMotion( const CvArr* mhi, CvArr* seg_mask,
CvMemStorage* storage,
double timestamp, double seg_thresh );
/****************************************************************************************\
* Tracking *
\****************************************************************************************/
/* Implements CAMSHIFT algorithm - determines object position, size and orientation
from the object histogram back project (extension of meanshift) */
CVAPI(int) cvCamShift( const CvArr* prob_image, CvRect window,
CvTermCriteria criteria, CvConnectedComp* comp,
CvBox2D* box CV_DEFAULT(NULL) );
/* Implements MeanShift algorithm - determines object position
from the object histogram back project */
CVAPI(int) cvMeanShift( const CvArr* prob_image, CvRect window,
CvTermCriteria criteria, CvConnectedComp* comp );
/*
standard Kalman filter (in G. Welch' and G. Bishop's notation):
x(k)=A*x(k-1)+B*u(k)+w(k) p(w)~N(0,Q)
z(k)=H*x(k)+v(k), p(v)~N(0,R)
*/
typedef struct CvKalman
{
int MP; /* number of measurement vector dimensions */
int DP; /* number of state vector dimensions */
int CP; /* number of control vector dimensions */
/* backward compatibility fields */
#if 1
float* PosterState; /* =state_pre->data.fl */
float* PriorState; /* =state_post->data.fl */
float* DynamMatr; /* =transition_matrix->data.fl */
float* MeasurementMatr; /* =measurement_matrix->data.fl */
float* MNCovariance; /* =measurement_noise_cov->data.fl */
float* PNCovariance; /* =process_noise_cov->data.fl */
float* KalmGainMatr; /* =gain->data.fl */
float* PriorErrorCovariance;/* =error_cov_pre->data.fl */
float* PosterErrorCovariance;/* =error_cov_post->data.fl */
float* Temp1; /* temp1->data.fl */
float* Temp2; /* temp2->data.fl */
#endif
CvMat* state_pre; /* predicted state (x'(k)):
x(k)=A*x(k-1)+B*u(k) */
CvMat* state_post; /* corrected state (x(k)):
x(k)=x'(k)+K(k)*(z(k)-H*x'(k)) */
CvMat* transition_matrix; /* state transition matrix (A) */
CvMat* control_matrix; /* control matrix (B)
(it is not used if there is no control)*/
CvMat* measurement_matrix; /* measurement matrix (H) */
CvMat* process_noise_cov; /* process noise covariance matrix (Q) */
CvMat* measurement_noise_cov; /* measurement noise covariance matrix (R) */
CvMat* error_cov_pre; /* priori error estimate covariance matrix (P'(k)):
P'(k)=A*P(k-1)*At + Q)*/
CvMat* gain; /* Kalman gain matrix (K(k)):
K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)*/
CvMat* error_cov_post; /* posteriori error estimate covariance matrix (P(k)):
P(k)=(I-K(k)*H)*P'(k) */
CvMat* temp1; /* temporary matrices */
CvMat* temp2;
CvMat* temp3;
CvMat* temp4;
CvMat* temp5;
} CvKalman;
/* Creates Kalman filter and sets A, B, Q, R and state to some initial values */
CVAPI(CvKalman*) cvCreateKalman( int dynam_params, int measure_params,
int control_params CV_DEFAULT(0));
/* Releases Kalman filter state */
CVAPI(void) cvReleaseKalman( CvKalman** kalman);
/* Updates Kalman filter by time (predicts future state of the system) */
CVAPI(const CvMat*) cvKalmanPredict( CvKalman* kalman,
const CvMat* control CV_DEFAULT(NULL));
/* Updates Kalman filter by measurement
(corrects state of the system and internal matrices) */
CVAPI(const CvMat*) cvKalmanCorrect( CvKalman* kalman, const CvMat* measurement );
#define cvKalmanUpdateByTime cvKalmanPredict
#define cvKalmanUpdateByMeasurement cvKalmanCorrect
/** @} video_c */
#ifdef __cplusplus
} // extern "C"
#endif
#endif // OPENCV_TRACKING_C_H
include/opencv2/video/video.hpp
+5 -15
View File
@@ -7,11 +7,12 @@
// copy or use the software.
//
//
// License Agreement
// 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,
@@ -40,19 +41,8 @@
//
//M*/
#ifndef __OPENCV_VIDEO_HPP__
#define __OPENCV_VIDEO_HPP__
#include "opencv2/video/tracking.hpp"
#include "opencv2/video/background_segm.hpp"
#ifdef __cplusplus
namespace cv
{
CV_EXPORTS bool initModule_video(void);
}
#ifdef __OPENCV_BUILD
#error this is a compatibility header which should not be used inside the OpenCV library
#endif
#endif //__OPENCV_VIDEO_HPP__
#include "opencv2/video.hpp"