2014新跟踪算法KCF笔记 --续（代码部分）
KCF跟踪在opencv３.1中集成了，在opencv_contrib/tracking中有，opencv_contrib这个需要重新编译一下opencv３.1才能ｇｅｔ．ｗｉｎｄｏｗｓ下的编译方法如下网址
http://blog.csdn.net/yomo127/article/details/50474955
可以在git上直接下载也可，地址如下
https://github.com/Itseez/opencv_contrib
如果你是直接从ｇｉｔ下载的，可以看到关于ＫＣＦ部分添加的内容如下（ｇｉｔ ｌｏｇ可）
/*---------------STEP 1---------------------*/
/* modify this file
* opencv2/tracking/tracker.hpp
* and put several lines of snippet similar to
* the following:
*/
/*------------------------------------------*/
class CV_EXPORTS_W TrackerKCF : public Tracker
{
public:
struct CV_EXPORTS Params
{
Params();
void read( const FileNode& /*fn*/ );
void write( FileStorage& /*fs*/ ) const;
};
/** @brief Constructor
@param parameters KCF parameters TrackerKCF::Params
*/
BOILERPLATE_CODE("KCF",TrackerKCF);
};
/*---------------STEP 2---------------------*/
/* modify this file
* src/tracker.cpp
* add one line in function
* Ptr Tracker::create( const String& trackerType )
*/
/*------------------------------------------*/
Ptr Tracker::create( const String& trackerType )
{
BOILERPLATE_CODE("MIL",TrackerMIL);
BOILERPLATE_CODE("BOOSTING",TrackerBoosting);
BOILERPLATE_CODE("MEDIANFLOW",TrackerMedianFlow);
BOILERPLATE_CODE("TLD",TrackerTLD);
BOILERPLATE_CODE("KCF",TrackerKCF); // add this line!
return Ptr();
}
/*---------------STEP 3---------------------*/
/* make a new file and paste the snippet below
* and modify it according to your needs.
* also make sure to put the LICENSE part.
* src/trackerKCF.cpp
*/
/*------------------------------------------*/
/*---------------------------
| TrackerKCFModel
|---------------------------*/
namespace cv{
/**
* \brief Implementation of TrackerModel for MIL algorithm
*/
class TrackerKCFModel : public TrackerModel{
public:
TrackerKCFModel(TrackerKCF::Params /*params*/){}
~TrackerKCFModel(){}
protected:
void modelEstimationImpl( const std::vector& responses ){}
void modelUpdateImpl(){}
};
} /* namespace cv */
/*---------------------------
| TrackerKCF
|---------------------------*/
namespace cv{
/*
* Prototype
*/
class TrackerKCFImpl : public TrackerKCF{
public:
TrackerKCFImpl( const TrackerKCF::Params ¶meters = TrackerKCF::Params() );
void read( const FileNode& fn );
void write( FileStorage& fs ) const;
protected:
bool initImpl( const Mat& image, const Rect2d& boundingBox );
bool updateImpl( const Mat& image, Rect2d& boundingBox );
TrackerKCF::Params params;
};
/*
* Constructor
*/
Ptr TrackerKCF::createTracker(const TrackerKCF::Params ¶meters){
return Ptr(new TrackerKCFImpl(parameters));
}
TrackerKCFImpl::TrackerKCFImpl( const TrackerKCF::Params ¶meters ) :
params( parameters )
{
isInit = false;
}
void TrackerKCFImpl::read( const cv::FileNode& fn ){
params.read( fn );
}
void TrackerKCFImpl::write( cv::FileStorage& fs ) const{
params.write( fs );
}
bool TrackerKCFImpl::initImpl( const Mat& image, const Rect2d& boundingBox ){
model=Ptr(new TrackerKCFModel(params));
return true;
}
bool TrackerKCFImpl::updateImpl( const Mat& image, Rect2d& boundingBox ){return true;}
/*
* Parameters
*/
TrackerKCF::Params::Params(){
}
void TrackerKCF::Params::read( const cv::FileNode& fn ){
}
void TrackerKCF::Params::write( cv::FileStorage& fs ) const{
}
} /* namespace cv */ class CV_EXPORTS_W Tracker : public virtual Algorithm
{
public:
virtual ~Tracker();
/** @brief Initialize the tracker with a know bounding box that surrounding the target
@param image The initial frame
@param boundingBox The initial boundig box
@return True if initialization went succesfully, false otherwise
*/
CV_WRAP bool init( const Mat& image, const Rect2d& boundingBox );
/** @brief Update the tracker, find the new most likely bounding box for the target
@param image The current frame
@param boundingBox The boundig box that represent the new target location, if true was returned, not
modified otherwise
@return True means that target was located and false means that tracker cannot locate target in
current frame. Note, that latter *does not* imply that tracker has failed, maybe target is indeed
missing from the frame (say, out of sight)
*/
CV_WRAP bool update( const Mat& image, CV_OUT Rect2d& boundingBox );
/** @brief Creates a tracker by its name.
@param trackerType Tracker type
The following detector types are supported:
- "MIL" -- TrackerMIL
- "BOOSTING" -- TrackerBoosting
*/
CV_WRAP static Ptr create( const String& trackerType );
virtual void read( const FileNode& fn )=0;
virtual void write( FileStorage& fs ) const=0;
Ptr getModel()
{
return model;
}
protected:
virtual bool initImpl( const Mat& image, const Rect2d& boundingBox ) = 0;
virtual bool updateImpl( const Mat& image, Rect2d& boundingBox ) = 0;
bool isInit;
Ptr featureSet;
Ptr sampler;
Ptr model;
}; 下面看一下继承了Tracker这个KCF ｔｒａｃｋｅｒ，这个算法的论文链接在上一篇博客里
/** @brief KCF is a novel tracking framework that utilizes properties of circulant matrix to enhance the processing speed.
* This tracking method is an implementation of @cite KCF_ECCV which is extended to KFC with color-names features (@cite KCF_CN).
* The original paper of KCF is available at
* as well as the matlab implementation. For more information about KCF with color-names features, please refer to
* .
*/
class CV_EXPORTS TrackerKCF : public Tracker
{
public:
/**
* \brief Feature type to be used in the tracking grayscale, colornames, compressed color-names
* The modes available now:
- "GRAY" -- Use grayscale values as the feature
- "CN" -- Color-names feature
*/
enum MODE {
GRAY = (1u << 0),
CN = (1u << 1),
CUSTOM = (1u << 2)
};
struct CV_EXPORTS Params
{
/**
* \brief Constructor
*/
Params();
/**
* \brief Read parameters from file, currently unused
*/
void read(const FileNode& /*fn*/);
/**
* \brief Read parameters from file, currently unused
*/
void write(FileStorage& /*fs*/) const;
double sigma; //!< gaussian kernel bandwidth
double lambda; //!< regularization
double interp_factor; //!< linear interpolation factor for adaptation
double output_sigma_factor; //!< spatial bandwidth (proportional to target)
double pca_learning_rate; //!< compression learning rate
bool resize; //!< activate the resize feature to improve the processing speed
bool split_coeff; //!< split the training coefficients into two matrices
bool wrap_kernel; //!< wrap around the kernel values
bool compress_feature; //!< activate the pca method to compress the features
int max_patch_size; //!< threshold for the ROI size
int compressed_size; //!< feature size after compression
unsigned int desc_pca; //!< compressed descriptors of TrackerKCF::MODE
unsigned int desc_npca; //!< non-compressed descriptors of TrackerKCF::MODE
};
virtual void setFeatureExtractor(void(*)(const Mat, const Rect, Mat&), bool pca_func = false);
/** @brief Constructor
@param parameters KCF parameters TrackerKCF::Params
*/
BOILERPLATE_CODE("KCF", TrackerKCF);
}; 好，上面这些只是介绍了在opencv中 KCF的接口，下面举一个例子来看看怎么调用
//安装配置好opencv3.1
#include
#include
#include
#include
#include
#include
using namespace std;
using namespace cv;
int main( ){
// declares all required variables
//! [vars]
Rect2d roi;
Mat frame;
//! [vars]
// create a tracker object
//! create这个函数的参数也可以是- "MIL" -- TrackerMIL
//! - "BOOSTING" -- TrackerBoosting ,还可以是 "TLD"，"MEDIANFLOW"
Ptr tracker = Tracker::create( "KCF" );
//! [create]
// set input video
//! [setvideo]
std::string video = "test.avi";
VideoCapture cap(video);
//! [setvideo]
// get bounding box
//! [getframe]
cap >> frame;
//! [getframe]
//! [selectroi]选择目标ｒｏｉ以ＧＵＩ的形式
roi=selectROI("tracker",frame);
//! [selectroi]
//quit if ROI was not selected
if(roi.width==0 || roi.height==0)
return 0;
// initialize the tracker
//! [init]
tracker->init(frame,roi);
//! [init]
// perform the tracking process
printf("Start the tracking process\n");
for ( ;; ){
// get frame from the video
cap >> frame;
// stop the program if no more images
if(frame.rows==0 || frame.cols==0)
break;
// update the tracking result
//! [update]
tracker->update(frame,roi);
//! [update]
//! [visualization]
// draw the tracked object
rectangle( frame, roi, Scalar( 255, 0, 0 ), 2, 1 );
// show image with the tracked object
imshow("tracker",frame);
//! [visualization]
//quit on ESC button
if(waitKey(1)==27)
break;
}
return 0;
}