[learning opencv]第十章 跟踪与运动：金字塔Lucas-kanade(cvCalcOpticalFlowPyrLK)检测光流

函数解析

cvGoodFeaturesToTrack，http://blog.csdn.net/moc062066/article/details/6634120，和

cvFindCornerSubPix ，http://blog.csdn.net/moc062066/article/details/6634961

两个函数的基础，接下来就是在视频中检测光流（optical flow），经常用的函数是cvCalcOpticalFlowPyrLK，函数说明如下；

Calculates the optical flow for a sparse feature set using the iterative Lucas-Kanade method with
pyramids.

//通过Lucas-Kanade方法与图像金字塔的结合，计算稀疏特征集合的光流

void cvCalcOpticalFlowPyrLK(
							const CvArr* prev,
							const CvArr* curr,
							CvArr* prevPyr,
							CvArr* currPyr,
							const CvPoint2D32f* prevFeatures,
							CvPoint2D32f* currFeatures,
							int count,
							CvSize winSize,
							int level,
							char* status,
							float* track error,
							CvTermCriteria criteria,
							int flags );

prev First frame, at time t  //取t时刻为第一帧

curr Second frame, at time t + dt //第二帧出现在 t + dt时刻

prevPyr Buffer for the pyramid for the first frame. If the pointer is not NULL , the buffer must
have a sufficient size to store the pyramid from level 1 to level level ; the total size of
(image width+8)*image height/3 bytes is sufficient

//第一帧的图像金字塔的缓存之处。如果该指针不为空，该buffer必须有足够的空间来存储从第1层到第level 层的图像金字塔；prevPyr 指针所指的图像/矩阵的大小为(image width+8) * （image height/3） 就足够了。

currPyr Similar to prevPyr, used for the second frame //同上

prevFeatures Array of points for which the flow needs to be found //在数组中定义（当前帧中的）那些点是要在（下一帧）检测的

currFeatures Array of 2D points containing the calculated new positions of the input features
in the second image

//一个二维的点数组，用于存放输入的特征（就是prevFeatures ）在第二帧中的新位置

count Number of feature points//特征点的数目

winSize Size of the search window of each pyramid level //每一层金字塔所有的搜索窗口的大小

level Maximal pyramid level number. If 0 , pyramids are not used (single level), if 1 , two levels
are used, etc

//最多有多少层金字塔。如果是0，就不用图像金字塔，如果是1，就有两层，以此类推。

status Array. Every element of the array is set to 1 if the flow for the corresponding feature has
been found, 0 otherwise

//是一个数组，对应点在第二帧中找到，那该位置就值为1，找不到就值为0.

track error Array of double numbers containing the difference between patches around the
original and moved points. Optional parameter; can be NULL
criteria Specifies when the iteration process of finding the flow for each point on each pyramid
level should be stopped

flags Miscellaneous flags:

CV LKFLOWPyr A READY pyramid for the first frame is precalculated before the call
CV LKFLOWPyr B READY pyramid for the second frame is precalculated before the call
CV LKFLOW INITIAL GUESSES array B contains initial coordinates of features before the
function call

demo：

//cvCaclOpticalFlowPyrLk_demo
//mochen
//2011年7月26日20:23:42

#include 
#include "cv.h"
#include "cxcore.h"
#include "highgui.h"

#pragma comment(lib, "opencv_core220d.lib")
#pragma comment(lib, "opencv_highgui220d.lib")
#pragma comment(lib, "opencv_imgproc220d.lib")
#pragma comment(lib, "opencv_calib3d220d.lib")
#pragma comment(lib, "opencv_features2d220d.lib")
#pragma comment(lib, "opencv_contrib220d.lib")
#pragma comment(lib, "opencv_ml220d.lib") 
#pragma comment(lib, "opencv_video220d.lib") 


#if 0
void cvCalcOpticalFlowPyrLK(
							const CvArr* prev,
							const CvArr* curr,
							CvArr* prevPyr,
							CvArr* currPyr,
							const CvPoint2D32f* prevFeatures,
							CvPoint2D32f* currFeatures,
							int count,
							CvSize winSize,
							int level,
							char* status,
							float* track error,
							CvTermCriteria criteria,
							int flags );
#endif

const int MAX_CORNERS = 1000 ;

int main(int argc,char** argv)
{
	while ( 1 )
	{
		//use webcam 
		CvCapture* cam = cvCaptureFromCAM( CV_CAP_ANY ) ;
		assert( NULL != cam ) ;

		//get a color image 
		IplImage* frame = cvQueryFrame(cam) ;

		CvSize img_sz = cvGetSize(frame);
		const int win_size = 10 ;

		//convert the image to grey image
		IplImage* frame_prev = cvQueryFrame(cam) ;
		IplImage* img_prev = cvCreateImage(img_sz,IPL_DEPTH_8U,1) ;
		cvCvtColor( frame_prev,img_prev ,CV_BGR2GRAY);

		//convert the image to grey image
		IplImage* frame_cur = cvQueryFrame(cam) ;
		IplImage* img_curr = cvCreateImage(img_sz,IPL_DEPTH_8U,1) ;
		cvCvtColor( frame_cur,img_curr ,CV_BGR2GRAY);

		//create a imge to display result
		IplImage* img_res = cvCreateImage(img_sz,IPL_DEPTH_8U,1) ;
		for ( int y = 0 ; y < img_sz.height ; ++y )
		{
			uchar* ptr = (uchar*)( img_res->imageData + y * img_res->widthStep ) ;
			for ( int x = 0 ; x width; ++x )
			{
				ptr[x] = 255 ;
			}
		}

		//get good features 
		IplImage* img_eig = cvCreateImage(img_sz,IPL_DEPTH_32F,1) ;
		IplImage* img_temp = cvCreateImage(img_sz,IPL_DEPTH_32F,1) ;
		int corner_count = MAX_CORNERS ;
		CvPoint2D32f*  features_prev = new CvPoint2D32f[MAX_CORNERS] ;

		cvGoodFeaturesToTrack(
			img_prev,
			img_eig,
			img_temp,
			features_prev,
			&corner_count,
			0.01,
			5.0,
			0,
			3,
			0,
			0.4
			);

		cvFindCornerSubPix(
			img_prev,
			features_prev,
			corner_count,
			cvSize(win_size,win_size),
			cvSize(-1,-1),
			cvTermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER,20,0.03)
			);

		// L-K 
		char feature_found[ MAX_CORNERS ] ;
		float feature_errors[ MAX_CORNERS ] ;

		CvSize pyr_sz = cvSize( frame->width + 8 ,frame->height / 3 ) ;

		IplImage* pyr_prev = cvCreateImage(img_sz,IPL_DEPTH_32F,1) ;
		IplImage* pyr_cur = cvCreateImage(img_sz,IPL_DEPTH_32F,1) ;
		CvPoint2D32f*  features_cur = new CvPoint2D32f[ MAX_CORNERS ] ;

		cvCalcOpticalFlowPyrLK(
			img_prev,
			img_curr,
			pyr_prev,
			pyr_cur,
			features_prev,
			features_cur,
			corner_count,
			cvSize(win_size,win_size),
			5,
			feature_found,
			feature_errors,
			cvTermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER,20,0.3),
			0
			);

		for ( int i = 0 ; i < corner_count ; i++)
		{
			if ( 0 == feature_found[i] || feature_errors[i] > 550 )
			{
				printf("error is %f \n" , feature_errors[i] ) ;
				continue ;
			}

			printf("find it !\n") ;

			CvPoint pt_prev = cvPoint( features_prev[i].x , features_prev[i].y ) ;
			CvPoint pt_cur = cvPoint( features_cur[i].x , features_cur[i].y ) ;

			cvLine( img_res,pt_prev,pt_cur,CV_RGB( 255,0,0),2 );
		}

		const char* window_prev = "img_prev" ;
		const char* window_curr = "img_curr" ;
		const char* window_res = "result" ;
		cvNamedWindow(window_prev,CV_WINDOW_AUTOSIZE);
		cvNamedWindow(window_curr,CV_WINDOW_AUTOSIZE);
		cvNamedWindow(window_res,CV_WINDOW_AUTOSIZE);

		cvShowImage( window_prev,img_prev );
		cvShowImage( window_curr,img_curr );
		cvShowImage( window_res,img_res );

		char opt = cvWaitKey( 10000 ) ;
		if ( 27 == opt )
		{
			break ;
		}

		cvReleaseCapture( &cam );
		cvReleaseImage( &img_curr );
		cvReleaseImage( &img_eig );
		cvReleaseImage( &img_prev );
		cvReleaseImage( &img_res );
		cvReleaseImage( &img_temp );
		cvDestroyAllWindows() ;
	}


	return 0 ;
}

结果：