最簡單的目標跟蹤-模板匹配跟蹤
模板匹配TemplateMatching是在影象中尋找目標的方法之一。原理很簡單,就是在一幅影象中尋找和模板影象(patch)最相似的區域。在OpenCV中有對應的函式可以呼叫:
void matchTemplate( const Mat& image, const Mat& templ, Mat&result, int method );
該函式的功能為,在輸入源影象Sourceimage(I)中滑動框,尋找各個位置與模板影象Template image(T)的相似度,並將結果儲存在結果矩陣result matrix(R)中。該矩陣的每一個點的亮度表示與模板T的匹配程度。然後可以通過函式minMaxLoc定位矩陣R中的最大值(該函式也可以確定最小值)。那通過什麼去評價兩個影象相似呢?這就存在一個評價準則,也就是引數method,它可以有以下值(匹配的方法):
CV_TM_SQDIFF 平方差匹配法,最好的匹配為0,值越大匹配越差;
CV_TM_SQDIFF_NORMED 歸一化平方差匹配法;
CV_TM_CCORR 相關匹配法,採用乘法操作,數值越大表明匹配越好;
CV_TM_CCORR_NORMED 歸一化相關匹配法;
CV_TM_CCOEFF 相關係數匹配法,最好的匹配為1,-1表示最差的匹配;
CV_TM_CCOEFF_NORMED 歸一化相關係數匹配法;
前面兩種方法為越小的值表示越匹配,後四種方法值越大越匹配。
其中:
CV_TM_SQDIFF為:Sumof Squared Difference (SSD) 差值的平方和:
CV_TM_CCORR 為:
SSD可以看成是歐式距離的平方。我們把SSD展開,可以得到:
可以看到,上式的第一項(模板影象T的能量)是一個常數,第三項(影象I區域性的能量)也可以近似一個常數,那麼可以看到,剩下的第二項就是和cross correlation一樣的,也就是互相關項。而SSD是數值越大,相似度越小,cross correlation是數值越大,相似度越大。
參考:
Konstantinos G. Derpanis 等《RelationshipBetween the Sum of Squared Difference (SSD) and Cross Correlation for TemplateMatching》
實現:
simpleTracker.cpp
// Object tracking algorithm using matchTemplate
#include <opencv2/opencv.hpp>
using namespace cv;
using namespace std;
// Global variables
Rect box;
bool drawing_box = false;
bool gotBB = false;
// bounding box mouse callback
void mouseHandler(int event, int x, int y, int flags, void *param){
switch( event ){
case CV_EVENT_MOUSEMOVE:
if (drawing_box){
box.width = x-box.x;
box.height = y-box.y;
}
break;
case CV_EVENT_LBUTTONDOWN:
drawing_box = true;
box = Rect( x, y, 0, 0 );
break;
case CV_EVENT_LBUTTONUP:
drawing_box = false;
if( box.width < 0 ){
box.x += box.width;
box.width *= -1;
}
if( box.height < 0 ){
box.y += box.height;
box.height *= -1;
}
gotBB = true;
break;
}
}
// tracker: get search patches around the last tracking box,
// and find the most similar one
void tracking(Mat frame, Mat &model, Rect &trackBox)
{
Mat gray;
cvtColor(frame, gray, CV_RGB2GRAY);
Rect searchWindow;
searchWindow.width = trackBox.width * 3;
searchWindow.height = trackBox.height * 3;
searchWindow.x = trackBox.x + trackBox.width * 0.5 - searchWindow.width * 0.5;
searchWindow.y = trackBox.y + trackBox.height * 0.5 - searchWindow.height * 0.5;
searchWindow &= Rect(0, 0, frame.cols, frame.rows);
Mat similarity;
matchTemplate(gray(searchWindow), model, similarity, CV_TM_CCOEFF_NORMED);
double mag_r;
Point point;
minMaxLoc(similarity, 0, &mag_r, 0, &point);
trackBox.x = point.x + searchWindow.x;
trackBox.y = point.y + searchWindow.y;
model = gray(trackBox);
}
int main(int argc, char * argv[])
{
VideoCapture capture;
capture.open("david.mpg");
bool fromfile = true;
//Init camera
if (!capture.isOpened())
{
cout << "capture device failed to open!" << endl;
return -1;
}
//Register mouse callback to draw the bounding box
cvNamedWindow("Tracker", CV_WINDOW_AUTOSIZE);
cvSetMouseCallback("Tracker", mouseHandler, NULL );
Mat frame, model;
capture >> frame;
while(!gotBB)
{
if (!fromfile)
capture >> frame;
imshow("Tracker", frame);
if (cvWaitKey(20) == 'q')
return 1;
}
//Remove callback
cvSetMouseCallback("Tracker", NULL, NULL );
Mat gray;
cvtColor(frame, gray, CV_RGB2GRAY);
model = gray(box);
int frameCount = 0;
while (1)
{
capture >> frame;
if (frame.empty())
return -1;
double t = (double)cvGetTickCount();
frameCount++;
// tracking
tracking(frame, model, box);
// show
stringstream buf;
buf << frameCount;
string num = buf.str();
putText(frame, num, Point(20, 20), FONT_HERSHEY_SIMPLEX, 1, Scalar(0, 0, 255), 3);
rectangle(frame, box, Scalar(0, 0, 255), 3);
imshow("Tracker", frame);
t = (double)cvGetTickCount() - t;
cout << "cost time: " << t / ((double)cvGetTickFrequency()*1000.) << endl;
if ( cvWaitKey(1) == 27 )
break;
}
return 0;
}