我正在尝试使用模板实现实时跟踪。我希望每帧更新模板。我所做的主要修改是：
1）将模板匹配和minmaxLoc分别分成单独的模块，即 TplMatch（）和 minmax（）函数。
2）在 track（）函数中，select_flag始终为true，以便每次迭代都会将新模板复制到“myTemplate”。
3）功能 track（）的最后3行是更新模板（roiImg）。
4）此外，我删除了 track（）函数的所有参数，因为， img 和 roiImg 是全局变量，因此无需将它们传递给函数。
以下是代码：
#include <iostream>
#include "opencv2/opencv.hpp"
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <sstream>
using namespace cv;
using namespace std;
Point point1, point2; /* vertical points of the bounding box */
int drag = 0;
Rect rect; /* bounding box */
Mat img, roiImg; /* roiImg - the part of the image in the bounding box */
int select_flag = 0;
bool go_fast = false;
Mat mytemplate;
///------- template matching -----------------------------------------------------------------------------------------------
Mat TplMatch( Mat &img, Mat &mytemplate )
{
Mat result;
matchTemplate( img, mytemplate, result, CV_TM_SQDIFF_NORMED );
normalize( result, result, 0, 1, NORM_MINMAX, -1, Mat() );
return result;
}
///------- Localizing the best match with minMaxLoc ------------------------------------------------------------------------
Point minmax( Mat &result )
{
double minVal, maxVal;
Point minLoc, maxLoc, matchLoc;
minMaxLoc( result, &minVal, &maxVal, &minLoc, &maxLoc, Mat() );
matchLoc = minLoc;
return matchLoc;
}
///------- tracking --------------------------------------------------------------------------------------------------------
void track()
{
if (select_flag)
{
roiImg.copyTo(mytemplate);
// select_flag = false;
go_fast = true;
}
// imshow( "mytemplate", mytemplate ); waitKey(0);
Mat result = TplMatch( img, mytemplate );
Point match = minmax( result );
rectangle( img, match, Point( match.x + mytemplate.cols , match.y + mytemplate.rows ), CV_RGB(255, 255, 255), 0.5 );
std::cout << "match: " << match << endl;
/// latest match is the new template
Rect ROI = cv::Rect( match.x, match.y, mytemplate.cols, mytemplate.rows );
roiImg = img( ROI );
imshow( "roiImg", roiImg ); //waitKey(0);
}
///------- MouseCallback function ------------------------------------------------------------------------------------------
void mouseHandler(int event, int x, int y, int flags, void *param)
{
if (event == CV_EVENT_LBUTTONDOWN && !drag)
{
/// left button clicked. ROI selection begins
point1 = Point(x, y);
drag = 1;
}
if (event == CV_EVENT_MOUSEMOVE && drag)
{
/// mouse dragged. ROI being selected
Mat img1 = img.clone();
point2 = Point(x, y);
rectangle(img1, point1, point2, CV_RGB(255, 0, 0), 3, 8, 0);
imshow("image", img1);
}
if (event == CV_EVENT_LBUTTONUP && drag)
{
point2 = Point(x, y);
rect = Rect(point1.x, point1.y, x - point1.x, y - point1.y);
drag = 0;
roiImg = img(rect);
// imshow("MOUSE roiImg", roiImg); waitKey(0);
}
if (event == CV_EVENT_LBUTTONUP)
{
/// ROI selected
select_flag = 1;
drag = 0;
}
}
///------- Main() ----------------------------------------------------------------------------------------------------------
int main()
{
int k;
/*
///open webcam
VideoCapture cap(0);
if (!cap.isOpened())
return 1;*/
///open video file
VideoCapture cap;
cap.open( "Megamind.avi" );
if ( !cap.isOpened() )
{ cout << "Unable to open video file" << endl; return -1; }
/*
/// Set video to 320x240
cap.set(CV_CAP_PROP_FRAME_WIDTH, 320);
cap.set(CV_CAP_PROP_FRAME_HEIGHT, 240);*/
cap >> img;
GaussianBlur( img, img, Size(7,7), 3.0 );
imshow( "image", img );
while (1)
{
cap >> img;
if ( img.empty() )
break;
// Flip the frame horizontally and add blur
cv::flip( img, img, 1 );
GaussianBlur( img, img, Size(7,7), 3.0 );
if ( rect.width == 0 && rect.height == 0 )
cvSetMouseCallback( "image", mouseHandler, NULL );
else
track();
imshow("image", img);
// waitKey(100); k = waitKey(75);
k = waitKey(go_fast ? 30 : 10000);
if (k == 27)
break;
}
return 0;
}
未跟踪更新的模板。我无法弄清楚为什么会发生这种情况，因为我每次迭代都会更新我的模板（roiImg）。 minmax（）函数中的匹配值每次都返回相同的点（坐标）。测试视频可在以下网址获得：http://www.youtube.com/watch?v=vpnkk7N2E0Q&feature=youtu.be 请仔细研究并提前指导......非常感谢！
答案 0 :(得分：13)
我从您的问题修订版中获取原始代码：https://stackoverflow.com/revisions/20180073/3
我对原始代码进行了最小的更改，生成的代码如下：
#include <iostream>
#include "opencv2/opencv.hpp"
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <sstream>
using namespace cv;
using namespace std;
Point point1, point2; /* vertical points of the bounding box */
int drag = 0;
Rect rect; /* bounding box */
Mat img, roiImg; /* roiImg - the part of the image in the bounding box */
int select_flag = 0;
bool go_fast = false;
Mat mytemplate;
///------- template matching -----------------------------------------------------------------------------------------------
Mat TplMatch( Mat &img, Mat &mytemplate )
{
Mat result;
matchTemplate( img, mytemplate, result, CV_TM_SQDIFF_NORMED );
normalize( result, result, 0, 1, NORM_MINMAX, -1, Mat() );
return result;
}
///------- Localizing the best match with minMaxLoc ------------------------------------------------------------------------
Point minmax( Mat &result )
{
double minVal, maxVal;
Point minLoc, maxLoc, matchLoc;
minMaxLoc( result, &minVal, &maxVal, &minLoc, &maxLoc, Mat() );
matchLoc = minLoc;
return matchLoc;
}
///------- tracking --------------------------------------------------------------------------------------------------------
void track()
{
if (select_flag)
{
//roiImg.copyTo(mytemplate);
// select_flag = false;
go_fast = true;
}
// imshow( "mytemplate", mytemplate ); waitKey(0);
Mat result = TplMatch( img, mytemplate );
Point match = minmax( result );
rectangle( img, match, Point( match.x + mytemplate.cols , match.y + mytemplate.rows ), CV_RGB(255, 255, 255), 0.5 );
std::cout << "match: " << match << endl;
/// latest match is the new template
Rect ROI = cv::Rect( match.x, match.y, mytemplate.cols, mytemplate.rows );
roiImg = img( ROI );
roiImg.copyTo(mytemplate);
imshow( "roiImg", roiImg ); //waitKey(0);
}
///------- MouseCallback function ------------------------------------------------------------------------------------------
void mouseHandler(int event, int x, int y, int flags, void *param)
{
if (event == CV_EVENT_LBUTTONDOWN && !drag)
{
/// left button clicked. ROI selection begins
point1 = Point(x, y);
drag = 1;
}
if (event == CV_EVENT_MOUSEMOVE && drag)
{
/// mouse dragged. ROI being selected
Mat img1 = img.clone();
point2 = Point(x, y);
rectangle(img1, point1, point2, CV_RGB(255, 0, 0), 3, 8, 0);
imshow("image", img1);
}
if (event == CV_EVENT_LBUTTONUP && drag)
{
point2 = Point(x, y);
rect = Rect(point1.x, point1.y, x - point1.x, y - point1.y);
drag = 0;
roiImg = img(rect);
roiImg.copyTo(mytemplate);
// imshow("MOUSE roiImg", roiImg); waitKey(0);
}
if (event == CV_EVENT_LBUTTONUP)
{
/// ROI selected
select_flag = 1;
drag = 0;
}
}
///------- Main() ----------------------------------------------------------------------------------------------------------
int main()
{
int k;
/*
///open webcam
VideoCapture cap(0);
if (!cap.isOpened())
return 1;*/
///open video file
VideoCapture cap;
cap.open( "Megamind.avi" );
if ( !cap.isOpened() )
{ cout << "Unable to open video file" << endl; return -1; }
/*
/// Set video to 320x240
cap.set(CV_CAP_PROP_FRAME_WIDTH, 320);
cap.set(CV_CAP_PROP_FRAME_HEIGHT, 240);*/
cap >> img;
GaussianBlur( img, img, Size(7,7), 3.0 );
imshow( "image", img );
while (1)
{
cap >> img;
if ( img.empty() )
break;
// Flip the frame horizontally and add blur
cv::flip( img, img, 1 );
GaussianBlur( img, img, Size(7,7), 3.0 );
if ( rect.width == 0 && rect.height == 0 )
cvSetMouseCallback( "image", mouseHandler, NULL );
else
track();
imshow("image", img);
// waitKey(100); k = waitKey(75);
k = waitKey(go_fast ? 30 : 10000);
if (k == 27)
break;
}
return 0;
}
https://www.youtube.com/watch?v=rBCopeneCos的视频显示了对上述程序的测试。
我会避免使用全局变量，因为我认为它们无助于理解问题所在;此外，我还要关注OpenCV的Mat类的浅层和深层副本，1''在answer中写道：
OpenCV的
Mat类只是实际图像数据的标题， 它包含一个指针。operator=复制指针 （以及标题中的其他信息，如图像尺寸） 这样两个Mats共享相同的数据。这意味着修改 一个Mat中的数据也会在另一个中改变它。这被称为a “浅”复制，因为只复制顶层（标题），而不是 下层（数据）。要制作基础数据的副本（称为“深层副本”），请使用
clone()方法。您可以在页面上找到有关它的信息 你链接到。
编辑漂移： 在评论Real-time template matching - OpenCV, C++中，learner询问跟踪偏差。 观看视频https://www.youtube.com/watch?v=rBCopeneCos，我们看到在视频开头，节目正在跟踪女孩的右眼，而在0:15它开始跟踪女孩的眉毛，在0:19它开始跟踪男孩的眉毛并且它从不跟踪女孩的眼睛，例如在0:27它跟踪女孩的右眉，而女孩的右眼在图像中清晰可见。
跟踪眼睛跟踪眉毛的这种漂移在我发布的简单代码中是正常的，解释非常简单：在https://www.youtube.com/watch?v=sGHEu3u9XvI看视频，视频以跟踪开始（内容为扑克牌的黑色矩形，然后我从场景中取出扑克牌，跟踪黑色矩形“漂移”到场景的左下角;毕竟我们正在不断更新模板，所以行为是正确的：程序停止跟踪扑克牌并开始跟踪白色背景，因此你有“漂移”...换句话说，你的{{1}函数将始终返回有效的TplMatch()图像，并且您当前的result实现将始终返回有效的最小值。
答案 1 :(得分：2)
您可以按照OpenCV教程"Template Matching"进行操作。您的track函数可能包含在当前帧中查找模板的代码;一个简单的代码基于matchTemplate和minMaxLoc函数。
与问题的“实时”部分相关的有趣问题是在当前帧和下一帧之间的时间内成功找到匹配项（如果存在）。
修改：
以下快速而肮脏的代码和http://www.youtube.com/watch?v=vpnkk7N2E0Q&feature=youtu.be上的视频显示了我对跟踪的含义。
由于我没有网络摄像头，因此我稍微修改了您的代码，只使用了一个视频，https://code.ros.org/trac/opencv/export/7237/trunk/opencv/samples/cpp/tutorial_code/HighGUI/video-input-psnr-ssim/video/Megamind.avi
然后我添加track功能和一些逻辑来减慢视频速度，直到我选择投资回报率，然后以正常速度播放视频。
#include <iostream>
#include "opencv2/opencv.hpp"
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <sstream>
using namespace cv;
using namespace std;
Point point1, point2; /* vertical points of the bounding box */
int drag = 0;
Rect rect; /* bounding box */
Mat img, roiImg; /* roiImg - the part of the image in the bounding box */
int select_flag = 0;
bool go_fast = false;
Mat mytemplate;
void track(cv::Mat &img, const cv::Mat &templ, const cv::Rect &r )
{
static int n = 0;
if (select_flag)
{
templ.copyTo(mytemplate);
select_flag = false;
go_fast = true;
}
cv::Mat result;
/// Do the Matching and Normalize
matchTemplate( img, mytemplate, result, CV_TM_SQDIFF_NORMED );
normalize( result, result, 0, 1, NORM_MINMAX, -1, Mat() );
/// Localizing the best match with minMaxLoc
double minVal; double maxVal; Point minLoc; Point maxLoc;
Point matchLoc;
minMaxLoc( result, &minVal, &maxVal, &minLoc, &maxLoc, Mat() );
matchLoc = minLoc;
rectangle( img, matchLoc, Point( matchLoc.x + mytemplate.cols , matchLoc.y + mytemplate.rows ), CV_RGB(255, 255, 255), 3 );
std::cout << matchLoc << "\n";
}
///MouseCallback function
void mouseHandler(int event, int x, int y, int flags, void *param)
{
if (event == CV_EVENT_LBUTTONDOWN && !drag)
{
/* left button clicked. ROI selection begins */
point1 = Point(x, y);
drag = 1;
}
if (event == CV_EVENT_MOUSEMOVE && drag)
{
/* mouse dragged. ROI being selected */
Mat img1 = img.clone();
point2 = Point(x, y);
rectangle(img1, point1, point2, CV_RGB(255, 0, 0), 3, 8, 0);
imshow("image", img1);
}
if (event == CV_EVENT_LBUTTONUP && drag)
{
point2 = Point(x, y);
rect = Rect(point1.x, point1.y, x - point1.x, y - point1.y);
drag = 0;
roiImg = img(rect);
}
if (event == CV_EVENT_LBUTTONUP)
{
/* ROI selected */
select_flag = 1;
drag = 0;
}
}
///Main function
int main()
{
int k;
/*
VideoCapture cap(0);
if (!cap.isOpened())
return 1;
*/
VideoCapture cap;
//cap.open("~/Downloads/opencv-2.4.4/samples/cpp/tutorial_code/HighGUI/video-input-psnr-ssim/video/Megamind.avi");
cap.open("./Megamind.avi");
if (!cap.isOpened())
{
printf("Unable to open video file\n");
return -1;
}
/*
// Set video to 320x240
cap.set(CV_CAP_PROP_FRAME_WIDTH, 320);
cap.set(CV_CAP_PROP_FRAME_HEIGHT, 240);
*/
cap >> img;
imshow("image", img);
while (1)
{
cap >> img;
if (img.empty())
break;
if (rect.width == 0 && rect.height == 0)
cvSetMouseCallback("image", mouseHandler, NULL);
else
track(img, roiImg, rect);
if (select_flag == 1)
imshow("Template", roiImg);
imshow("image", img);
k = waitKey(go_fast ? 30 : 10000);
if (k == 27)
break;
}
return 0;
}
答案 2 :(得分：0)
您还可以从此维基百科页面http://en.wikipedia.org/wiki/Video_tracking
开始对该主题进行一般性介绍