lea*_*ner 8 c++ opencv image-processing computer-vision template-matching
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分别分离成单独的模块,即TplMatch()和minmax()函数.
2)在track()函数内部,select_flag始终保持为true,以便在每次迭代时将新模板复制到"myTemplate".
3)函数track()的最后3行是更新模板(roiImg).
4)另外,我已经删除了track()函数的任何参数,因为img和roiImg是全局变量,因此不需要将它们传递给函数.
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取:http://www.youtube.com/watch？v = vpnkk7N2E0Q&feature = yououtu.be 请仔细研究并提前指导...非常感谢!
Ale*_*son 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上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,我还要注意OpenCV Mat课程的浅层和深层拷贝,正如1''在他的回答中所写:
OpenCV的
Mat类只是实际图像数据的标题,它包含一个指针.的operator=复制指针(以及在报头中的其他信息,如图像尺寸),使得两个垫共享同一数据.这意味着修改一个Mat中的数据也会在另一个中更改它.这被称为"浅"副本,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"),请使用该
clone()方法.您可以在链接到的页面上找到有关它的信息.
关于漂移的编辑: 在评论实时模板匹配 - OpenCV,C++,学习者询问跟踪漂移.观看视频https://www.youtube.com/watch?v=rBCopeneCos,我们看到在视频开头,该节目正在跟踪女孩的右眼,而在0:15开始跟踪女孩的眉毛, 0:19它开始跟踪男孩的眉毛,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偏差在我发布的简单代码中是正常的,解释非常简单:请参阅https://www.youtube.com/watch?v=sGHEu3u9XvI上的视频,视频从扑克牌的跟踪(黑色矩形的内容)开始,然后从场景中移除扑克牌,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,所以你有"漂移"...换句话说,你的TplMatch()功能将永远返回有效的result图像和您当前的实现minmax()将始终返回有效的最小值.