高版本OpenCV KCF调用演示注意事项

      OpenCV的KCF调用，网上已有好多，我接触KCF时，希望利用OpenCV搭建一个KCF示例程序，但从网上粘过来的代码运行时总是报错，“Ptr<Tracker> tracker = Tracker::create();" 这句在编译是出现Tracker中没有create成员”，当时很纳闷，具体的参考的代码如下：

#include <opencv2/core/utility.hpp>  
#include <opencv2/tracking.hpp>  
#include <opencv2/videoio.hpp>  
#include <opencv2/highgui.hpp>  
#include <iostream>  
#include <cstring>  
  
using namespace std;  
using namespace cv;  
  
int main() {  
    // declares all required variables  
    //! [vars]  
    Rect2d roi;  
    Mat frame;  
    //! [vars]  
  
    // create a tracker object  
    Ptr<Tracker> tracker = Tracker::create("KCF");  //在我的OpenCV3.3.0中运行报错找不到成员函数
    //! [create]  
  
    // set input video  
    //! [setvideo]  
    std::string video = "E:\\demo1.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;  
}  

      最后点开OpenCV库源码，发现现在已经没有tracker 这个类了，而是TrackerKCF类了，调用KCF算法的初始化应该使用：Ptr<TrackerKCF> tracker = TrackerKCF::create();

      网上查了一下，Ptr是个Ptr模板类啥的没太明白，参考：

    https://www.jianshu.com/p/0642948df118

    https://www.cnblogs.com/liu-jun/archive/2013/03/24/2979648.html

反正大致就是这样搞是为了安全和泛型编程，以前调用fast角点检测也遇到这个Ptr ，好像比较新版的OpenCV好些地方都采样了这种方式。

    因此高版本的OpenCV中调用KCF的完整代码如下：

#include <opencv2/core/utility.hpp>
#include <opencv2/tracking.hpp>
#include <opencv2/videoio.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
#include <cstring>

using namespace std;
using namespace cv;

int main()
{
    Rect2d roi;
    Mat frame;
    Ptr<TrackerKCF> tracker = TrackerKCF::create();//高版本一般是这样创建KCF的
    string video = ".\KCFTestData\NBA.mov"; //视频流
    //    VideoCapture cap(0);//启用摄像头
    VideoCapture cap(video);
    if (!cap.isOpened())
    {
        return 0;
    }
    cout << "press c to leap current Image" << endl;
    cout << "press q to slect current Image" << endl;
    cout << "press empty key to start track RIO Object" << endl;

    cap >> frame;
    while (1)
    {
        char key = waitKey(1);
        if (key == 'c')  // 按c键跳帧
        {
            cap >> frame;
        }
        if (key == 'q')  // 按q键退出跳帧
        {
            break;
        }
        imshow("first", frame);
    }

    cv::destroyWindow("first");

    roi = selectROI("tracker", frame);

    if (roi.width == 0 || roi.height == 0)
        return 0;

    tracker->init(frame, roi);

    // 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) {
            cv::destroyWindow("tracker");
            break;
        }

        // update the tracking result

        tracker->update(frame, roi);

        // draw the tracked object
        rectangle(frame, roi, Scalar(255, 0, 0), 2, 1);

        // show image with the tracked object
        imshow("tracker", frame);

        //quit on ESC button
        if (char(waitKey(1)) == 'q') {
            cv::destroyWindow("tracker");
            break;
        }
    }
    return 0;
}

      至此就完成了KCF的调用，最后说一句，在库配置正确的前提下，当运行OpenCV程序出错了，很大可能是你没有按照它约定的用法书写程序，此时你可以去看看OpenCV库的函数源码，一般浏览一下类下有没有这个成员函数和成员变量，函数的参数个数对吧等，这样也许就找到问题了。