获取已在 OpenCV C++ 中的跟踪算法中跟踪的 ROI 的 x 和 y 像素坐标

Question

我有一个跟踪程序，如下所示。我在视频的第一帧中绘制了两个 ROI（矩形框），并且在整个视频中跟踪了这些 ROI 中的对象。我想获得将在视频中跟踪的 ROI 的 x 和 y 坐标（即视频所有帧中 2 个 ROI 的位置）。我在调试时可以看到这些值，但是当我尝试为每一帧使用 bboxes[0].x,bboxes[0].y,bboxes[1].x,bboxes[1].y 打印它们时，我得到了所有帧的相同值。我在这里做错了什么？

#include <opencv2/opencv.hpp>
#include <opencv2/tracking.hpp>
#include "opencv2/highgui.hpp"
#include "opencv2/core.hpp"
#include "opencv2/imgproc.hpp"

using namespace cv;
using namespace std;

// Convert to string
//#define SSTR( x ) static_cast< std::ostringstream & >( \
( std::ostringstream() << std::dec << x ) ).str()

vector<string> trackerTypes = { "BOOSTING", "MIL", "KCF", "TLD", "MEDIANFLOW", "GOTURN", "MOSSE", "CSRT" };

// create tracker by name
Ptr<Tracker> createTrackerByName(string trackerType)
{
    Ptr<Tracker> tracker;
    if (trackerType == trackerTypes[0])
        tracker = TrackerBoosting::create();
    else if (trackerType == trackerTypes[1])
        tracker = TrackerMIL::create();
    else if (trackerType == trackerTypes[2])
        tracker = TrackerKCF::create();
    else if (trackerType == trackerTypes[3])
        tracker = TrackerTLD::create();
    else if (trackerType == trackerTypes[4])
        tracker = TrackerMedianFlow::create();
    else if (trackerType == trackerTypes[5])
        tracker = TrackerGOTURN::create();
    else if (trackerType == trackerTypes[6])
        tracker = TrackerMOSSE::create();
    else if (trackerType == trackerTypes[7])
        tracker = TrackerCSRT::create();
    else {
        cout << "Incorrect tracker name" << endl;
        cout << "Available trackers are: " << endl;
        for (vector<string>::iterator it = trackerTypes.begin(); it != trackerTypes.end(); ++it)
            std::cout << " " << *it << endl;
    }
    return tracker;
}

// Fill the vector with random colors
void getRandomColors(vector<Scalar> &colors, int numColors)
{
    RNG rng(0);
    for (int i = 0; i < numColors; i++)
        colors.push_back(Scalar(rng.uniform(0, 255), rng.uniform(0, 255), rng.uniform(0, 255)));
}

int main(int argc, char * argv[])
{
    cout << "Available tracking algorithms are:" << endl;
    for (vector<string>::iterator it = trackerTypes.begin(); it != trackerTypes.end(); ++it)
        std::cout << " " << *it << endl;

    string trackerType = "KCF";
    cout << "The Selected tracker is " << trackerType << endl;

    string videoPath = "SS-100_zoom_Trim.mp4";

    // Initialize MultiTracker with tracking algo
    vector<Rect> bboxes;
    Mat frame;
    cv::VideoCapture cap(videoPath);
    //cap.set(CV_CAP_PROP_FRAME_WIDTH, 1280);
    //cap.set(CV_CAP_PROP_FRAME_HEIGHT, 720);

    if (!cap.isOpened())
    {
        cout << "Error opening video file " << videoPath << endl;
        return -1;
    }
    cap >> frame;

    bool showCrosshair = true;
    bool fromCenter = false;

    cv::selectROIs("MultiTracker", frame, bboxes, showCrosshair, fromCenter);

    if (bboxes.size() < 1)
        return 0;

    vector<Scalar> colors;
    getRandomColors(colors, bboxes.size());

    // Create multitracker
    Ptr<MultiTracker> multiTracker = cv::MultiTracker::create();

    // initialize multitracker
    for (int i = 0; i < bboxes.size(); i++)
        multiTracker->add(createTrackerByName(trackerType), frame, Rect2d(bboxes[i]));

    cout << "Started tracking, press ESC to quit." << endl;

    while (cap.isOpened())
    {
        cap >> frame;
        if (frame.empty()) break;

        //update the tracking result with new frame
        multiTracker->update(frame);

        putText(frame, trackerType + " Tracker", Point(100, 20), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(50, 170, 50), 2);

        // draw tracked objects
        for (unsigned i = 0; i < multiTracker->getObjects().size(); i++)
        {                                                                               
            rectangle(frame, multiTracker->getObjects()[i], colors[i], 2, 1);
        }

        cout << "\nPosition of box1 in X-axis :" << bboxes[0].x << endl;
        cout << "\nPosition of box1 in Y-axis :" << bboxes[0].y << endl;   
        cout << "\nPosition of box2 in X-axis :" << bboxes[1].x << endl;
        cout << "\nPosition of box2 in Y-axis :" << bboxes[1].y << endl;

        resize(frame, frame, Size(1280, 720), 0, 0, INTER_CUBIC);
        imshow("MultiTracker", frame);
        if (waitKey(1) == 27) break; 

    }



}

bboxes.size() 是 2 ，因为我只画了 2 个 ROI。我正在使用 OpenCV 3.4.1 和 Visual Studio 2015

这是我得到的输出样本

Answer 1

您的 bboxes[] 变量似乎用于初始化，但之后没有更新。您可以尝试使用 multiTracker->getObjects() 的输出作为 x 和 y 坐标，就像您在绘制矩形时已经在做的那样。

Answer 2

如@Nicolas Gaborel 所述，您没有更新 bboxes 的值。有两种方法可以做到这一点

如果顺序无关紧要，那么只需在 for-loop

bboxes[i] = multiTracker->getObjects()[i]

如果您还想跟踪订单，则需要为检测到的箱子分配某种 ID。一种快速的方法是首先计算矩形的质心并存储它们。检测到对象后，您将计算对象矩形的质心。此后计算检测到的对象的质心与存储在 bboxes 中的欧几里德距离。 bboxes中距离最小的矩形是正确的。

获取已在 OpenCV C++ 中的跟踪算法中跟踪的 ROI 的 x 和 y 像素坐标

Get the x and y pixel co-ordinates of the ROI that has been tracked in a tracking algorithm in OpenCV C++

opencv

computer-vision

video-tracking