目标跟踪 行人行走方向统计

在B站上看到可以对行人方向做统计：

感觉很有意思，之前在github上发现有个类似的项目：项目在这里

思路是：

• 准备一个背景板，上面画出2个区域，分为上行标识区、下行标识区。
• 当人经过上行标识区、下行标识区的时候，就相应地记数

效果：

当行人经过标识区，其中心蓝色点显示出来，并进行相应记数

添加行人行走方向记数的main.cpp

        /*!
    @Description : https://github.com/shaoshengsong/
    @Author      : shaoshengsong
    @Date        : 2022-09-23 02:52:22
*/
#include <fstream>
#include <sstream>
//#include <iostream>
//#include <cstring>

#include <opencv2/imgproc.hpp>
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
#include "YOLOv5Detector.h"

//#include "FeatureTensor.h"
#include "BYTETracker.h" //bytetrack
#include "tracker.h"//deepsort
//Deep SORT parameter

// https://cloud.tencent.com/developer/article/2099504






std::vector<STrack>  test_bytetrack(cv::Mat& frame, std::vector<detect_result>& results,
                    BYTETracker& tracker, std::vector<std::string> & classes)
{
    int track_num=0;

    std::vector<detect_result> objects;


    for (detect_result dr : results)
    {

        if(dr.classId == 0 ) // person
        {
            objects.push_back(dr);
        }
    }

    // bytetrack主函数
    std::vector<STrack> output_stracks = tracker.update(objects);

    // 对于track结果
    for (unsigned long i = 0; i < output_stracks.size(); i++)
    {
        std::vector<float> tlwh = output_stracks[i].tlwh;

        //  目标像素不能小于20个像素、宽高比需 < 1.6
        // 其实这里加一个判定不是很合理，因为 bytetrack主函数中ID已经增加了，只不过没有显示该目标而已
//        bool vertical = tlwh[2] / tlwh[3] > 1.6;
//        if (tlwh[2] * tlwh[3] > 20 && !vertical)
        if(1)
        {
            // 框出目标，并标注ID
            cv::Scalar s = tracker.get_color(output_stracks[i].track_id);
            cv::putText(frame, cv::format("%s--%d",classes[output_stracks[i].class_index].c_str(),output_stracks[i].track_id),
                    cv::Point(tlwh[0], tlwh[1] - 5),
                    0, 0.6, cv::Scalar(0, 0, 255), 2, cv::LINE_AA);
            cv::rectangle(frame, cv::Rect(tlwh[0], tlwh[1], tlwh[2], tlwh[3]), s, 2);

        }
    }


    return output_stracks;

}
int main(int argc, char *argv[])
{
    // 加载类别名称
    std::vector<std::string> classes;
    std::string file="/home/jason/work/my-deploy/01-bytetrack-deepsort/coco_80_labels_list.txt";
    std::ifstream ifs(file);
    if (!ifs.is_open())
        CV_Error(cv::Error::StsError, "File " + file + " not found");
    std::string line;
    while (std::getline(ifs, line))
    {
        classes.push_back(line);
    }

    // 上行 下行 记数
    int total_num=0;
    std::vector<int> up_ID;
    std::vector<int> down_ID;
    cv::Mat background= cv::Mat::zeros(1080, 1920, CV_8U); // 高、宽

    std::vector<cv::Point> down ={cv::Point(0,500), cv::Point(1920, 500),
                                 cv::Point(1920, 540),cv::Point(0,540)};
    std::vector<cv::Point> up ={cv::Point(0,550), cv::Point(1920, 550),
                                  cv::Point(1920, 580),cv::Point(0,580)};

    cv::fillPoly(background, down, cv::Scalar(60));
    cv::fillPoly(background, up, cv::Scalar(100));
    cv::imshow("back", background);


    // 检测器
    std::cout<<"classes:"<<classes.size();
    std::shared_ptr<YOLOv5Detector> detector(new YOLOv5Detector());
    detector->init(k_detect_model_path);

    //bytetrack设置
    int fps=20;
    BYTETracker bytetracker(fps, 30); // 后面的30是30帧没有发现，

    // 读取视频
    std::cout<<"begin read video"<<std::endl;
    cv::VideoCapture capture("/home/jason/work/my-deploy/01-bytetrack-deepsort/1.mp4");
    if (!capture.isOpened()) {
        printf("could not read this video file...\n");
        return -1;
    }
    std::cout<<"end read video"<<std::endl;

    // 结果
    std::vector<detect_result> results;

    // 输出另存
    cv::VideoWriter video("out.avi",cv::VideoWriter::fourcc('M','J','P','G'),10, cv::Size(1920,1080));

    int num_frames = 0;
    cv::Mat frame;
    while (true)
    {



        if (!capture.read(frame)) // if not success, break loop
        {
            std::cout<<"\n Cannot read the video file. please check your video.\n";
            break;
        }
        num_frames ++;

        //Second/Millisecond/Microsecond  秒s/毫秒ms/微秒us
        auto start = std::chrono::system_clock::now();

        // 获得检测结果
        detector->detect(frame, results);

        // 计算检测耗时
        auto end = std::chrono::system_clock::now();
        auto detect_time =std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count();//ms
//        std::cout<<classes.size()<<":"<<results.size()<<":"<<num_frames<<std::endl;
        printf("视频尺寸：%d宽  * %d高\n", frame.cols, frame.rows );
        printf("帧数:%d  检测器耗时：%dms ",num_frames, (int)detect_time);


        // 进行跟踪
        std::vector<STrack> temp_tracks;
        auto start2 = std::chrono::system_clock::now();
        temp_tracks = test_bytetrack(frame, results,bytetracker,classes);
        auto end2 = std::chrono::system_clock::now();

        // 计算跟踪器耗时
        auto detect_time2 =std::chrono::duration_cast<std::chrono::milliseconds>(end2 - start2).count();//ms
        printf("跟踪器耗时：%dms \n", (int)detect_time2);


        //上下行走方向记数
        for (size_t i=0; i<temp_tracks.size(); i++)
        {
            // 目标id
            if (temp_tracks[i].track_id > total_num)
            {
                total_num = temp_tracks[i].track_id;
            }

            int left= temp_tracks[i].tlwh[0];
            int top = temp_tracks[i].tlwh[1];
            int width = temp_tracks[i].tlwh[2];
            int height = temp_tracks[i].tlwh[3];
            int bbox_ID = temp_tracks[i].track_id;


            cv::Point center = cv::Point(left+width/2, top +height/2);



            int down = 60;// 下行标识区颜色
            int up = 100; // 上行标识去颜色
            int move =background.at<uchar>(center.y,center.x);
            int buffer = 0; // background非标识区颜色为0
            if (move != buffer)
            {

                if (move == down)
                {
                    if (!std::count(up_ID.begin(), up_ID.end(), bbox_ID)) // 判断 bbox_ID 是否在up_ID列表中
                    {
                        cv::circle(frame, center,10, cv::Scalar(255, 0,0),-1); // 撞线的目标标识蓝色实心点
                        if (!std::count(down_ID.begin(), down_ID.end(), bbox_ID)) // 判断 bbox_ID 是否在down_ID列表中
                        {
                            down_ID.push_back(bbox_ID);

                        }
                    }
                }

                else if (move == up)
                {
                    if (!std::count(down_ID.begin(), down_ID.end(), bbox_ID))
                    {
                        cv::circle(frame, center,10, cv::Scalar(255, 0,0),-1); // 撞线的目标标识蓝色实心点
                        if (!std::count(up_ID.begin(), up_ID.end(), bbox_ID))
                        {
                            up_ID.push_back(bbox_ID);

                        }
                    }
                }
            }



        }
        // 显示人流量
        cv::putText(frame, cv::format("total:%d  up:%d  down:%d ", total_num, (int)up_ID.size(), (int)down_ID.size()),
                    cv::Point(30, 30),
                    0,1,cv::Scalar(0, 0, 255), 2, 8);

        cv::line(frame, cv::Point(0, 500), cv::Point(1920, 500), cv::Scalar(0, 100, 0), 2);
        cv::line(frame, cv::Point(0, 540), cv::Point(1920, 540), cv::Scalar(0, 150, 0), 2);
        cv::line(frame, cv::Point(0, 580), cv::Point(1920, 580), cv::Scalar(0, 200, 0), 2);
        cv::imshow("YOLOv5-6.x", frame);

        //------------------------------------------------------------------

        video.write(frame);

        if(cv::waitKey(30) == 27) // Wait for 'esc' key press to exit
        {
            break;
        }

        results.clear();


    }
    capture.release();
    video.release();
    cv::destroyAllWindows();


}

yolov5+bytetrack原项目地址：https://github.com/shaoshengsong/DeepSORT

作为一个计算机视觉领域刚刚入门的新人，很崇拜大佬能把这么庞大的python项目转为C+++，必须star！