计算机视觉 目标跟踪

一、实验目的

通过python 语言编程设计跟踪算法，实现目标行人的选择，跟踪。促进学生理解并掌握相关跟踪算法，培养学生的编程能力。

二、实验硬、软件环境

笔记本电脑、windows10系统,Visual Studio Code编辑器，opencv视觉库，numpy库, matplolib库。

三、实验内容及步骤

（一）实验内容  

编程实现目标行人的跟踪。

（二）实验过程及代码

1.选择目标跟踪方法

有以下跟踪方法函数

if tracker_type=='BOOSTING':
tracker=cv2.legacy.TrackerBoosting_create()
if tracker_type=='MIL':
tracker=cv2.TrackerMIL_create()
if tracker_type=='KCF':
tracker=cv2.TrackerKCF_create()
if tracker_type=='TLD':
tracker=cv2.legacy.TrackerTLD_create()
if tracker_type=='MEDIANFLOW':
tracker=cv2.legacy.TrackerMedianFlow_create()
if tracker_type=='GOTURN':#深度学习，缺少模型数据
tracker=cv2.TrackerGOTURN_create()
if tracker_type=='MOSSE':
tracker=cv2.legacy.TrackerMOSSE_create()
if tracker_type=="CSRT":
tracker=cv2.TrackerCSRT_create()

我所使用的为tld

     tracker_types = ['TLD']

tracker_type = tracker_types[0]

   if tracker_type == 'TLD':

     tracker = cv2.legacy.TrackerTLD_create()

2.读取视频

   

 video = cv2.VideoCapture("F:/Three/CV/计算机视觉/11.mp4")

                                  

图1视频图像

3.人工选择跟踪目标

bbox = cv2.selectROI(frame, False)

ok = tracker.init(frame, bbox)

 

图2 目标物体框

   4.实验完整代码

import cv2
import sys
import argparse
 
if __name__ == '__main__' :
 
    # Set up tracker.
    # Instead of MIL, you can also use
 
    tracker_types = ['TLD']
    tracker_type = tracker_types[0]
 
    if tracker_type == 'TLD':
        tracker = cv2.legacy.TrackerTLD_create()
   
    # Read video 获取视频
    video = cv2.VideoCapture("F:/Three/CV/计算机视觉/11.mp4")
 
    # Exit if video not opened.
    if not video.isOpened():
        print("Could not open video")
        sys.exit()
 
    # Read first frame.
    ok, frame = video.read()
    if not ok:
        print('Cannot read video file')
        sys.exit()
    
    # Define an initial bounding box 定义初始化的边界框
    bbox = (100, 40, 86,100)
 
    # Uncomment the line below to select a different bounding box 取消下面一行的注释，选择一个不同的边界框架
    bbox = cv2.selectROI(frame, False)
 
    # Initialize tracker with first frame and bounding box 用第一帧和包围框初始化跟踪边界框架
    ok = tracker.init(frame, bbox)
 
    while True:
        # Read a new frame
        ok, frame = video.read()
        if not ok:
            break
        
        # Start timer 开始计时
        timer = cv2.getTickCount()
 
        # Update tracker 更新跟踪信号
        ok, bbox = tracker.update(frame)
 
        # Calculate Frames per second (FPS) 计算每秒帧数(FPS) 
        fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer);
 
        # Draw bounding box 绘制边界框
        if ok:
            # Tracking success 跟踪成功
            p1 = (int(bbox[0]), int(bbox[1]))
            p2 = (int(bbox[0] + bbox[2]), int(bbox[1] + bbox[3]))
            cv2.rectangle(frame, p1, p2, (255,0,0), 2, 1)
        else :
            # Tracking failure 跟踪失败
            cv2.putText(frame, "Tracking failure detected", (100,80), cv2.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)
 
        # Display tracker type on frame 在帧上显示跟踪器类型
        cv2.putText(frame, tracker_type + " Tracker", (100,20), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50),2);
    
        # Display FPS on frame 帧显示FPS
        cv2.putText(frame, "FPS : " + str(int(fps)), (100,50), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50), 2);
 
 
        # Display result 显示结果
        cv2.imshow("Tracking", frame)
 
        # Exit if ESC pressed 
        k = cv2.waitKey(1) & 0xff
        if k == 27 : break