实时对象跟踪 - 如何让视频在开始播放，让用户暂停，绘制边界框，然后开始跟踪？答案

【问题标题】：Real time object tracking - how to let the video play in the beginning, let the user pause it, draw the bounding box, and then begin the tracking?实时对象跟踪 - 如何让视频在开始播放，让用户暂停，绘制边界框，然后开始跟踪？
【发布时间】：2021-04-30 22:40:37
【问题描述】：

以下是我找到的here 用于实时对象跟踪的代码：

import cv2
import sys

major_ver, minor_ver, subminor_ver = cv2.__version__.split('.')

if __name__ == '__main__' :

    # Set up tracker.
    tracker_types = ['BOOSTING', 'MIL','KCF', 'TLD', 'MEDIANFLOW', 'GOTURN', 'MOSSE', 'CSRT']
    tracker_type = tracker_types[1]

    if int(minor_ver) < 3:
        tracker = cv2.Tracker_create(tracker_type)
    else:
        if tracker_type == 'BOOSTING':
            tracker = cv2.TrackerBoosting_create()
        if tracker_type == 'MIL':
            tracker = cv2.TrackerMIL_create()
        if tracker_type == 'KCF':
            tracker = cv2.TrackerKCF_create()
        if tracker_type == 'TLD':
            tracker = cv2.TrackerTLD_create()
        if tracker_type == 'MEDIANFLOW':
            tracker = cv2.TrackerMedianFlow_create()
        if tracker_type == 'GOTURN':
            tracker = cv2.TrackerGOTURN_create()
        if tracker_type == 'MOSSE':
            tracker = cv2.TrackerMOSSE_create()
        if tracker_type == "CSRT":
            tracker = cv2.TrackerCSRT_create()

    # Read video
    video = cv2.VideoCapture(0) # 0 means webcam. Otherwise if you want to use a video file, replace 0 with "video_file.MOV")

    # 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
    bbox = (287, 23, 86, 320)

    # Uncomment the line below to select a different bounding box
    bbox = cv2.selectROI(frame, False)

    # Initialize tracker with first frame and bounding box
    ok = tracker.init(frame, bbox)

    while True:
        # Read a new frame
        ok, frame = video.read()
        if not ok:
            break
        
        # Start timer
        timer = cv2.getTickCount()

        # Update tracker
        ok, bbox = tracker.update(frame)

        # Calculate Frames per second (FPS)
        fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer);

        # Draw bounding box
        if ok:
            # Tracking success
            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
            cv2.putText(frame, "Tracking failure detected", (100,80), cv2.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)

        # Display tracker type on frame
        cv2.putText(frame, tracker_type + " Tracker", (100,20), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50),2);
    
        # Display FPS on frame
        cv2.putText(frame, "FPS : " + str(int(fps)), (100,50), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50), 2);

        # Display result
        cv2.imshow("Tracking", frame)

        # Exit if ESC pressed
        k = cv2.waitKey(1) & 0xff
        if k == 27 : break

它工作正常，但是当您运行程序时，它会在第一帧暂停，直到您绘制边界框以开始跟踪。

我想让视频先播放，然后用户应该能够暂停它，绘制边界框，然后恢复视频以开始跟踪。为此，我替换了以下内容：

    # Read video
    video = cv2.VideoCapture(0) # 0 means webcam. Otherwise if you want to use a video file, replace 0 with "video_file.MOV")

    # 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
    bbox = (287, 23, 86, 320)

    # Uncomment the line below to select a different bounding box
    bbox = cv2.selectROI(frame, False)

    # Initialize tracker with first frame and bounding box
    ok = tracker.init(frame, bbox)

用这个：

    while True:
        # Read video
        video = cv2.VideoCapture(0) # 0 means webcam. Otherwise if you want to use a video file, replace 0 with "video_file.MOV")

        # 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()
        
        # Retrieve an image and Display it.
        if(0xFF & cv2.waitKey(10))==ord('p'): # Press key `p` to pause the video to start tracking
            break
        cv2.namedWindow("Image", cv2.WINDOW_NORMAL)
        cv2.imshow("Image", frame)
    cv2.destroyWindow("Image")

当我现在运行程序时，视频开始播放，但是我一按p，Python就崩溃了：

我该如何解决这个问题？

编辑：为了清楚起见，在此处粘贴带有替换/替换的整个代码：

import cv2
import sys

major_ver, minor_ver, subminor_ver = cv2.__version__.split('.')

if __name__ == '__main__' :

    # Set up tracker.
    tracker_types = ['BOOSTING', 'MIL','KCF', 'TLD', 'MEDIANFLOW', 'GOTURN', 'MOSSE', 'CSRT']
    tracker_type = tracker_types[1]

    if int(minor_ver) < 3:
        tracker = cv2.Tracker_create(tracker_type)
    else:
        if tracker_type == 'BOOSTING':
            tracker = cv2.TrackerBoosting_create()
        if tracker_type == 'MIL':
            tracker = cv2.TrackerMIL_create()
        if tracker_type == 'KCF':
            tracker = cv2.TrackerKCF_create()
        if tracker_type == 'TLD':
            tracker = cv2.TrackerTLD_create()
        if tracker_type == 'MEDIANFLOW':
            tracker = cv2.TrackerMedianFlow_create()
        if tracker_type == 'GOTURN':
            tracker = cv2.TrackerGOTURN_create()
        if tracker_type == 'MOSSE':
            tracker = cv2.TrackerMOSSE_create()
        if tracker_type == "CSRT":
            tracker = cv2.TrackerCSRT_create()

    while True:
        # Read video
        video = cv2.VideoCapture(0) # 0 means webcam. Otherwise if you want to use a video file, replace 0 with "video_file.MOV")

        # 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()
        
        # Retrieve an image and Display it.
        if((0xFF & cv2.waitKey(10))==ord('p')): # Press key `p` to pause the video to start tracking
            break
        cv2.namedWindow("Image", cv2.WINDOW_NORMAL)
        cv2.imshow("Image", frame)
    cv2.destroyWindow("Image")

    while True:
        # Read a new frame
        ok, frame = video.read()
        if not ok:
            break
        
        # Start timer
        timer = cv2.getTickCount()

        # Update tracker
        ok, bbox = tracker.update(frame)

        # Calculate Frames per second (FPS)
        fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer);

        # Draw bounding box
        if ok:
            # Tracking success
            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
            cv2.putText(frame, "Tracking failure detected", (100,80), cv2.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)

        # Display tracker type on frame
        cv2.putText(frame, tracker_type + " Tracker", (100,20), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50),2);
    
        # Display FPS on frame
        cv2.putText(frame, "FPS : " + str(int(fps)), (100,50), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50), 2);

        # Display result
        cv2.imshow("Tracking", frame)

        # Exit if ESC pressed
        k = cv2.waitKey(1) & 0xff
        if k == 27 : break

【问题讨论】：

标签： python opencv deep-learning object-detection video-tracking

【解决方案1】：

你的 if 语句的括号放错了地方

if(0xFF & cv2.waitKey(10))==ord('p'):

应该是

if ((0xFF & cv2.waitKey(10)) == ord('p')):

虽然如果你使用 ord() 你可以直接比较

if (cv2.waitKey(10) == ord('p')):

这是您的代码，稍作修改。它适用于跟踪我的脸。

import cv2
import sys

major_ver, minor_ver, subminor_ver = cv2.__version__.split('.')

if __name__ == '__main__' :

    # Set up tracker.
    tracker_types = ['BOOSTING', 'MIL','KCF', 'TLD', 'MEDIANFLOW', 'GOTURN', 'MOSSE', 'CSRT']
    tracker_type = tracker_types[1]

    if int(minor_ver) < 3:
        tracker = cv2.Tracker_create(tracker_type)
    else:
        if tracker_type == 'BOOSTING':
            tracker = cv2.TrackerBoosting_create()
        if tracker_type == 'MIL':
            tracker = cv2.TrackerMIL_create()
        if tracker_type == 'KCF':
            tracker = cv2.TrackerKCF_create()
        if tracker_type == 'TLD':
            tracker = cv2.TrackerTLD_create()
        if tracker_type == 'MEDIANFLOW':
            tracker = cv2.TrackerMedianFlow_create()
        if tracker_type == 'GOTURN':
            tracker = cv2.TrackerGOTURN_create()
        if tracker_type == 'MOSSE':
            tracker = cv2.TrackerMOSSE_create()
        if tracker_type == "CSRT":
            tracker = cv2.TrackerCSRT_create()

    # Read video
    video = cv2.VideoCapture(0) # 0 means webcam. Otherwise if you want to use a video file, replace 0 with "video_file.MOV")

    # Exit if video not opened.
    if not video.isOpened():
        print ("Could not open video")
        sys.exit()

    while True:

        # Read first frame.
        ok, frame = video.read()
        if not ok:
            print ('Cannot read video file')
            sys.exit()
        
        # Retrieve an image and Display it.
        if((0xFF & cv2.waitKey(10))==ord('p')): # Press key `p` to pause the video to start tracking
            break
        cv2.namedWindow("Image", cv2.WINDOW_NORMAL)
        cv2.imshow("Image", frame)
    cv2.destroyWindow("Image");

    # select the bounding box
    bbox = (287, 23, 86, 320)

    # Uncomment the line below to select a different bounding box
    bbox = cv2.selectROI(frame, False)

    # Initialize tracker with first frame and bounding box
    ok = tracker.init(frame, bbox)

    while True:
        # Read a new frame
        ok, frame = video.read()
        if not ok:
            break
        
        # Start timer
        timer = cv2.getTickCount()

        # Update tracker
        ok, bbox = tracker.update(frame)

        # Calculate Frames per second (FPS)
        fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer);

        # Draw bounding box
        if ok:
            # Tracking success
            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
            cv2.putText(frame, "Tracking failure detected", (100,80), cv2.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)

        # Display tracker type on frame
        cv2.putText(frame, tracker_type + " Tracker", (100,20), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50),2);
    
        # Display FPS on frame
        cv2.putText(frame, "FPS : " + str(int(fps)), (100,50), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50), 2);

        # Display result
        cv2.imshow("Tracking", frame)

        # Exit if ESC pressed
        k = cv2.waitKey(1) & 0xff
        if k == 27 : break

我将 videocapture 声明移到了循环之外，这样就不会在每次循环迭代时都重新构建它。我在第一个和第二个循环之间添加了 ROI 选择器和跟踪器初始化。

【讨论】：

好的。但这并不能解决按下 p 时 Python 崩溃的问题。
你是如何运行python程序的？是否有关于程序的哪个部分崩溃的其他信息？你能用你的替换发布整个代码吗？
好的，我已经编辑了问题以包含整个代码并进行替换。我运行它就像运行任何其他 Python 程序一样 - 将文件命名为 tracking.py，然后将其运行为 python3 tracking.py。
需要 object_tracker_master 吗？当我运行程序时（删除 object_tracker_master 后），它运行时不会崩溃。
如果相机没有移动，那么您可以在您已经跟踪的物体周围的任何边界框之外查找图像中发生的变化。不过，这有点像它自己的问题，根据您的环境/设置/容差，有不同的技术。