Following is a code I found here for real time object tracking:

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

It works fine, but when you run the program, it pauses at the first frame until you draw the bounding box for the tracking to start.

I want to let the video play first, then the user should be able to pause it, draw the bounding box and then resume the video for the tracking to begin. For that, I replaced the following:

    # 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)

with this:

    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")

When I run the program now, the video starts to play in the beginning, but as soon as I press p, Python crashes:

enter image description here

How do I fix this?

EDIT: Pasting the entire code with the replacement/substitution here for clarity:

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
1

There are 1 best solutions below

8
On BEST ANSWER

your if statement has the parenthesis in the wrong place

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

should be

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

Though if you're using ord() you can do a direct comparison

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

Here's your code with a few edits. It works for tracking my face.

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

I moved the videocapture declaration outside of the loop so that it's not getting rebuilt every loop iteration. I added back in the ROI selector and tracker initialization inbetween the first and second loops.