Tracking keypoints between frames using the Lucas-Kanade algorithm

In this recipe, you will learn how to track keypoints between frames in videos using the sparse Lucas-Kanade optical flow algorithm. This functionality is useful in many computer vision applications, such as object tracking and video stabilization.

Getting ready

Before you proceed with this recipe, you need to install the OpenCV version 3.3 (or greater) Python API package.

How to do it

You need to complete the following steps:

1. Import the necessary modules:

import cv2

2. Open a test video and initialize the auxiliary variables:

video = cv2.VideoCapture('../data/traffic.mp4')
prev_pts = None
prev_gray_frame = None
tracks = None

3. Start reading the frames from the video, converting each image into grayscale:

while True:
    retval, frame = video.read()
    if not retval: break
    gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

4. Track the keypoints from a previous frame using the sparse Lucas-Kanade optical flow algorithm or, if you've...