Implementing a basic background subtractor

To implement a basic background subtractor, let's take the following approach:

  1. Start capturing frames from a camera.
  2. Discard nine frames so that the camera has time to properly adjust its autoexposure to suit the lighting conditions in the scene.
  3. Take the 10th frame, convert it to grayscale, blur it, and use this blurred image as the reference image of the background.
  4. For each subsequent frame, blur the frame, convert it to grayscale, and compute the absolute difference between this blurred frame and the reference image of the background. Perform thresholding, smoothing, and contour detection on the differenced image. Draw and show the bounding boxes of the major contours.
The use of a Gaussian ...

Get Learning OpenCV 4 Computer Vision with Python 3 now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.