Foreground Detection Using GMM on Depth Images

I used vision.ForegroundDetector() to detect foreground on RGB video frames. The input of step() is from the vision.VideoFileReader() which reads .avi video frame. If I want to detect foreground on depth images, how can I provide an input of 20 depth images (.png) instead of an .avi file?

Answer 1

[Dima Lisin]

The step method of vision.ForegroundDetector takes an image, which can come from anywhere. So you can just read your depth maps from the png files with imread and feed them into the foreground detector.