Hi,
New to openCV here. I am trying to build a system to capture motion-activated photos/videos of the animal in my garden. Most of the motion detection algorithms I found online subtract the current frame from the initial frame, but that doesn't work outdoors as the lighting changes over the course of the day.
I currently subtract the current frame from the previous frame, however this still gives me a lot of false positives due to the wind moving the leaves in the trees.
Are there other algorithms I should look into in order to detect exclusively the sustained motion of foreground objects?
Thanks!