I have a time averaged grayscale frame of a video:
I applied Canny edge detector to that frame, but sometimes there is noise like this:
I want to extract the area of a tv logo using boundingRect(), but it works wrong if there is noise. How can i avoid it?
simple average isn't good enough. you need to be sensitive to a pixel changing at all (within some tolerance) over a certain time, because the station logo doesn't change at all, while the rest of the picture usually changes, but may not change much, or may be visible for a long time but not all the time (that recognizable frame/border within view)
look into the background subtraction/segmentation module within OpenCV. tweak the parameters.
if that doesn't help, you'll probably need to come up with your own approach.
Asked: 2020-12-09 01:20:19 -0600
Seen: 888 times
Last updated: Dec 09 '20
if you share your code maybe we can help to improve