Find missing objects using image difference

asked 2013-07-09 00:44:31 -0500

yohanrw gravatar image

updated 2013-07-09 04:05:29 -0500

I want to detect missing objects of an image. Here is the situation

You have an image of a room. There is a ball in the room. You have another image of the same room (Light conditions similar). The only difference is, the ball is missing. Now I need to opencv to compare these 2 images and find what is missing.

If I subtract image 1 with image 2, I can get the difference, or I can use abs() method to find the difference isn't it?

Now the other problem. I need to draw a rectangle/circle or something over the "missing area to show what is missing from where.

I was told the second objective can be done by blob detection. In motion detection I used contours so can I apply the same technique to here? I detected motion by using abs() to find the difference and drawing contours.

Anyway, I need help and advice about this. I do not know what technique to follow. I am learning image processing only by doing opencv, and reading opencv stuff. Please help.

PS. Ball is just an example. Anything could be missing from the room (which are in the vision of the camera) , including book, table etc. Camera will be in the 100% same angle always.

edit retag flag offensive close merge delete


Any chance you figured this out in the last three years? I'm basically doing the exact same thing.

AoifeOS gravatar imageAoifeOS ( 2016-06-22 09:19:02 -0500 )edit