Ask Your Question

Background Subtraction problem

asked 2017-02-16 12:10:35 -0500

zed961 gravatar image

Hello all,

I am trying to build a system that could identify changes in images taken every day (24h delay between each image). My approach was to use backgroundsubtractionMOG2 but it's failing when the weather changes dramatically (sunny to cloudy day) and learning the background is taking a lot of time.

Do you recommend any algorithm or method to solve this?


edit retag flag offensive close merge delete


could you provide sample images

sturkmen gravatar imagesturkmen ( 2017-02-16 14:05:46 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2017-02-16 13:24:14 -0500

kevin_lomax gravatar image

What exactly do you mean by "identify changes in images"? Do you want to detect new objects that enter the scene or understand the changing weather conditions? The answer could change depend on what your goal is.

For more robustness against weather changes, you can try deep neural networks (esp. convolutional neural nets) provided that you have enough training images. But depending on the actual images, the solution could also be much easier. What are you trying to achieve with background subtraction?

edit flag offensive delete link more


Hello Kevin, Thanks a lot for your fast reply.

I am mainly trying to detect any new object in the scene. I can use a neural network to detect every single object (car, humans, etc...) but i fear it's going to be costly as this requires a lot of data. For this reason i thought of identifying the background and any change in the background will be considered as an intruder or "change".

zed961 gravatar imagezed961 ( 2017-02-16 13:41:11 -0500 )edit
Login/Signup to Answer

Question Tools

1 follower


Asked: 2017-02-16 12:10:35 -0500

Seen: 104 times

Last updated: Feb 16 '17