Background Subtraction

Processing a video stream to segment foreground objects from the background is a critical first step in many computer vision applications. Background subtraction (BGS) is a commonly used technique for achieving this segmentation. The popularity of BGS largely comes from its computational efficiency, which allows applications such as human-computer interaction, video surveillance, and traffic monitoring to meet their real-time goals.

Numerous BGS algorithms and a number of post-processing techniques that aim to improve the results of these algorithms have been proposed. In this project, I evaluated several popular, state-of-the-art BGS algorithms and examine how post-processing techniques affect their performance. The experimental results demonstrate that post-processing techniques can significantly improve the foreground segmentation masks produced by a BGS algorithm.


Information related to this project:

  • Parks, D. H. and Fels, S. (accepted for oral presentation, Sept. 2008). Evaluation of Background Subtraction Algorithms with Post-processing. IEEE International Conference on Advanced Video and Signal-based Surveillance.
  • Proposal
  • Presentation
  • Background Subtraction Library: library containing 7 popular background subtraction algorithms (adaptive median filtering, eigenbackground, single Gaussian, Gaussian mixture models, adaptive Gaussian mixture models, running mean, mediod filtering).
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License