An online discriminative approach to background subtraction
- Li Cheng
- Shaomin Wang, MIT
- Dale Schuurmans, AICML
- Terry Caelli, National ICT Australia and the Australian National University
- S.V.N. Vishwantathan
We present a simple, principled approach to detecting foreground objects in video sequences in real-time. Our method is based on an on-line discriminative learning technique that is able to cope with illumination changes due to discontinuous switching, or illumination drifts caused by slower processes such as varying time of the day. Starting from a discriminative learning principle, we derive a training algorithm that, for each pixel, computes a weighted linear combination of selected past observations with timedecay. We present experimental results that show the proposed approach outperforms existing methods on both synthetic sequences and real video data.
Citation
L. Cheng, S. Wang, D. Schuurmans, T. Caelli, S. Vishwantathan. "An online discriminative approach to background subtraction". IEEE, January 2006.Keywords: | machine learning |
Category: | In Conference |
BibTeX
@incollection{Cheng+al:IEEE06, author = {Li Cheng and Shaomin Wang and Dale Schuurmans and Terry Caelli and S.V.N. Vishwantathan}, title = {An online discriminative approach to background subtraction}, booktitle = {}, year = 2006, }Last Updated: March 12, 2007
Submitted by AICML Admin Assistant