Published Articles >> Table of Contents >> Abstract

2006 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS'06)   p. 2
An Online Discriminative Approach to Background Subtraction
Li Cheng, National ICT Australia, Australia
Shaojun Wang, University of Alberta, Canada
Dale Schuurmans, University of Alberta, Canada
Terry Caelli, National ICT Australia, Australia
S.V.N. Vishwanathan, National ICT Australia, Australia

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AVSS.2006.22
Send link to a friend

Abstract
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 time-decay. We present experimental results that show the proposed approach outperforms existing methods on both synthetic sequencse and real video data.
Back to Top Additional Information
Citation:  Li Cheng, Shaojun Wang, Dale Schuurmans, Terry Caelli, S.V.N. Vishwanathan, "An Online Discriminative Approach to Background Subtraction," avss, p. 2,  2006 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS'06),  2006