Skip to main content

Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians

Publication ,  Journal Article
Haque, M; Murshed, M
Published in: Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012
November 6, 2012

Robust background subtraction (BS) is essential for high quality foreground detection in most video analytics systems. Recent BS techniques achieve superior detection quality mostly by exploiting the complementary strengths of multiple background models or processing stages. Consequently, these techniques fail to meet the operational requirements of real-time video analytics due to high computational overhead where BS is just the primary processing task. In this paper, we propose a new BS technique, named multi-hypothesis mixture-of-Gaussians (MH-MOG), suitable for real-time video analytics. The essential idea is to maintain a single background model based on perception-aware mixture-of-Gaussians and then, generating multiple detection hypotheses with different processing bases. Finally, only during the detection stage, the complementary strengths of the hypotheses are exploited to achieve superior detection quality without significant computational overhead. Comprehensive experimental evaluation validates the efficacy of MH-MOG. © 2012 IEEE.

Duke Scholars

Published In

Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012

DOI

Publication Date

November 6, 2012

Start / End Page

166 / 171
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Haque, M., & Murshed, M. (2012). Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians. Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, 166–171. https://doi.org/10.1109/AVSS.2012.15
Haque, M., and M. Murshed. “Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians.” Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, November 6, 2012, 166–71. https://doi.org/10.1109/AVSS.2012.15.
Haque M, Murshed M. Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians. Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012. 2012 Nov 6;166–71.
Haque, M., and M. Murshed. “Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians.” Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, Nov. 2012, pp. 166–71. Scopus, doi:10.1109/AVSS.2012.15.
Haque M, Murshed M. Background subtraction for real-time video analytics based on multi-hypothesis mixture-of-gaussians. Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012. 2012 Nov 6;166–171.

Published In

Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012

DOI

Publication Date

November 6, 2012

Start / End Page

166 / 171