A real-time background subtraction method with camera motion compensation

by: Tiehan Lv, B Ozer, W Wolf

Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on, Vol. 1 (2004), pp. 331-334 Vol.1.

View FullText article

IEEE Explore

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

derinb

Find related articles with these CiteULike tags

bgsub

Abstract

Background subtraction algorithms are critical to many video recognition/analysis systems and have been studied for decades. Most of the algorithms assume that the camera is fixed. We propose a background subtraction algorithm that works when a shaking camera is present. In this algorithm, the input frames are compensated and compared with the given reference frame to separate foreground objects from the background. Experimental results show that the proposed method outperforms the widely used Gaussian mixture model based method in both fixed camera and shaking camera scenarios with respect to accuracy, robustness, and efficiency.

@inproceedings{TiehanOzerWolf04, abstract = {Background subtraction algorithms are critical to many video recognition/analysis systems and have been studied for decades. Most of the algorithms assume that the camera is fixed. We propose a background subtraction algorithm that works when a shaking camera is present. In this algorithm, the input frames are compensated and compared with the given reference frame to separate foreground objects from the background. Experimental results show that the proposed method outperforms the widely used Gaussian mixture model based method in both fixed camera and shaking camera scenarios with respect to accuracy, robustness, and efficiency.}, author = {Lv, Tiehan and Ozer, B. and Wolf, W. }, citeulike-article-id = {600860}, journal = {Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on}, keywords = {bgsub}, pages = {331--334 Vol.1}, posted-at = {2006-04-26 04:15:17}, priority = {2}, title = {A real-time background subtraction method with camera motion compensation}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1394196}, volume = {1}, year = {2004} }

RIS record

TY - CONF ID - TiehanOzerWolf04 L3 - citeulike-article-id:600860 TI - A real-time background subtraction method with camera motion compensation JF - Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on VL - 1 SP - 331 EP - 334 Vol.1 N2 - Background subtraction algorithms are critical to many video recognition/analysis systems and have been studied for decades. Most of the algorithms assume that the camera is fixed. We propose a background subtraction algorithm that works when a shaking camera is present. In this algorithm, the input frames are compensated and compared with the given reference frame to separate foreground objects from the background. Experimental results show that the proposed method outperforms the widely used Gaussian mixture model based method in both fixed camera and shaking camera scenarios with respect to accuracy, robustness, and efficiency. KW - bgsub AU - Lv, Tiehan AU - Ozer, B AU - Wolf, W PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1394196 ER -

RIS BibTeX