Background modeling using special type of Markov Chain

IEICE Electronics Express

Pyke Tin²  Takashi Toriu²  Hiromitsu Hama¹  Thi Thi Zin² 

[1] Research Center for Industry Innovation, Osaka City University;Graduate School of Engineering, Osaka City University

关键词: background modeling;    special type of Markov Chain;    Gamma Markov;    video surveillance;   

DOI  :  10.1587/elex.8.1082

学科分类：电子、光学、磁材料

来源: Denshi Jouhou Tsuushin Gakkai

【 摘 要 】

References(7)Background modeling is important in video surveillance for extracting foreground regions from a complex environment. In this paper, we present a novel background modeling technique based on a special type of Markov Chain. The method is a substantial extension to the existing background subtraction techniques. First, a background pixel is statistically modeled by a linear regressive Gamma Markov distribution. Then, these statistical estimates are used as important parameters in background update schemes. The experimental results show that the proposed model is less sensitive to movements of the texture background and more robust for real time segmenting the foreground object accurately.

【 授权许可】

Unknown