Background Modeling Using Combined Kernel Density Estimation and Correlation Coefficients
Kernel density estimation algorithm is an effective way for segmenting fore/background. However, its computation complexity is high. In addition, it suffers from low robustness when there are dynamic scenes and/or sudden lighting changes. On the other hand, the correlation coefficients method is effective in describing the similarity between images. Furthermore, this method is not sensitive to small image appearance changes. To take advantage of this characteristic, a hierarchical block detection mechanism is proposed in this paper. First, the noise from the dynamic background scenes and/or the lighting changes are filtered by the correlation coefficients. After that, the blocks with fore-ground are segmented by kernel density estimation. Experiments confirmed that the proposed method is effective to deal with dynamic backgrounds and fast in computation.
intelligent video background modeling kernel density estimation correlation coefficients
Ting Rui Jian-chun Xing Jing-wei Zhu Hu-sheng Fang
Engineering Institute of Engineering Corps , PLA Univ. of Sci.&Tech., Nanjing, Jiangsu, China
国际会议
2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)
上海
英文
197-200
2010-12-25(万方平台首次上网日期,不代表论文的发表时间)