Integration of Multiple Shape Features for Human Detection in Videos

Liang-Hua Chen, Pei Chieh Lee, Li-Yun Wang, Hong-Yuan Mark Liao

Abstract: In this paper, we propose an integrated approach for human detection in surveillance video. In our approach, the moving object is extracted by background subtraction, and the background model is updated by the first order recurrence filter. Then, two complementary shape features are extracted for moving object classification. They are contour-based description: Fourier descriptor and region-based description: histogram of oriented gradient. As the binary classifier (support vector machine) is able to provide the posterior probability, we effectively integrate two types of features to achieve better performance. Experimental results show that the proposed approach is effective and outperforms some existing technique.