Human Tracking Method under Occlusion and Across Cameras
The cameras in this study are used to extend the field of view. The essence of human tracking with multiple cameras is to match people among different cameras. However, human occlusion, when many people walk side by side, similar appearance and light variation could cause serious effects to human tracking. With this respect, the paper proposed a three-dimensional information-based human tracking method. The method first samples the pixels within the human body region in one of the video images, and then finds the matching points in the other simultaneous video images by polar line constraints. The threedimensional points in space corresponding to each pair of the matches are obtained by triangulation and are also clustered.The pixels in the image plane corresponding to each clustering region, which includes the three-dimensional points, are decided. Finally, Gaussian-smoothing histograms are created, based on the pixels in the image plane. Occluded people would be divided into each other by the Gaussiansmoothing histograms. The matching relation of each person in different cameras could be found and thus, human tracking is realized. Experimental results show the method’s efficiency.
Human tracking video surveillance multi-cameras Gaussian-smoothing histograms matching points
Li Zhang Hai-bin Yu
School of Computer Science, Hangzhou Dianzi University, Hangzhou, China School of Electronic & Information, Hangzhou Dianzi University, Hangzhou, China Zhejiang Provincial
国际会议
2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)
厦门
英文
347-351
2010-04-12（万方平台首次上网日期，不代表论文的发表时间）