A Dynamic Texture-based Method for Multi-directional Motions Segmentation of Crowd

摘要：

A dynamic texture-based method used in crowds multidirectional motions segmentation is presented. Firstly, the magnitude and direction of the optical flow field are extracted as the dynamic texture features of the motion crowds; Secondly, initial multi-directional motions segmentation will be performed by means of the dynamic texture features with the aid of the perspective normalization and Renyis entropy threshold; Finally, level set algorithm without re-initialization is introduced to optimize the initial segmentation so as to achieve the final multi-directional motions segmentation result The experimental results show that compared with existing methods, the method presented in this paper is more suitable for the segmentation of the crowd motions with multiple motion directions.

关键词： dynamic texture motion segmentation level set crowd

作者: Haibin Yu Zhiwei He Yuanyuan Liu Li Zhang

作者单位: School of Electronic & Information Hangzhou Dianzi University Hangzhou, China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou, China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 1132-1136

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）