中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Abnormal Crowd Motion Analysis

文献类型:会议论文

作者Tian Cao; Xinyu Wu; Jinnian Guo; Shiqi Yu; Yangsheng Xu
出版日期2009
会议名称2009 IEEE International Conference on Robotics and Biomimetics, ROBIO 2009
英文摘要Video surveillance in crowded areas is becoming more and more significant for public security. This paper presents a method for the detection ofabnormality in crowded scenes based on the crowd motion characteristics. These characteristics includes the crowd kinetic energy and themotion directions. This approach estimates the crowd kinetic energy and the motion directions based on the optical flow techniques. The motionvariation is derived from the crowd kinetic energy of two adjacent frames, and the motion direction variation is estimated using mutual information of the direction histograms of two neighboring motion vector fields. The proposed method combines crowd kinetic energy, motion variation and direction variation for the abnormality detection. The experiments on the video data which captured by ourselves demonstrate that our method can detect the abnormal behaviors effectively.
收录类别EI
语种英语
源URL[http://ir.siat.ac.cn:8080/handle/172644/2489]  
专题深圳先进技术研究院_集成所
作者单位2009
推荐引用方式
GB/T 7714
Tian Cao,Xinyu Wu,Jinnian Guo,et al. Abnormal Crowd Motion Analysis[C]. 见:2009 IEEE International Conference on Robotics and Biomimetics, ROBIO 2009.

入库方式: OAI收割

来源:深圳先进技术研究院

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。