Abnormal crowd motion analysis

Tian Cao, Xinyu Wu, Jinnian Guo, Shiqi Yu, Yangsheng Xu

Abstract: Video surveillance in crowded areas is becoming more and more significant for public security. This paper presents a method for the detection of abnormality in crowded scenes based on the crowd motion characteristics. These characteristics includes the crowd kinetic energy and the motion directions. This approach estimates the crowd kinetic energy and the motion directions based on the optical flow techniques. The motion variation 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.

External IDs:dblp:conf/robio/CaoWGYX09