Abnormal event detection based on analysis of movement information of video sequence

Tian Wang (1) , Meina Qiao (1) , Yingjun Deng (2) , Yi Zhou (3) , Huan Wang (4) , Qi Lyu (1) , Hichem Snoussi (5)

1 BUAA - Beihang University
2 Center for Applied Mathematics, Tianjin University
3 Dalian Maritime University
4 WHUT - Wuhan University of Technology
5 LM2S - Laboratoire Modélisation et Sûreté des Systèmes

Abnormal event detection is a challenging problem in video surveillance which is essential to the early-warning security and protection system. We propose an algorithm to solve this problem efficiently based on an image descriptor which encodes the movement information and the classification method. The new abnormality indicator is derived from the hidden Markov model which learns the histograms of optical flow orientations of the observed video frames. This indicator measures the similarity between the observed video frame and existing normal frames. The proposed method is evaluated and validated on several video surveillance datasets.

Domains: Signal and Image processing

Tian Wang, Meina Qiao, Yingjun Deng, Yi Zhou, Huan Wang, et al.. Abnormal event detection based on analysis of movement information of video sequence. Optik, 2018, 152, pp.50-60. ⟨10.1016/j.ijleo.2017.07.064⟩. ⟨hal-03320601⟩