Visible to the public Abnormal crowd behavior detection using interest points

TitleAbnormal crowd behavior detection using interest points
Publication TypeConference Paper
Year of Publication2014
AuthorsYueguo Zhang, Lili Dong, Shenghong Li, Jianhua Li
Conference NameBroadband Multimedia Systems and Broadcasting (BMSB), 2014 IEEE International Symposium on
Date PublishedJune
Keywordsabnormal crowd behavior detection, behavioural sciences computing, Broadband communication, Broadcasting, complex network-based algorithm, complex networks, Computer vision, Crowd Behavior, crowd behavior feature analysis, feature extraction, global texture feature extraction, image texture, interest point detection, Multimedia systems, object detection, video processing, video signal processing, video surveillance

Abnormal crowd behavior detection is an important research issue in video processing and computer vision. In this paper we introduce a novel method to detect abnormal crowd behaviors in video surveillance based on interest points. A complex network-based algorithm is used to detect interest points and extract the global texture features in scenarios. The performance of the proposed method is evaluated on publicly available datasets. We present a detailed analysis of the characteristics of the crowd behavior in different density crowd scenes. The analysis of crowd behavior features and simulation results are also demonstrated to illustrate the effectiveness of our proposed method.

Citation Key6873527