A Classification Method Based on Multi-Features for Abnormal Crowd Behaviors

• Published in: Applied Mechanics and Materials Vol. 685; no. Machine, Industry and Manufacturing Based on Applied-Information Technology IV; pp. 501 - 506
• Main Authors: Wang, Xiao Fei, Hu, Jun, Yu, Wei, Sun, Rui, Kuang, Yin
• Format: Journal Article
• Language: English
• Published: Zurich Trans Tech Publications Ltd 01.10.2014
• Subjects: Classification; Density; Security; Crowd Density Estimation; Abnormal Crowd Behavior Classification; Crowd Intensity; Abnormal Crowd Behavior Detection
• ISBN: 9783038353256; 3038353256
• ISSN: 1660-9336; 1662-7482; 1662-7482
• DOI: 10.4028/www.scientific.net/AMM.685.501

An abnormal crowd behavior would harm social public security. Different abnormal crowd behaviors would bring about different harms and subject to different attentions of social public. The higher the harm of the abnormal crowd behavior was, the higher the attention of the social public would be. Therefore, in this paper, a classification method, using crowd density estimation and crowd intensity, is proposed for abnormal crowd behaviors. In order to describe the abnormal crowd behavior more reasonably, we shoot some videos. Finally, the effectiveness and accuracy of our method for abnormal behavior classification is validated by the experimental results.