Abnormal Event Detection Using HOSF

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Proceeding > Item 987654321/97001

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/97001

Title:	Abnormal Event Detection Using HOSF
Authors:	Yen, Shwu-Huey;Wang, Chun-Hui
Contributors:	淡江大學資訊工程學系
Keywords:	normality;crowd;social force (SF);histogram of oriented social force (HOSF);z-value
Date:	2013-12-16
Issue Date:	2014-03-14 16:25:32 (UTC+8)
Abstract:	In this paper a simple and effective crowd behavior normality method is proposed. We use the histogram of oriented social force (HOSF) as the feature vector to encode the observed events of a surveillance video. A dictionary of codewords is trained to include typical HOSFs. To detect whether an event is normal is accomplished by comparing how similar to the closest codeword via z-value. The proposed method includes the following characteristic: (1) the training is automatic without human labeling; (2) instead of object tracking, the method integrates particles and social force as feature descriptors; (3) z-score is used in measuring the normality of events. The method is testified by the UMN dataset with promising results.
Relation:	Proceedings of the International Conference on IT Convergence and Security (ICITCS 2013), 4p.
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Proceeding

Files in This Item:

File	Description	Size	Format
Abnormal Event Detection Using HOSF.pdf		635Kb	Adobe PDF	725	View/Open