Abnormal event detection based on deep autoencoder fusing optical flow

doi:10.23919/ChiCC.2017.8029129

	Abnormal event detection based on deep autoencoder fusing optical flow
	Qiao, Meina 2; Wang, Tian 2; Li, Jiakun 2; Li, Ce 3; Lin, Zhiwei 1; Snoussi, Hichem 4
	2017-09-07
会议日期	July 26, 2017 - July 28, 2017
会议地点	Dalian, China
关键词	Abnormal event detection Deep autoencoder Optical flow
DOI	10.23919/ChiCC.2017.8029129
页码	11098-11103
英文摘要	As an important research topic in computer vision, abnormal detection has gained more and more attention. In order to detect abnormal events effectively, we propose a novel method using optical flow and deep autoencoder. In our model, optical flow of the original video sequence is calculated and visualized as optical flow image, which is then fed into a deep autoencoder. Then the deep autoencoder extract features from the training samples which are compressed to low dimension vectors. Finally, the normal and abnormal samples gather separately in the coordinate axis. In the evaluation, we show that our approach outperforms the existing methods in different scenes, in terms of accuracy. © 2017 Technical Committee on Control Theory, CAA.
会议录	Chinese Control Conference, CCC
会议录出版者	IEEE Computer Society
会议录出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
语种	英语
资助项目	Gansu Province Basic Research Innovation Group Project[1506RJIA031]
ISSN号	19341768
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
WOS记录号	WOS:000432015504177
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/118153]
专题	电气工程与信息工程学院
通讯作者	Wang, Tian
作者单位	1.Ulster Univ, Sch Comp, Coleraine BT37 0QB, Londonderry, North Ireland 2.Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China 3.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Gansu, Peoples R China 4.Univ Technol Troyes, CNRS, UMR 6279, Inst Charles Delaunay,LM2S,STMR, F-10004 Troyes, France
推荐引用方式 GB/T 7714	Qiao, Meina,Wang, Tian,Li, Jiakun,et al. Abnormal event detection based on deep autoencoder fusing optical flow[C]. 见:. Dalian, China. July 26, 2017 - July 28, 2017.