interactive event detection in crowd scenes

ISCAS OpenIR

	interactive event detection in crowd scenes
	Qin Lei; Cheng Zhongwei; Huang Qingming; Pang Junbiao
	2012
会议名称	4th International Conference on Internet Multimedia Computing and Service, ICIMCS 2012
会议录名称	ACM International Conference Proceeding Series
页码	46-49
会议日期	September 9, 2012 - September 11, 2012
会议地点	Wuhan, China
收录类别	EI
ISBN	9781450316002
部门归属	(1) Key Lab. of Intel. Inf. Proc. Institute of Computing Technology Chinese Academy of Sciences Beijing China; (2) Graduate University of Chinese Academy of Sciences Beijing China; (3) Beijing Municipal Key Lab. of Multimedia and Intelligent Software Technology Beijing Univ. of Tech. China
摘要	As an important aspect in video content analysis, event detection is still an open problem. In particular, the study on detecting interactive events in crowd scenes is still limited. In this paper, we investigate detecting interactive events between persons, e.g. PeopleMeet, PeopleSplitUp and Embrace in complex scenes using a sequence learning based approach. By sequence learning, the spatial-temporal context information is introduced in the learning stage. Experiments have been performed over TRECVid Event Detection 2010 dataset, which contains totally 144 hours surveillance video of London Gatwick airport. According to the TRECVid-ED 2010 formal evaluation, our approach obtains promising results, with the top performance (NDCR) for PeopleMeet and PeopleSplit-Up, and second-best performance (NDCR) for Embrace. Copyright © 2012 ACM.; As an important aspect in video content analysis, event detection is still an open problem. In particular, the study on detecting interactive events in crowd scenes is still limited. In this paper, we investigate detecting interactive events between persons, e.g. PeopleMeet, PeopleSplitUp and Embrace in complex scenes using a sequence learning based approach. By sequence learning, the spatial-temporal context information is introduced in the learning stage. Experiments have been performed over TRECVid Event Detection 2010 dataset, which contains totally 144 hours surveillance video of London Gatwick airport. According to the TRECVid-ED 2010 formal evaluation, our approach obtains promising results, with the top performance (NDCR) for PeopleMeet and PeopleSplit-Up, and second-best performance (NDCR) for Embrace. Copyright © 2012 ACM.
关键词	Airport Security Internet Network Security Security Systems
主办者	ACM SIGMM China Chapter; Central China Normal University; National Science Foundation of China Academy of Sciences; NEC Laboratories China; Microsoft Research; Wuhan Daqian Information Technology Company Limited
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15812
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Qin Lei,Cheng Zhongwei,Huang Qingming,et al. interactive event detection in crowd scenes[C],2012:46-49.