Anomaly detection in crowd scene via online learning

OPT OpenIR > 光谱成像技术研究室

	Anomaly detection in crowd scene via online learning
	Ma, Dandan; Wang, Qi; Yuan, Yuan
	2014
会议名称	6th International Conference on Internet Multimedia Computing and Service, ICIMCS 2014
会议录名称	ICIMCS 2014 - Proceedings of the 6th International Conference on Internet Multimedia Computing and Service
页码	158-162
会议日期	2014-07-10
会议地点	Xiamen, China
会议主办者	National Natural Foundation of China; SIGMM China Chapter; Xiamen University
出版者	Association for Computing Machinery
产权排序	1
摘要	Anomaly detection in crowd scene has attracted an increasing attention in video surveillance, but a precise detection still remains a challenge. This paper presents a novel online learning method to automatically detect abnormal behaviors in crowd scene. Our focus is mainly on the deviation between the real motion and the predicted one. Through on-line defining experts, analyzing their motions, and dynamically updating the learned model, anomaly can be identified by the final expert joint decision. The outputs are represented as the anomaly probability of an examined frame. Compared with most of existing methods, the proposed one needs neither tracking each individual straight to the end nor requires any complex training procedure. We test the proposed method on public datasets, and the results show its effectiveness. Copyright 2014 ACM.
作者部门	光学影像学习与分析中心
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.opt.ac.cn/handle/181661/22640
专题	光谱成像技术研究室
推荐引用方式 GB/T 7714	Ma, Dandan,Wang, Qi,Yuan, Yuan. Anomaly detection in crowd scene via online learning[C]:Association for Computing Machinery,2014:158-162.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Anomaly detection in（821KB）			限制开放	CC BY-NC-SA	请求全文