View-invariant Action Recognition in Surveillance Videos

CASIA OpenIR > 智能感知与计算研究中心

	View-invariant Action Recognition in Surveillance Videos
	Fang Zhang; Yunhong Wang; Zhaoxiang Zhang
	2011-11-28
会议名称	1st Asian Conference on Pattern Recognition
会议录名称	ACPR 2011
会议日期	28th November 2011
会议地点	Beijing, China
摘要	Recently, human action recognition has been a popular and important topic in computer vision. However, except some conventional problems such as noise, low resolution etc., view-invariant recognition is one of the most challenging problems. In this paper, we focus on solve multi-view action recognition from surveillance video. To detect moving objects from complicated backgrounds, this paper employs improved Gaussian mixed model, which uses K-means clustering to initialize the model and it gets better motion detection results for surveillance videos. We demonstrate the silhouette representation “Envelope Shape” can solve the viewpoint problem in surveillance videos. The experiment results demonstrate that our human action recognition system is fast and efficient on CASIA activity analysis database.
关键词	Videos Gaussian Distribution Surveillance Shape Humans Hidden Markov Models Databases
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13277
专题	智能感知与计算研究中心
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Fang Zhang,Yunhong Wang,Zhaoxiang Zhang. View-invariant Action Recognition in Surveillance Videos[C],2011.