Multi-view Gymnastic Activity Recognition with Fused HMM

CASIA OpenIR > 智能感知与计算研究中心

	Multi-view Gymnastic Activity Recognition with Fused HMM
	Ying Wang; Kaiqi Huang; Tieniu Tan
	2007
会议名称	the 8th Asian Conference on Computer Vision
会议录名称	the 8th Asian Conference on Computer Vision
页码	667-677
会议日期	2007
会议地点	Tokyo, Japan
摘要	More and more researchers focus their studies on multi-view activity recognition, because a fixed view could not provide enough information for recognition. In this paper, we use multi-view features to recognize six kinds of gymnastic activities. Firstly, shape-based features are extracted from two orthogonal cameras in the form of 脗\Re transform. Then a multi-view approach based on Fused HMM is proposed to combine different features for similar gymnastic activity recognition. Compared with other activity models, our method achieves better performance even in the case of frame loss.
关键词	Multi-view Gymnastic Activity Recognition
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12716
专题	智能感知与计算研究中心
通讯作者	Kaiqi Huang
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Ying Wang,Kaiqi Huang,Tieniu Tan. Multi-view Gymnastic Activity Recognition with Fused HMM[C],2007:667-677.