Multi-view Multi-stance Gait Identification

CASIA OpenIR > 智能感知与计算研究中心

	Multi-view Multi-stance Gait Identification
	Maodi Hu; Yunhong Wang; Zhaoxiang Zhang; De Zhang
	2011-09-11
会议名称	IEEE International Conference on Image Processing
会议录名称	ICIP 2011
会议日期	11-14 September 2011
会议地点	Brussels, Belgium
摘要	View transformation in gait analysis has attracted more and more attentions recently. However, most of the existing methods are based on the entire gait dynamics, such as Gait Energy Image (GEI). And the distinctive characteristics of different walking phases are neglected. This paper proposes a multi-view multi-stance gait identification method using unified multi-view population Hidden Markov Models (pHMM-s), in which all the models share the same transition probabilities. Hence, the gait dynamics in each view can be normalized into fixed-length stances by Viterbi decoding. To optimize the view-independent and stance-independent identity vector, a multi-linear projection model is learned from tensor decomposition. The advantage of using tensor is that different types of information are integrated in the final optimal solution. Extensive experiments show that our algorithm achieves promising performances of multi-view gait identification even with incomplete gait cycles.
关键词	Normalized Dynamics Multi-view Multi-stance Gait Identification
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13281
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	Maodi Hu,Yunhong Wang,Zhaoxiang Zhang,et al. Multi-view Multi-stance Gait Identification[C],2011.