Tracking Human Pose Using Max-Margin Markov Models

doi:10.1109/TIP.2015.2473662

OPT OpenIR > 光谱成像技术研究室

	Tracking Human Pose Using Max-Margin Markov Models
	Zhao, Lin 1; Gao, Xinbo 2; Tao, Dacheng3,4 ; Li, Xuelong5
	2015-12-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
卷号	24 期号:12 页码:5274-5287
摘要	We present a new method for tracking human pose by employing max-margin Markov models. Representing a human body by part-based models, such as pictorial structure, the problem of pose tracking can be modeled by a discrete Markov random field. Considering max-margin Markov networks provide an efficient way to deal with both structured data and strong generalization guarantees, it is thus natural to learn the model parameters using the max-margin technique. Since tracking human pose needs to couple limbs in adjacent frames, the model will introduce loops and will be intractable for learning and inference. Previous work has resorted to pose estimation methods, which discard temporal information by parsing frames individually. Alternatively, approximate inference strategies have been used, which can overfit to statistics of a particular data set. Thus, the performance and generalization of these methods are limited. In this paper, we approximate the full model by introducing an ensemble of two tree-structured sub-models, Markov networks for spatial parsing and Markov chains for temporal parsing. Both models can be trained jointly using the max-margin technique, and an iterative parsing process is proposed to achieve the ensemble inference. We apply our model on three challengeable data sets, which contains highly varied and articulated poses. Comprehensive experimental results demonstrate the superior performance of our method over the state-of-the-art approaches.
文章类型	Article
关键词	Pose Tracking Pose Estimation Max-margin Articulated Shapes
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TIP.2015.2473662
收录类别	SCI ; EI
关键词[WOS]	ACTION RECOGNITION ; PICTORIAL STRUCTURES ; FLEXIBLE MIXTURES ; PEOPLE ; VIDEO ; FLOW ; PROPAGATION ; PARTS
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000362488900013
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/25434
专题	光谱成像技术研究室
作者单位	1.Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China 2.Xidian Univ, Sch Elect Engn, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China 3.Univ Technol, Ctr Quantum Computat & Intelligent Syst, Sydney, NSW 2007, Australia 4.Univ Technol, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia 5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Lin,Gao, Xinbo,Tao, Dacheng,et al. Tracking Human Pose Using Max-Margin Markov Models[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015,24(12):5274-5287.
APA	Zhao, Lin,Gao, Xinbo,Tao, Dacheng,&Li, Xuelong.(2015).Tracking Human Pose Using Max-Margin Markov Models.IEEE TRANSACTIONS ON IMAGE PROCESSING,24(12),5274-5287.
MLA	Zhao, Lin,et al."Tracking Human Pose Using Max-Margin Markov Models".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.12(2015):5274-5287.

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
Tracking Human Pose （4300KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	请求全文