Human Pose Estimation and Tracking via Parsing a Tree Structure Based Human Model

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 视频内容安全团队

	Human Pose Estimation and Tracking via Parsing a Tree Structure Based Human Model
	Zhang, Xiaoqin 1; Li, Changcheng 2; Hu, Weiming3 ; Tong, Xiaofeng 4; Maybank, Steve 5; Zhang, Yimin 4
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2014-05-01
卷号	44 期号:5 页码:580-592
关键词	Human pose estimation Markov Chain Monte Carlo parse tracking
英文摘要	Human pose estimation and tracking is the task of determining the states (location, orientation, and scale) of each body part over time. It is important for many vision understanding applications, such as visual interactive gaming, immersive virtual reality, visual surveillance, and content-based image retrieval. However, it remains a challenging task due to unknown image background, presence of clutter and especially the high dimensional state space (usually 30+ dimensions). In this paper, we contribute to human pose estimation and tracking in two aspects. First, we design two efficient Markov Chain dynamics under the data-driven Markov Chain Monte Carlo framework to effectively explore the high dimensional state space. Second, we parse the tree structure state space into a lexicographic order according to the image observations and body topology, and the optimization process is conducted in this order. This realizes a much more efficient exploration of the state space than the sampling based search or exhaustive search, and thus achieves a tremendous speed-up. Experimental results demonstrate the efficiency and effectiveness of the proposed method in estimating and tracking various kinds of human poses, even against cluttered backgrounds, in poor illumination or under partial self-occlusion.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Automation & Control Systems ; Computer Science, Cybernetics
研究领域[WOS]	Automation & Control Systems ; Computer Science
关键词[WOS]	OBJECT RECOGNITION ; CONFIGURATIONS ; SEGMENTATION ; CONSTRAINTS ; REGIONS ; PEOPLE ; IMAGES ; 2D
收录类别	SCI
语种	英语
WOS记录号	WOS:000335226900006
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/3277]
专题	自动化研究所_模式识别国家重点实验室_视频内容安全团队
作者单位	1.Wenzhou Univ, Inst Intelligent Syst & Decis, Wenzhou 325000, Zhejiang, Peoples R China 2.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100021, Peoples R China 4.Intel China Res Ctr, Beijing 100080, Peoples R China 5.Univ London Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
推荐引用方式 GB/T 7714	Zhang, Xiaoqin,Li, Changcheng,Hu, Weiming,et al. Human Pose Estimation and Tracking via Parsing a Tree Structure Based Human Model[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2014,44(5):580-592.
APA	Zhang, Xiaoqin,Li, Changcheng,Hu, Weiming,Tong, Xiaofeng,Maybank, Steve,&Zhang, Yimin.(2014).Human Pose Estimation and Tracking via Parsing a Tree Structure Based Human Model.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,44(5),580-592.
MLA	Zhang, Xiaoqin,et al."Human Pose Estimation and Tracking via Parsing a Tree Structure Based Human Model".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 44.5(2014):580-592.