Data-driven human model estimation for realtime motion capture

doi:10.1016/j.jvlc.2018.05.001

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Data-driven human model estimation for realtime motion capture
	Zhai, Wenpeng 3; Su, Le 3; Xia, Shihong 4; Liao, Lianjun 1,2,4
刊名	JOURNAL OF VISUAL LANGUAGES AND COMPUTING
	2018-10-01
卷号	48 页码:10-18
关键词	Human model estimation Data driven Human motion capture Depth image
ISSN号	1045-926X
DOI	10.1016/j.jvlc.2018.05.001
英文摘要	In this paper, we present a practicable method to estimate individual 3D human model in a low cost multi-view realtime 3D human motion capture system. The key idea is: using human geometric model database and human motion database to establish geometric priors and pose prior model; when given the geometric prior, pose prior and a standard template geometry model, the individual human body model and its embedded skeleton can be estimated from the 3D point cloud captured from multiple depth cameras. Because of the introduction of the global prior model of body pose and shapes into a unified nonlinear optimization problem, the accuracy of geometric model estimation is significantly improved. The experiments on the synthesized data set with noise or without noise and the real data set captured from multiple depth cameras show that the estimation results of our method are more reasonable and accurate than the classical methods, and our method is better noise-immunity. The proposed new individual 3D geometric model estimation method is suitable for online realtime human motion tracking system.
资助项目	Knowledge Innovation Program of the Institute of Computing Technology of the Chinese Academy of Sciences[ICT20166040] ; Science and Technology Service Network Initiative of Chinese Academy of Sciences[KFJ-STS-ZDTP-017] ; National Natural Science Foundation of China[61772499] ; National Natural Science Foundation of China[61603396]
WOS研究方向	Computer Science
语种	英语
出版者	ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
WOS记录号	WOS:000448625700003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/3632]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xia, Shihong
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.North China Univ Technol, Beijing 100144, Peoples R China 3.Civil Aviat Univ China, Tianjin 300300, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhai, Wenpeng,Su, Le,Xia, Shihong,et al. Data-driven human model estimation for realtime motion capture[J]. JOURNAL OF VISUAL LANGUAGES AND COMPUTING,2018,48:10-18.
APA	Zhai, Wenpeng,Su, Le,Xia, Shihong,&Liao, Lianjun.(2018).Data-driven human model estimation for realtime motion capture.JOURNAL OF VISUAL LANGUAGES AND COMPUTING,48,10-18.
MLA	Zhai, Wenpeng,et al."Data-driven human model estimation for realtime motion capture".JOURNAL OF VISUAL LANGUAGES AND COMPUTING 48(2018):10-18.