Stratification approach for 3-D Euclidean reconstruction of nonrigid objects from uncalibrated image sequences

CASIA OpenIR > 09年以前成果

	Stratification approach for 3-D Euclidean reconstruction of nonrigid objects from uncalibrated image sequences
	Wang, Guanghui 1,2,3; Wu, Q. M. Jonathan 1
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
	2008-02-01
卷号	38 期号:1 页码:90-101
文章类型	Article
摘要	This paper addresses the problem of 3-D reconstruction of nonrigid objects from uncalibrated image sequences. Under the assumption of affine camera and that the nonrigid object is composed of a rigid part and a deformation part, we propose a stratification approach to recover the structure of nonrigid objects by first reconstructing the structure in affine space and then upgrading it to the Euclidean space. The novelty and main features of the method lies in several aspects. First, we propose a deformation weight constraint to the problem and prove the invariability between the recovered structure and shape bases under this constraint. The constraint was not observed by previous studies. Second, we propose a constrained power factorization algorithm to recover the deformation structure in affine space. The algorithm overcomes some limitations of a previous singular-value-decomposition-based method. It can even work with missing data in the tracking matrix. Third, we propose to separate the rigid features from the deformation ones in 3-D affine space, which makes the detection more accurate and robust. The stratification matrix is estimated from the rigid features, which may relax the influence of large tracking errors in the deformation part. Extensive experiments on synthetic data and real sequences validate the proposed method and show improvements over existing solutions.
关键词	Constrained Power Factorization (Cpf) Deformation Weight Constraint Motion Analysis Nonrigid Factorization Stratified 3-d Reconstruction Structure From Motion
WOS标题词	Science & Technology ; Technology
关键词[WOS]	FACTORIZATION METHOD ; MOTION ; SHAPE ; STREAMS
收录类别	SCI
语种	英语
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000252611700010
引用统计	被引频次：21[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/9614
专题	09年以前成果
作者单位	1.Univ Windsor, Dept Elect & Comp Engn, Windsor, ON N9B 3P4, Canada 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100080, Peoples R China 3.Aviat Univ, Dept Control Engn, Changchun 130022, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Guanghui,Wu, Q. M. Jonathan. Stratification approach for 3-D Euclidean reconstruction of nonrigid objects from uncalibrated image sequences[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,2008,38(1):90-101.
APA	Wang, Guanghui,&Wu, Q. M. Jonathan.(2008).Stratification approach for 3-D Euclidean reconstruction of nonrigid objects from uncalibrated image sequences.IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,38(1),90-101.
MLA	Wang, Guanghui,et al."Stratification approach for 3-D Euclidean reconstruction of nonrigid objects from uncalibrated image sequences".IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 38.1(2008):90-101.