Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation

doi:10.1109/TIP.2014.2352497

	Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation
	Dong, Weisheng 1; Shi, Guangming 1; Hu, Xiaocheng 2; Ma, Yi3,4
	2014-10
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING (IF:10.8[JCR-2023],12.1[5-Year])
ISSN	1057-7149
卷号	23 期号:10 页码:4527-4538
发表状态	已发表
DOI	10.1109/TIP.2014.2352497
摘要	Designing an appropriate regularizer is of great importance for accurate optical flow estimation. Recent works exploiting the nonlocal similarity and the sparsity of the motion field have led to promising flow estimation results. In this paper, we propose to unify these two powerful priors. To this end, we propose an effective flow regularization technique based on joint low-rank and sparse matrix recovery. By grouping similar flow patches into clusters, we effectively regularize the motion field by decomposing each set of similar flow patches into a low-rank component and a sparse component. For better enforcing the low-rank property, instead of using the convex nuclear norm, we use the log det (.) function as the surrogate of rank, which can also be efficiently minimized by iterative singular value thresholding. Experimental results on the Middlebury benchmark show that the performance of the proposed nonlocal sparse and low-rank regularization method is higher than (or comparable to) those of previous approaches that harness these same priors, and is competitive to current state-of-the-art methods.
关键词	Optical flow low-rank sparse representation nonlocal self-similarity
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	Fundamental Research Funds of the Central Universities of China[BDY081424]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000342159100008
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20144100082984
EI主题词	Benchmarking ; Iterative methods
EI分类号	Light/Optics:741.1 ; Industrial Engineering and Management:912 ; Production Planning and Control; Manufacturing:913 ; Numerical Methods:921.6
WOS关键词	SEGMENTATION ; MINIMIZATION
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/2370
专题	信息科学与技术学院信息科学与技术学院_PI研究组_马毅组
通讯作者	Dong, Weisheng
作者单位	1.Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China 2.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230000, Peoples R China 3.Shanghai Tech Univ, Sch Informat Sci & Technol, Shanghai 200444, Peoples R China 4.Univ Illinois, Dept Elect & Comp Engn, Champaign, IL 61820 USA
推荐引用方式 GB/T 7714	Dong, Weisheng,Shi, Guangming,Hu, Xiaocheng,et al. Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2014,23(10):4527-4538.
APA	Dong, Weisheng,Shi, Guangming,Hu, Xiaocheng,&Ma, Yi.(2014).Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation.IEEE TRANSACTIONS ON IMAGE PROCESSING,23(10),4527-4538.
MLA	Dong, Weisheng,et al."Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation".IEEE TRANSACTIONS ON IMAGE PROCESSING 23.10(2014):4527-4538.