Robust Visual Tracking Via Consistent Low-Rank Sparse Learning

doi:10.1007/s11263-014-0738-0

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 > 多媒体计算与图形学团队

	Robust Visual Tracking Via Consistent Low-Rank Sparse Learning
	Zhang, Tianzhu1,2 ; Liu, Si 3; Ahuja, Narendra 4; Yang, Ming-Hsuan 5; Ghanem, Bernard 2,6; Si Liu
刊名	International Journal of Computer Vision
	2015
卷号	111 期号:2 页码:171-190
关键词	Visual Tracking Temporal Consistency Sparse Representation Low-rank Representation
DOI	10.1007/s11263-014-0738-0
文献子类	期刊
英文摘要	Object tracking is the process of determining the states of a target in consecutive video frames based on properties of motion and appearance consistency. In this paper, we propose a consistent low-rank sparse tracker (CLRST) that builds upon the particle filter framework for tracking. By exploiting temporal consistency, the proposed CLRST algorithm adaptively prunes and selects candidate particles. By using linear sparse combinations of dictionary templates, the proposed method learns the sparse representations of image regions corresponding to candidate particles jointly by exploiting the underlying low-rank constraints. In addition, the proposed CLRST algorithm is computationally attractive since temporal consistency property helps prune particles and the low-rank minimization problem for learning joint sparse representations can be efficiently solved by a sequence of closed form update operations. We evaluate the proposed CLRST algorithm against 14 state-of-the-art tracking methods on a set of 25 challenging image sequences. Experimental results show that the CLRST algorithm performs favorably against state-of-the-art tracking methods in terms of accuracy and execution time.
学科主题	Computer Science
URL标识	查看原文
资助项目	NSF CAREER Grant ; research grant for the Human Sixth Sense Programme at the Advanced Digital Sciences Center from Singapore's Agency for Science, Technology and Research (A*STAR)
WOS关键词	OBJECT TRACKING ; REPRESENTATION
WOS研究方向	Computer Science
项目编号	1149783
语种	英语
WOS记录号	WOS:000348345500003
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/13642]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Si Liu
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.Advanced Digital Sciences Center, Singapore 3.National University of Singapore 4.University of Illinois at Urbana-Champaign 5.University of California Merced 6.King Abdullah University of Science and Technology
推荐引用方式 GB/T 7714	Zhang, Tianzhu,Liu, Si,Ahuja, Narendra,et al. Robust Visual Tracking Via Consistent Low-Rank Sparse Learning[J]. International Journal of Computer Vision,2015,111(2):171-190.
APA	Zhang, Tianzhu,Liu, Si,Ahuja, Narendra,Yang, Ming-Hsuan,Ghanem, Bernard,&Si Liu.(2015).Robust Visual Tracking Via Consistent Low-Rank Sparse Learning.International Journal of Computer Vision,111(2),171-190.
MLA	Zhang, Tianzhu,et al."Robust Visual Tracking Via Consistent Low-Rank Sparse Learning".International Journal of Computer Vision 111.2(2015):171-190.