Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking

doi:10.1109/TPAMI.2015.2509979

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 > 生物识别与安全技术研究中心

	Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking
	Wen, Longyin 1,2; Lei, Zhen1,2 ; Lyu, Siwei 3; Li, Stan Z.1,2 ; Yang, Ming-Hsuan 4
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2016-10-01
卷号	38 期号:10 页码:1983-1996
关键词	Multi-object Tracking Tracklet Hierarchical Undirected Affinity Hypergraph Dense Structures
DOI	10.1109/TPAMI.2015.2509979
文献子类	Article
英文摘要	Most multi-object tracking algorithms are developed within the tracking-by-detection framework that consider the pairwise appearance similarities between detection responses or tracklets within a limited temporal window, and thus less effective in handling long-term occlusions or distinguishing spatially close targets with similar appearance in crowded scenes. In this work, we propose an algorithm that formulates the multi-object tracking task as one to exploit hierarchical dense structures on an undirected hypergraph constructed based on tracklet affinity. The dense structures indicate a group of vertices that are inter-connected with a set of hyperedges with high affinity values. The appearance and motion similarities among multiple tracklets across the spatio-temporal domain are considered globally by exploiting high-order similarities rather than pairwise ones, thereby facilitating distinguish spatially close targets with similar appearance. In addition, the hierarchical design of the optimization process helps the proposed tracking algorithm handle long-term occlusions robustly. Extensive experiments on various challenging datasets of both multi-pedestrian and multi-face tracking tasks, demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.
WOS关键词	MULTIPLE-TARGET TRACKING ; ROBUST FACE TRACKING ; MULTITARGET TRACKING ; APPEARANCE MODELS ; CRF MODEL ; GRAPH ; FRAMEWORK ; LINKING ; SCENES
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000384240600005
资助机构	National Natural Science Foundation of China(61375037 ; National Science and Technology Support Program Project(2013BAK02B01) ; Chinese Academy of Sciences Project(KGZD-EW-102-2) ; AuthenMetric RD Funds ; US NSF(IIS-0953373 ; NSF(1149783) ; NSF IIS Grant(1152576) ; 61473291 ; CCF-1319800) ; 61572501 ; 61572536)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/12658]
专题	自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
作者单位	1.Chinese Acad Sci, Ctr Biometr & Secur Res, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.SUNY Albany, Dept Comp Sci, Albany, GA USA 4.Univ Calif Merced, Sch Engn, Merced, CA USA
推荐引用方式 GB/T 7714	Wen, Longyin,Lei, Zhen,Lyu, Siwei,et al. Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2016,38(10):1983-1996.
APA	Wen, Longyin,Lei, Zhen,Lyu, Siwei,Li, Stan Z.,&Yang, Ming-Hsuan.(2016).Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,38(10),1983-1996.
MLA	Wen, Longyin,et al."Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 38.10(2016):1983-1996.