Robust Deformable and Occluded Object Tracking With Dynamic Graph

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Robust Deformable and Occluded Object Tracking With Dynamic Graph
	Cai, Zhaowei 1; Wen, Longyin 2; Lei, Zhen2 ; Vasconcelos, Nuno 1; Li, Stan Z.2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2014-12-01
卷号	23 期号:12 页码:5497-5509
文章类型	Article
摘要	While some efforts have been paid to handle deformation and occlusion in visual tracking, they are still great challenges. In this paper, a dynamic graph-based tracker (DGT) is proposed to address these two challenges in a unified framework. In the dynamic target graph, nodes are the target local parts encoding appearance information, and edges are the interactions between nodes encoding inner geometric structure information. This graph representation provides much more information for tracking in the presence of deformation and occlusion. The target tracking is then formulated as tracking this dynamic undirected graph, which is also a matching problem between the target graph and the candidate graph. The local parts within the candidate graph are separated from the background with Markov random field, and spectral clustering is used to solve the graph matching. The final target state is determined through a weighted voting procedure according to the reliability of part correspondence, and refined with recourse to a foreground/background segmentation. An effective online updating mechanism is proposed to update the model, allowing DGT to robustly adapt to variations of target structure. Experimental results show improved performance over several state-of-the-art trackers, in various challenging scenarios.
关键词	Visual Tracking Dynamic Graph Graph Matching Deformation Occlusion
WOS标题词	Science & Technology ; Technology
关键词[WOS]	ENERGY MINIMIZATION ; ONLINE
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000345565000001
引用统计	被引频次：74[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/173211/8022
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
作者单位	1.Univ Calif San Diego, Dept Elect & Comp Engn, La Jolla, CA 92093 USA 2.Chinese Acad Sci, Inst Automat, Ctr Biometr & Secur Res, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cai, Zhaowei,Wen, Longyin,Lei, Zhen,et al. Robust Deformable and Occluded Object Tracking With Dynamic Graph[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2014,23(12):5497-5509.
APA	Cai, Zhaowei,Wen, Longyin,Lei, Zhen,Vasconcelos, Nuno,&Li, Stan Z..(2014).Robust Deformable and Occluded Object Tracking With Dynamic Graph.IEEE TRANSACTIONS ON IMAGE PROCESSING,23(12),5497-5509.
MLA	Cai, Zhaowei,et al."Robust Deformable and Occluded Object Tracking With Dynamic Graph".IEEE TRANSACTIONS ON IMAGE PROCESSING 23.12(2014):5497-5509.