Robust tracking with adaptive appearance learning and occlusion detection

doi:10.1007/s00530-015-0460-y

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Robust tracking with adaptive appearance learning and occlusion detection
	Ding, Jianwei 1; Tang, Yunqi 1; Tian, Huawei 1; Liu, Wei 2; Huang, Yongzhen3
刊名	MULTIMEDIA SYSTEMS
	2016-03-01
卷号	22 期号:2 页码:255-269
关键词	Object Tracking Manifold Occlusion Detection Graph Cuts
DOI	10.1007/s00530-015-0460-y
文献子类	Article
英文摘要	It is still challenging to design a robust and efficient tracking algorithm in complex scenes. We propose a new object tracking algorithm with adaptive appearance learning and occlusion detection in an efficient self-tuning particle filter framework. The appearance of an object is modeled with a set of weighted and ordered submanifolds, which can guarantee the adaptability when there is fast illumination or pose change. To overcome the occlusion problem, we use the reconstruction error data of the appearance model to extract occlusion region by graph cuts. And the tracking result is improved with feedback of occlusion detection. The motion model is also integrated with adaptability to overcome the abrupt motion problem. To improve the efficiency of particle filter, the number of samples is tuned with respect to the scene conditions. Experimental results demonstrate that our algorithm can achieve great robustness, high accuracy and good efficiency in challenging scenes.
WOS关键词	VISUAL TRACKING ; OBJECT TRACKING ; MODELS
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000376407000008
资助机构	Fundamental Research Funds for the Central Universities(2014JKF01116) ; National High Technology Research and Development Program of China(2013AA014604) ; National Natural Science Foundation of China(61402484 ; SAMSUNG GRO Program ; CCF-Tencent Program ; 360 OpenLab Program ; 61203252)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/12226]
专题	自动化研究所_智能感知与计算研究中心
作者单位	1.Peoples Publ Secur Univ China, Beijing, Peoples R China 2.Nanyang Normal Univ, Nanyang, Henan, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ding, Jianwei,Tang, Yunqi,Tian, Huawei,et al. Robust tracking with adaptive appearance learning and occlusion detection[J]. MULTIMEDIA SYSTEMS,2016,22(2):255-269.
APA	Ding, Jianwei,Tang, Yunqi,Tian, Huawei,Liu, Wei,&Huang, Yongzhen.(2016).Robust tracking with adaptive appearance learning and occlusion detection.MULTIMEDIA SYSTEMS,22(2),255-269.
MLA	Ding, Jianwei,et al."Robust tracking with adaptive appearance learning and occlusion detection".MULTIMEDIA SYSTEMS 22.2(2016):255-269.