Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking
	Hu, Weiming1 ; Li, Xi 1; Zhang, Xiaoqin 2; Shi, Xinchu1 ; Maybank, Stephen 3; Zhang, Zhongfei 4
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2011-02-01
卷号	91 期号:3 页码:303-327
文章类型	Article
摘要	Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based algorithms cannot effectively represent spatial correlations between pixel values. Current tensor subspace-based algorithms construct an offline representation of image ensembles, and current online tensor subspace learning algorithms cannot be applied to background modeling and object tracking. In this paper, we propose an online tensor subspace learning algorithm which models appearance changes by incrementally learning a tensor subspace representation through adaptively updating the sample mean and an eigenbasis for each unfolding matrix of the tensor. The proposed incremental tensor subspace learning algorithm is applied to foreground segmentation and object tracking for grayscale and color image sequences. The new background models capture the intrinsic spatiotemporal characteristics of scenes. The new tracking algorithm captures the appearance characteristics of an object during tracking and uses a particle filter to estimate the optimal object state. Experimental evaluations against state-of-the-art algorithms demonstrate the promise and effectiveness of the proposed incremental tensor subspace learning algorithm, and its applications to foreground segmentation and object tracking.
关键词	Incremental Learning Tensor Subspace Foreground Segmentation Tracking
WOS标题词	Science & Technology ; Technology
关键词[WOS]	ROBUST VISUAL TRACKING ; SHADOW SEGMENTATION ; APPEARANCE MODELS ; REPRESENTATION ; SURVEILLANCE ; RECOGNITION ; PEOPLE ; OBJECT ; CUES
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000286610300005
引用统计	被引频次：117[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/173211/3248
专题	多模态人工智能系统全国重点实验室_视频内容安全
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Wenzhou Univ, Coll Math & Informat Sci, Wenzhou 325000, Zhejiang, Peoples R China 3.Univ London Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England 4.SUNY Binghamton, Binghamton, NY 13902 USA
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hu, Weiming,Li, Xi,Zhang, Xiaoqin,et al. Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2011,91(3):303-327.
APA	Hu, Weiming,Li, Xi,Zhang, Xiaoqin,Shi, Xinchu,Maybank, Stephen,&Zhang, Zhongfei.(2011).Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking.INTERNATIONAL JOURNAL OF COMPUTER VISION,91(3),303-327.
MLA	Hu, Weiming,et al."Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking".INTERNATIONAL JOURNAL OF COMPUTER VISION 91.3(2011):303-327.