Learning A Superpixel-Driven Speed Function for Level Set Tracking

doi:10.1109/TCYB.2015.2451100

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

	Learning A Superpixel-Driven Speed Function for Level Set Tracking
	Zhou, Xue 1; Li, Xi 2; Hu, Weiming3
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2016-07-01
卷号	46 期号:7 页码:1498-1510
文章类型	Article
摘要	A key problem in level set tracking is to construct a discriminative speed function for effective contour evolution. In this paper, we propose a level set tracking method based on a discriminative speed function, which produces a superpixel-driven force for effective level set evolution. Based on kernel density estimation and metric learning, the speed function is capable of effectively encoding the discriminative information on object appearance within a feasible metric space. Furthermore, we introduce adaptive object shape modeling into the level set evolution process, which leads to the tracking robustness in complex scenarios. To ensure the efficiency of adaptive object shape modeling, we develop a simple but efficient weighted non-negative matrix factorization method that can online learn an object shape dictionary. Experimental results on a number of challenging video sequences demonstrate the effectiveness and robustness of the proposed tracking method.
关键词	Level Set Tracking Metric Learning Non-negative Matrix Factorization (Nf) Speed Function Superpixel (Sp)-driven
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2015.2451100
关键词[WOS]	GEODESIC ACTIVE CONTOURS ; IMAGE SEGMENTATION ; MATRIX FACTORIZATION ; VISUAL TRACKING ; OBJECT TRACKING ; SHAPE PRIORS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(NSFC 61472063 ; 973 Basic Research Program of China(2014CB349303) ; Fundamental Research Funds for the Central Universities(ZYGX 2011J076) ; China Knowledge Centre for Engineering Sciences and Technology ; National Basic Research Program of China(2012CB316400) ; Zhejiang Provincial Engineering Center on Media Data Cloud Processing and Analysis ; NVIDIA CUDA Research Center Program ; Microsoft Research Asia Collaborative Research Program ; MOE-Microsoft Key Laboratory, Zhejiang University ; 61472353)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000379757900002
引用统计	被引频次：9[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/173211/12153
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.Univ Elect Sci & Technol China, Dept Automat Engn, Chengdu 611731, Peoples R China 2.Zhejiang Univ, Coll Comp Sci, Hangzhou 310027, Zhejiang, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Xue,Li, Xi,Hu, Weiming. Learning A Superpixel-Driven Speed Function for Level Set Tracking[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(7):1498-1510.
APA	Zhou, Xue,Li, Xi,&Hu, Weiming.(2016).Learning A Superpixel-Driven Speed Function for Level Set Tracking.IEEE TRANSACTIONS ON CYBERNETICS,46(7),1498-1510.
MLA	Zhou, Xue,et al."Learning A Superpixel-Driven Speed Function for Level Set Tracking".IEEE TRANSACTIONS ON CYBERNETICS 46.7(2016):1498-1510.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Learning a superpixe（2788KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载