Layered Multitask Tracker via Spatial-Temporal Laplacian Graph

doi:10.1109/LSP.2017.2756998

CORC > 金属研究所 > 中国科学院金属研究所

	Layered Multitask Tracker via Spatial-Temporal Laplacian Graph
	Fan, Baojie 2; Li, Xiaomao 1; Cong, Yang 3
刊名	IEEE SIGNAL PROCESSING LETTERS
	2017-12-01
卷号	24 期号:12 页码:1768-1772
关键词	Object tracking reverse layered multitask learning spatial-temporal Laplacian graphs weighted similarity map
ISSN号	1070-9908
DOI	10.1109/LSP.2017.2756998
通讯作者	Fan, Baojie(jobfbj@gmail.com)
英文摘要	Most multitask trackers define the trace of each candidate as one task, and assume all tasks are equally related. Multitask learning is only evaluated on the current frame. In fact, these assumptions are limited, and ignore the multitask relationship in consecutive frames. In this letter, we propose a discriminative layered multitask tracker via spatial-temporal Laplacian graphs, which defines the layered tasks from a novel view, and naturally incorporates the global and local target information into reverse multitask tracking process. The spatial-temporal Laplacian graphs not only exploit the sequential consistent information of the target, but also make full use of the geometric structure corresponding to the tasks among the adjacent frames. Besides, l(0) norm constraint and labeling information are used to improve the tracking robustness. Encouraging experimental results on challenging sequences justify that the proposed method performs well both in accuracy and robustness against some related trackers.
资助项目	China Postdoctoral Science Foundation[2015M571785] ; China Postdoctoral Science Foundation[2016T90484] ; Foundation of Nanjing University of Tele. and Com.[NY215148] ; Foundation of Nanjing University of Tele. and Com.[NY217061]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000413334300003
资助机构	China Postdoctoral Science Foundation ; Foundation of Nanjing University of Tele. and Com.
内容类型	期刊论文
源URL	[http://ir.imr.ac.cn/handle/321006/127019]
专题	金属研究所_中国科学院金属研究所
通讯作者	Fan, Baojie
作者单位	1.Shanghai Univ, Shanghai, Peoples R China 2.Nanjing Univ Posts & Telecommun, Automat Coll, Nanjing, Jiangsu, Peoples R China 3.Chinese Acad Sci, State Key Lab Robot, Shenyang, Peoples R China
推荐引用方式 GB/T 7714	Fan, Baojie,Li, Xiaomao,Cong, Yang. Layered Multitask Tracker via Spatial-Temporal Laplacian Graph[J]. IEEE SIGNAL PROCESSING LETTERS,2017,24(12):1768-1772.
APA	Fan, Baojie,Li, Xiaomao,&Cong, Yang.(2017).Layered Multitask Tracker via Spatial-Temporal Laplacian Graph.IEEE SIGNAL PROCESSING LETTERS,24(12),1768-1772.
MLA	Fan, Baojie,et al."Layered Multitask Tracker via Spatial-Temporal Laplacian Graph".IEEE SIGNAL PROCESSING LETTERS 24.12(2017):1768-1772.