Layered Multitask Tracker via Spatial-Temporal Laplacian Graph

doi:10.1109/LSP.2017.2756998

IMR OpenIR

	Layered Multitask Tracker via Spatial-Temporal Laplacian Graph
	Fan, Baojie 1; Li, Xiaomao 2; Cong, Yang 3
通讯作者	Fan, Baojie(jobfbj@gmail.com)
	2017-12-01
发表期刊	IEEE SIGNAL PROCESSING LETTERS
ISSN	1070-9908
卷号	24 期号:12 页码:1768-1772
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.
关键词	Object tracking reverse layered multitask learning spatial-temporal Laplacian graphs weighted similarity map
资助者	China Postdoctoral Science Foundation ; Foundation of Nanjing University of Tele. and Com.
DOI	10.1109/LSP.2017.2756998
收录类别	SCI
语种	英语
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
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000413334300003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/127020
专题	中国科学院金属研究所
通讯作者	Fan, Baojie
作者单位	1.Nanjing Univ Posts & Telecommun, Automat Coll, Nanjing, Jiangsu, Peoples R China 2.Shanghai Univ, Shanghai, 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.