Densely connected Siamese network visual tracking

doi:10.1108/IR-01-2021-0010

	Densely connected Siamese network visual tracking
	Zhou, Xiaolong 1; Wang, Pinghao 3; Chan, Sixian 2,3; Fang, Kai 1; Fang, Jianwen 1
刊名	INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION
	2021-06-11
关键词	Robot vision Artificial intelligence Image processing Object tracking Siamese network Dynamic template
ISSN号	0143-991X
DOI	10.1108/IR-01-2021-0010
通讯作者	Chan, Sixian(sxchan@zjut.edu.cn)
英文摘要	Purpose Visual object tracking plays a significant role in intelligent robot systems. This study aims to focus on unlocking the tracking performance potential of the deep network and presenting a dynamic template update strategy for the Siamese trackers. Design/methodology/approach This paper presents a novel and efficient Siamese architecture for visual object tracking which introduces densely connected convolutional layers and a dynamic template update strategy into Siamese tracker. Findings The most advanced performance can be achieved by introducing densely connected convolutional neural networks that have not yet been applied to the tracking task into SiamRPN. By using the proposed architecture, the experimental results demonstrate that the performance of the proposed tracker is 5.8% (area under curve), 5.4% expected average overlap (EAO) and 3.5% (EAO) higher than the baseline on the OTB100, VOT2016 and VOT2018 data sets and achieves an excellent EAO score of 0.292 on the VOT2019 data set. Originality/value This study explores a deeper backbone network with each convolutional network layer densely connected. In response to tracking errors caused by templates that are not updated, this study proposes a dynamic template update strategy.
资助项目	National Natural Science Foundation of China (NSFC)[61876168] ; National Natural Science Foundation of China (NSFC)[61906168] ; National Natural Science Foundation of China (NSFC)[U1709207] ; National Key R&D Program of China[2018YFB1305200] ; Zhejiang Provincial Natural Science Foundation of China[LY18F030020] ; Quzhou Science and Technology Projects[2019K17] ; Quzhou Science and Technology Projects[2020K19]
WOS关键词	SYSTEM
WOS研究方向	Engineering ; Robotics
语种	英语
出版者	EMERALD GROUP PUBLISHING LTD
WOS记录号	WOS:000661924500001
资助机构	National Natural Science Foundation of China (NSFC) ; National Key R&D Program of China ; Zhejiang Provincial Natural Science Foundation of China ; Quzhou Science and Technology Projects
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/123908]
专题	中国科学院合肥物质科学研究院
通讯作者	Chan, Sixian
作者单位	1.Quzhou Univ, Coll Elect & Informat Engn, Quzhou, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Intelligent Machines, Hefei, Peoples R China 3.Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Xiaolong,Wang, Pinghao,Chan, Sixian,et al. Densely connected Siamese network visual tracking[J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION,2021.
APA	Zhou, Xiaolong,Wang, Pinghao,Chan, Sixian,Fang, Kai,&Fang, Jianwen.(2021).Densely connected Siamese network visual tracking.INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION.
MLA	Zhou, Xiaolong,et al."Densely connected Siamese network visual tracking".INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION (2021).