Adaptive multi-branch correlation filters for robust visual tracking

doi:10.1007/s00521-020-05126-9

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 远程智能医疗

	Adaptive multi-branch correlation filters for robust visual tracking
	Li, Xiaojing 1; Huang, Lei 1,3; Wei, Zhiqiang 1,3; Nie, Jie 1; Chen, Zhineng 2
刊名	NEURAL COMPUTING & APPLICATIONS
	2020-08-12
页码	16
关键词	Visual tracking Correlation filter Multi-branch Appearance changes Background suppression
ISSN号	0941-0643
DOI	10.1007/s00521-020-05126-9
通讯作者	Wei, Zhiqiang(weizhiqiang@ouc.edu.cn)
英文摘要	In recent years, deep convolutional features have been applied to discriminative correlation filters-based methods, which have achieved impressive performance in tracking. Most of them utilize hierarchical features from a certain layer. However, this is not always sufficient to learn target appearance changes and to suppress the background interference in complicated interfering factors (e.g., deformation, fast motion, low resolution, and rotations). In this paper, we propose an adaptive multi-branch correlation filter tracking method, by constructing multi-branch models and using an adaptive selection strategy to improve the accuracy and robustness of visual tracking. Specially, the multi-branch models are introduced to tolerate temporal changes of the object, which can serve different circumstances. In addition, the adaptive selection strategy incorporates both foreground and background information to learn background suppression. To further improve the tracking performance, we propose a measurement method to handle tracking failures from unreliable samples. Extensive experiments on OTB-2013, OTB-2015, and VOT-2016 datasets show that the proposed tracker has comparable performance compared to state-of-the-art tracking methods. Especially, on the OTB-2015, our method significantly improves the baseline with a gain of 5.5% in overlap precision.
资助项目	National Natural Science Foundation of China[61872326] ; National Natural Science Foundation of China[61672475] ; National Natural Science Foundation of China[61772526] ; Shandong Provincial Natural Science Foundation[ZR2019MF044]
WOS关键词	OBJECT TRACKING
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000559302200001
资助机构	National Natural Science Foundation of China ; Shandong Provincial Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40431]
专题	数字内容技术与服务研究中心_远程智能医疗
通讯作者	Wei, Zhiqiang
作者单位	1.Ocean Univ China, Coll Informat Sci & Engn, Qingdao 266000, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Qingdao Natl Lab Marine Sci & Technol, Qingdao 266000, Peoples R China
推荐引用方式 GB/T 7714	Li, Xiaojing,Huang, Lei,Wei, Zhiqiang,et al. Adaptive multi-branch correlation filters for robust visual tracking[J]. NEURAL COMPUTING & APPLICATIONS,2020:16.
APA	Li, Xiaojing,Huang, Lei,Wei, Zhiqiang,Nie, Jie,&Chen, Zhineng.(2020).Adaptive multi-branch correlation filters for robust visual tracking.NEURAL COMPUTING & APPLICATIONS,16.
MLA	Li, Xiaojing,et al."Adaptive multi-branch correlation filters for robust visual tracking".NEURAL COMPUTING & APPLICATIONS (2020):16.