Learning salient features to prevent model drift for correlation tracking

doi:10.1016/j.neucom.2019.12.006

	Learning salient features to prevent model drift for correlation tracking
	Zhang, Yu 1,2; Gao, Xingyu 1; Chen, Zhenyu 3,4; Zhong, Huicai 1; Li, Liang 5; Yan, Chenggang 6; Shen, Tao 7
	2020-12-22
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	418 页码:1-10
摘要	Correlation Filter (CF) based algorithms play an important role in the field of Visual Object Tracking (VOT) due to their high accuracy and low computational complexity. While existing CF tracking algorithms suf-fer performance degradation due to inaccurate object modeling. In this paper, we improve the object modeling accuracy in both CF training stage and target detection procedure to preventing the drift problem. Specifically, we propose a multi-model structure for CF trackers to capture the target appearance changes, where different appearance models are trained with specific samples to catch the salient features of the target and reduce the computational cost. Furthermore, a space filter for detection features is designed to suppress the boundary effect under Gaussian motion prior, which contributes to improving the accuracy of position estimation. We deploy our method to three hand-crafted features based CF trackers to perform real-time visual tracking on popular benchmarks. The experimental results demonstrate the efficacy of our proposed scheme and the efficiency of our trackers. In addition, we provide a comprehensive analysis of the proposed method to facilitate application. (c) 2019 Published by Elsevier B.V.
关键词	Salient features Drift prevention Correlation tracking
DOI	10.1016/j.neucom.2019.12.006
收录类别	SCI
语种	英语
资助项目	National Nature Science Foundation of China[61702491] ; National Nature Science Foundation of China[61771457] ; National Nature Science Foundation of China[61732007]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000589911100001
出版者	ELSEVIER
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16074
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Xingyu; Chen, Zhenyu
作者单位	1.Chinese Acad Sci, Inst Microelect, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Microelect, Beijing, Peoples R China 3.State Grid Corp China, Big Data Ctr, Beijing, Peoples R China 4.China Elect Power Res Inst, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 6.Hangzhou Dianzi Univ, Inst Informat & Control, Hangzhou, Peoples R China 7.Kunming Univ Sci & Technol, Sch Informat Engn & Automat, Kunming, Yunnan, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Yu,Gao, Xingyu,Chen, Zhenyu,et al. Learning salient features to prevent model drift for correlation tracking[J]. NEUROCOMPUTING,2020,418:1-10.
APA	Zhang, Yu.,Gao, Xingyu.,Chen, Zhenyu.,Zhong, Huicai.,Li, Liang.,...&Shen, Tao.(2020).Learning salient features to prevent model drift for correlation tracking.NEUROCOMPUTING,418,1-10.
MLA	Zhang, Yu,et al."Learning salient features to prevent model drift for correlation tracking".NEUROCOMPUTING 418(2020):1-10.