Dynamic Orthogonal Projection Constrained Discriminative Tracking

doi:10.1109/LSP.2022.3150984

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Dynamic Orthogonal Projection Constrained Discriminative Tracking
	Yu, Bin 1,3; Tang, Ming 1,3; Zhu, Guibo 1,3; Wang, Jinqiao 1,2,3; Lu, Hanqing 1,3
刊名	IEEE SIGNAL PROCESSING LETTERS
	2022
卷号	29 页码:652-656
关键词	Biological system modeling Training Feature extraction Dimensionality reduction Optimization Adaptation models Visualization Visual tracking dimensionality reduction discriminative model
ISSN号	1070-9908
DOI	10.1109/LSP.2022.3150984
通讯作者	Yu, Bin(bin.yu@nlpr.ia.ac.cn)
英文摘要	Due to the end-to-end feature learning with convolutional neural networks (CNNs), modern discriminative trackers improve the state of the art significantly. To achieve a strong discrimination, the learned features are usually high-dimensional, resulting in a massive number of parameters contained in the discriminative model and the increase of risk of over-fitting in the online tracking. In this letter, we try to alleviate the risk of over-fitting by means of the adaptive dimensionality reduction (DR) through CNNs. Specifically, an orthogonality constrained ridge regression model is proposed to reduce the dimensionality of features, and a dynamic sub-network (DOPNet) is designed to learn to perform DR. After trained with an orthogonality loss and a regression one, DOPNet generates a set of orthogonal bases (i. e., weights in FC layers) dynamically to reduce the feature dimensionality for a discriminative model in the online tracking. Based on the novel discriminative model and DOPNet, an effective and efficient tracker, DOPTracker, is developed. DOPTracker achieves the state-of-the-art results on four benchmarks, OTB-2015, VOT-2018, NfS, and GOT-10 k while running at 30 FPS.
资助项目	Key-Areas Research and Development Program of Guangdong Province[2020B010165001] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61976210] ; National Natural Science Foundation of China[62076235] ; National Natural Science Foundation of China[62002356] ; Open Research Projects of Zhejiang Lab[2021KH0AB07]
WOS关键词	OBJECT TRACKING
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000764786100006
资助机构	Key-Areas Research and Development Program of Guangdong Province ; National Natural Science Foundation of China ; Open Research Projects of Zhejiang Lab
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48057]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Yu, Bin
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100049, Peoples R China 2.ObjectEye Inc, Beijing 100049, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Yu, Bin,Tang, Ming,Zhu, Guibo,et al. Dynamic Orthogonal Projection Constrained Discriminative Tracking[J]. IEEE SIGNAL PROCESSING LETTERS,2022,29:652-656.
APA	Yu, Bin,Tang, Ming,Zhu, Guibo,Wang, Jinqiao,&Lu, Hanqing.(2022).Dynamic Orthogonal Projection Constrained Discriminative Tracking.IEEE SIGNAL PROCESSING LETTERS,29,652-656.
MLA	Yu, Bin,et al."Dynamic Orthogonal Projection Constrained Discriminative Tracking".IEEE SIGNAL PROCESSING LETTERS 29(2022):652-656.