Decision Controller for Object Tracking With Deep Reinforcement Learning

doi:10.1109/ACCESS.2019.2900476

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 > 模式分析与学习团队

	Decision Controller for Object Tracking With Deep Reinforcement Learning
	Zhong, Zhao1,2 ; Yang, Zichen 3; Feng, Weitao 3; Wu, Wei 3; Hu, Yangyang 3; Liu, Cheng-Lin1,4
刊名	IEEE ACCESS
	2019
卷号	7 页码:28069-28079
关键词	Computer vision deep learning object tracking reinforcement learning
ISSN号	2169-3536
DOI	10.1109/ACCESS.2019.2900476
通讯作者	Liu, Cheng-Lin(liucl@nlpr.ia.ac.cn)
英文摘要	There are many decisions which are usually made heuristically both in single object tracking (SOT) and multiple object tracking (MOT). Existing methods focus on tackling decision-making problems on special tasks in tracking without a unified framework. In this paper, we propose a decision controller (DC) which is generally applicable to both SOT and MOT tasks. The controller learns an optimal decision-making policy with a deep reinforcement learning algorithm that maximizes long term tracking performance without supervision. To prove the generalization ability of DC, we apply it to the challenging ensemble problem in SOT and tracker-detector switching problem in MOT. In the tracker ensemble experiment, our ensemble-based tracker can achieve leading performance in VOT2016 challenge and the light version can also get a state-of-the-art result at 50 FPS. In the MOT experiment, we utilize the tracker-detector switching controller to enable real-time online tracking with competitive performance and 10x speed up.
资助项目	National Natural Science Foundation of China (NSFC)[61721004] ; National Natural Science Foundation of China (NSFC)[61633021]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000461870200001
资助机构	National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/23561]
专题	自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者	Liu, Cheng-Lin
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Sensetime Res Inst, Beijing 100084, Peoples R China 4.Univ Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhong, Zhao,Yang, Zichen,Feng, Weitao,et al. Decision Controller for Object Tracking With Deep Reinforcement Learning[J]. IEEE ACCESS,2019,7:28069-28079.
APA	Zhong, Zhao,Yang, Zichen,Feng, Weitao,Wu, Wei,Hu, Yangyang,&Liu, Cheng-Lin.(2019).Decision Controller for Object Tracking With Deep Reinforcement Learning.IEEE ACCESS,7,28069-28079.
MLA	Zhong, Zhao,et al."Decision Controller for Object Tracking With Deep Reinforcement Learning".IEEE ACCESS 7(2019):28069-28079.