Robust visual tracking via scale-and-state-awareness

doi:10.1016/j.neucom.2018.10.035

	Robust visual tracking via scale-and-state-awareness
	Qi, Yuankai 1; Qin, Lei 2; Zhang, Shengping 3; Huang, Qingming 1,4; Yao, Hongxun 1
	2019-02-15
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	329 页码:75-85
摘要	Convolutional neural networks (CNNs) have been applied to visual tracking with demonstrated success in recent years. However, the performance of CNN-based trackers can be further improved, because the predicted upright bounding box cannot tightly enclose the target due to factors such as deformations and rotations. Besides, many existing CNN-based trackers neglect to distinguish the occluded state of the target from non-occluded states, which causes the samples collected during occlusions wrongly update the tracker to focus on other objects. To address these problems, we propose to adaptively utilize the level set segmentation and bounding box regression techniques to obtain a tight enclosing box, and design a CNN to recognize whether the target is occluded. Extensive experimental results on a large benchmark dataset demonstrate the effectiveness of the proposed method compared to several state-of-the-art tracking algorithms. (C) 2018 Elsevier B.V. All rights reserved.
关键词	Visual tracking Convolutional neural network Bounding box refinement Occlusion awareness
DOI	10.1016/j.neucom.2018.10.035
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[61332016] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61572465] ; National Natural Science Foundation of China[61390510] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61872112] ; National Natural Science Foundation of China[61772158] ; National Natural Science Foundation of China[61472103] ; National Natural Science Foundation of China[U1711265] ; Key Research Program of Frontier Sciences[CAS: QYZDJ-SSW-SYS013]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000453924300008
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：28[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/2XEOYT63/3517
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Huang, Qingming
作者单位	1.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Heilongjiang, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100089, Peoples R China 3.Harbin Inst Technol, Sch Comp Sci & Technol, Weihai 264209, Peoples R China 4.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Qi, Yuankai,Qin, Lei,Zhang, Shengping,et al. Robust visual tracking via scale-and-state-awareness[J]. NEUROCOMPUTING,2019,329:75-85.
APA	Qi, Yuankai,Qin, Lei,Zhang, Shengping,Huang, Qingming,&Yao, Hongxun.(2019).Robust visual tracking via scale-and-state-awareness.NEUROCOMPUTING,329,75-85.
MLA	Qi, Yuankai,et al."Robust visual tracking via scale-and-state-awareness".NEUROCOMPUTING 329(2019):75-85.