An Approach to Overcome Occlusions in Visual Tracking: By Occlusion Estimating Agency and Self-Adapting Learning Rate for Filter's Training

doi:10.1109/LSP.2018.2856102

CIOMP OpenIR

	An Approach to Overcome Occlusions in Visual Tracking: By Occlusion Estimating Agency and Self-Adapting Learning Rate for Filter's Training
	Jiang, Kaiwen 1,2; Qian, Feng 1; Song, Ce 1; Zhang, Bao 1
	2018-12-01
发表期刊	IEEE SIGNAL PROCESSING LETTERS
ISSN	1070-9908
卷号	25 期号:12 页码:1890-1894
通讯作者	Zhang, Bao(zhangb@ciomp.ac.cn)
摘要	Visual tracking methods have been successful in recent years. Correlation filter (CF) based methods significantly advanced state-of-the-art tracking. The advancement in CF tracking performance is predominantly attributed to powerful features and sophisticated online learning formulations. However, there would be trouble if the tracker indiscriminately learned samples. Particularly, when the target is severely occluded or out-of-view, the tracker will continuously learn the wrong information, resulting target loss in the following frames. In this study, aiming to avoid incorrect training when occlusions occur, we propose a regional color histogram-based occlusion estimating agency (RCHBOEA), which estimates the occlusion level and then instructs, based on the result, the tracker to work in one of two modes: normal or lost. In the normal mode, an occlusion level-based self-adopting learning rate is used for tracker training. In the lost mode, the tracker pauses its training and conducts a search and recapture strategy on a wider searching area. Our method can easily complement CF-based trackers. In our experiments, we employed four CF-based trackers as a baseline: discriminative CFs (DCF), kernelized CFs (KCF), background-aware CFs (BACF), and efficient convolution operators for tracking: hand-crafted feature version (ECO_HC). We performed extensive experiments on the standard benchmarks: VIVID, OTB50, and OTB100. The results demonstrated that combined with RCHBOEA, the trackers achieved a remarkable improvement.
关键词	Overcome occlusion regional color histogram (RCH) self-adopting learning rate visual tracking
DOI	10.1109/LSP.2018.2856102
关键词[WOS]	OBJECT TRACKING ; BENCHMARK
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61705225] ; National Natural Science Foundation of China[61705225] ; National Natural Science Foundation of China[61705225] ; National Natural Science Foundation of China[61705225]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000449973100008
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/60289
专题	中国科学院长春光学精密机械与物理研究所
通讯作者	Zhang, Bao
作者单位	1.Chinese Acad Sci, Changchun Inst Opt Fine Mech & Phys, Changchun 130033, Jilin, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Kaiwen,Qian, Feng,Song, Ce,et al. An Approach to Overcome Occlusions in Visual Tracking: By Occlusion Estimating Agency and Self-Adapting Learning Rate for Filter's Training[J]. IEEE SIGNAL PROCESSING LETTERS,2018,25(12):1890-1894.
APA	Jiang, Kaiwen,Qian, Feng,Song, Ce,&Zhang, Bao.(2018).An Approach to Overcome Occlusions in Visual Tracking: By Occlusion Estimating Agency and Self-Adapting Learning Rate for Filter's Training.IEEE SIGNAL PROCESSING LETTERS,25(12),1890-1894.
MLA	Jiang, Kaiwen,et al."An Approach to Overcome Occlusions in Visual Tracking: By Occlusion Estimating Agency and Self-Adapting Learning Rate for Filter's Training".IEEE SIGNAL PROCESSING LETTERS 25.12(2018):1890-1894.