SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING

doi:10.2316/J.2019.206-0108

CASIA OpenIR > 中国科学院工业视觉智能装备工程实验室 > 精密感知与控制

	SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING
	Zhu, Zheng1,2 ; Zou, Wei3 ; Zhang, Feng1
发表期刊	INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION
ISSN	0826-8185
	2019
卷号	34 期号:5 页码:477-490
通讯作者	Zou, Wei(wei.zou@ia.ac.cn)
摘要	Depth provided by binocular vision systems is extra information for stereo visual tracking, which has less distance limitation and can work well in outdoor environment compared to red-green-blue-depth (RGB-D) cameras. By fusing depth with edge and colour features, a stereo tracking algorithm named scalable and occlusion-aware multi-cues correlation filter tracker (SOMCFT) is proposed in this paper, which consists of multi-cue correlation filter tracker (MCFT), scale handling and occlusion-aware strategy. In MCFT, the confidence maps drawn from all the features are filtered by each other, and then an optimal confidence map is determined by minimizing the sum of Kullback-Leibler divergence. In scale handling, the target is segmented by 2D grey-depth histograms, and then a quantized set is used to guide the scale variants of bounding boxes. In occlusion-aware strategy, the start and end of occlusion is detected by combining the changes of depth and the results of MCFT; meanwhile, a reasonable candidate region is determined during occlusion. Both qualitative and quantitative evaluations on the stereo tracking dataset demonstrate that the proposed SOMCFT algorithm performs favourably when compared with other methods. Our algorithm outperforms the second-ranked method by 5.4% in success score and 14.59% in precision score.
关键词	Depth information stereo tracking visual tracking
DOI	10.2316/J.2019.206-0108
关键词[WOS]	OBJECT TRACKING
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61773374] ; National Key Research and Development Program of China[2018YFB1306303] ; National Key Research and Development Program of China[2018YFB1306303] ; National Natural Science Foundation of China[61773374]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Automation & Control Systems ; Robotics
WOS类目	Automation & Control Systems ; Robotics
WOS记录号	WOS:000483927100003
出版者	ACTA PRESS
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/27332
专题	中国科学院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Zou, Wei
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	精密感知与控制研究中心
推荐引用方式 GB/T 7714	Zhu, Zheng,Zou, Wei,Zhang, Feng. SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING[J]. INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION,2019,34(5):477-490.
APA	Zhu, Zheng,Zou, Wei,&Zhang, Feng.(2019).SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING.INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION,34(5),477-490.
MLA	Zhu, Zheng,et al."SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING".INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION 34.5(2019):477-490.