3D Tracker-Level Fusion for Robust RGB-D Tracking

doi:10.1587/transinf.2016EDP7498

	3D Tracker-Level Fusion for Robust RGB-D Tracking
	An, Ning1,2 ; Zhao, Xiao-Guang1,2 ; Hou, Zeng-Guang1,2
发表期刊	IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
	2017-08-01
卷号	E100D 期号:8 页码:1870-1881
文章类型	Article
摘要	In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.
关键词	Rgb-d Tracking Data Fusion 3d Object Tracking Online Video Processing
WOS标题词	Science & Technology ; Technology
DOI	10.1587/transinf.2016EDP7498
关键词[WOS]	OBJECT TRACKING ; VISUAL TRACKING ; BENCHMARK ; MODEL
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61271432 ; 61673378 ; 61421004)
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000406868400036
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/19942
专题	复杂系统认知与决策实验室_先进机器人
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	An, Ning,Zhao, Xiao-Guang,Hou, Zeng-Guang. 3D Tracker-Level Fusion for Robust RGB-D Tracking[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,2017,E100D(8):1870-1881.
APA	An, Ning,Zhao, Xiao-Guang,&Hou, Zeng-Guang.(2017).3D Tracker-Level Fusion for Robust RGB-D Tracking.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,E100D(8),1870-1881.
MLA	An, Ning,et al."3D Tracker-Level Fusion for Robust RGB-D Tracking".IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E100D.8(2017):1870-1881.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2{3D Tracker-Level F（5024KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载