Real-time depth camera tracking with geometrically stable weight algorithm

doi:10.1117/1.OE.56.3.033104

IMR OpenIR

	Real-time depth camera tracking with geometrically stable weight algorithm
	Fu, Xingyin 1,3,4,5; Zhu, Feng 1,4,5; Qi, Feng 2,4,5; Wang, Mingming 1,3,4,5
通讯作者	Zhu, Feng(fzhu@sia.cn)
	2017-03-01
发表期刊	OPTICAL ENGINEERING
ISSN	0091-3286
卷号	56 期号:3 页码:10
摘要	We present an approach for real-time camera tracking with depth stream. Existing methods are prone to drift in sceneries without sufficient geometric information. First, we propose a new weight method for an iterative closest point algorithm commonly used in real-time dense mapping and tracking systems. By detecting uncertainty in pose and increasing weight of points that constrain unstable transformations, our system achieves accurate and robust trajectory estimation results. Our pipeline can be fully parallelized with GPU and incorporated into the current real-time depth camera tracking system seamlessly. Second, we compare the state-of-theart weight algorithms and propose a weight degradation algorithm according to the measurement characteristics of a consumer depth camera. Third, we use Nvidia Kepler Shuffle instructions during warp and block reduction to improve the efficiency of our system. Results on the public TUM RGB-D database benchmark demonstrate that our camera tracking system achieves state-of-the-art results both in accuracy and efficiency. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
关键词	camera tracking weight algorithm shuffle depth camera reduction
DOI	10.1117/1.OE.56.3.033104
收录类别	SCI
语种	英语
WOS研究方向	Optics
WOS类目	Optics
WOS记录号	WOS:000397207200028
出版者	SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/126984
专题	中国科学院金属研究所
通讯作者	Zhu, Feng
作者单位	1.Chinese Acad Sci, Shenyang Inst Automat, Shenyang, Peoples R China 2.Chinese Acad Sci, Shenyang Inst Automat, THz Imaging Grp, Shenyang, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Chinese Acad Sci, Key Lab Optoelect Informat Proc, Shenyang, Peoples R China 5.Key Lab Image Understanding & Comp Vis, Shenyang, Liaoning Provin, Peoples R China
推荐引用方式 GB/T 7714	Fu, Xingyin,Zhu, Feng,Qi, Feng,et al. Real-time depth camera tracking with geometrically stable weight algorithm[J]. OPTICAL ENGINEERING,2017,56(3):10.
APA	Fu, Xingyin,Zhu, Feng,Qi, Feng,&Wang, Mingming.(2017).Real-time depth camera tracking with geometrically stable weight algorithm.OPTICAL ENGINEERING,56(3),10.
MLA	Fu, Xingyin,et al."Real-time depth camera tracking with geometrically stable weight algorithm".OPTICAL ENGINEERING 56.3(2017):10.