Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game

doi:10.1016/j.isprsjprs.2017.10.001

	Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game
	Zai, Dawei 1; Li, Jonathan 1,2; Guo, Yulan 3,4; Cheng, Ming 1; Huang, Pengdi 1; Cao, Xiaofei 1; Wang, Cheng 1
	2017-12-01
发表期刊	ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
ISSN	0924-2716
卷号	134 页码:15-29
摘要	It is challenging to automatically register TLS point clouds with noise, outliers and varying overlap. In this paper, we propose a new method for pairwise registration of TLS point clouds. We first generate covariance matrix descriptors with an adaptive neighborhood size from point clouds to find candidate correspondences, we then construct a non-cooperative game to isolate mutual compatible correspondences, which are considered as true positives. The method was tested on three models acquired by two different TLS systems. Experimental results demonstrate that our proposed adaptive covariance (ACOV) descriptor is invariant to rigid transformation and robust to noise and varying resolutions. The average registration errors achieved on three models are 0.46 cm, 0.32 cm and 1.73 cm, respectively. The computational times cost on these models are about 288 s, 184 s and 903 s, respectively. Besides, our registration framework using ACOV descriptors and a game theoretic method is superior to the state-of-the-art methods in terms of both registration error and computational time. The experiment on a large outdoor scene further demonstrates the feasibility and effectiveness of our proposed pairwise registration framework. (C) 2017 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
关键词	Terrestrial laser scanning (TLS) Registration Covariance matrix descriptor 3D representation Game theory
DOI	10.1016/j.isprsjprs.2017.10.001
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[41471379] ; National Natural Science Foundation of China[61471371] ; National Natural Science Foundation of China[61602499] ; Fujian Collaborative Innovation Center for Big Data Applications in Governments ; National Postdoctoral Program for Innovative Talents[BX201600172]
WOS研究方向	Physical Geography ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Geography, Physical ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000418220800002
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：60[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/2XEOYT63/5564
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Jonathan
作者单位	1.Xiamen Univ, Sch Informat Sci & Engn, Fujian Key Lab Sensing & Comp Smart City, Xiamen, Peoples R China 2.Univ Waterloo, Dept Geog & Environm Management, Waterloo, ON, Canada 3.Natl Univ Def Technol, Coll Elect Sci & Engn, Changsha, Hunan, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zai, Dawei,Li, Jonathan,Guo, Yulan,et al. Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game[J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,2017,134:15-29.
APA	Zai, Dawei.,Li, Jonathan.,Guo, Yulan.,Cheng, Ming.,Huang, Pengdi.,...&Wang, Cheng.(2017).Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game.ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,134,15-29.
MLA	Zai, Dawei,et al."Pairwise registration of TLS point clouds using covariance descriptors and a non-cooperative game".ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 134(2017):15-29.