3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration

doi:10.1109/LGRS.2019.2910546

	3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration
	Zhang, Zhenxin 3,4; Sun, Lan 3,4; Zhong, Ruofei 3,4; Chen, Dong 5; Xu, Zhihua 6,7; Wang, Cheng 1; Qin, Cheng-Zhi 8; Sun, Haili 3,4; Li, Roujing 2
刊名	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
	2019-12-01
卷号	16 期号:12 页码:1904-1908
关键词	3-D deep features convolutional neural networks (CNNs) mobile laser scanning (MLS) point clouds registration
ISSN号	1545-598X
DOI	10.1109/LGRS.2019.2910546
通讯作者	Zhong, Ruofei(zrfsss@163.com)
英文摘要	Due to errors in sensors and positioning, there exist mismatches between different phases of mobile laser scanning point clouds, which impede the application of point cloud, such as changing detection and deformation monitoring. To rectify such mismatches, we designed a 3-D deep feature construction method for point cloud registration. The proposed method combines two 3-D convolutional neural networks into a uniform deep learning model to extract 3-D deep features. First, the corresponding points and noncorresponding points are set to train the deep learning model to minimize the distance between corresponding points' features and maximize the distance between features of noncorresponding points. Second, in the test phase, the 3-D deep feature for each keypoint was extracted by the trained deep learning model. This could be used to determine the corresponding points by the k-dimensional tree and random sample consensus (RANSAC) algorithm. Finally, a transformation matrix was calculated based on the corresponding points and was then applied to point cloud registration. The experimental results illustrated that the proposed method of using 3-D deep features is more efficient at a corresponding point search than representatives of three existing methods. It also improved registration accuracy.
资助项目	Open Research Fund of Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences[2017LDE001] ; National Natural Science Foundation of China[41701533] ; National Natural Science Foundation of China[41701534] ; State Key Laboratory of Resources and Environmental Information System, Opening Research Fund of National Engineering Laboratory for Surface Transportation Weather Impacts Prevention[NELBP201701] ; Open Fund of State Key Laboratory of Remote Sensing Science[OFSLRSS201818] ; Opening Fund of Key Laboratory of Geohazard Prevention of Hilly Mountains, Ministry of Land and Resources (Fujian Key Laboratory of Geohazard Prevention)[FJKLGH2017K001]
WOS关键词	AUTOMATIC REGISTRATION ; ICP
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000501343000020
资助机构	Open Research Fund of Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences ; National Natural Science Foundation of China ; State Key Laboratory of Resources and Environmental Information System, Opening Research Fund of National Engineering Laboratory for Surface Transportation Weather Impacts Prevention ; Open Fund of State Key Laboratory of Remote Sensing Science ; Opening Fund of Key Laboratory of Geohazard Prevention of Hilly Mountains, Ministry of Land and Resources (Fujian Key Laboratory of Geohazard Prevention)
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/130172]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhong, Ruofei
作者单位	1.Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing 100094, Peoples R China 2.Beijing Normal Univ, Fac Geog Sci, Beijing 100875, Peoples R China 3.Broadvis Engn Consultants, Natl Engn Lab Surface Transportat Weather Impacts, Kunming 650200, Yunnan, Peoples R China 4.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Theory & Technol, Beijing 100048, Peoples R China 5.Nanjing Forestry Univ, Coll Civil Engn, Nanjing 210037, Jiangsu, Peoples R China 6.China Univ Min & Technol Beijing, Coll Geosci & Surveying Engn, Beijing 100083, Peoples R China 7.Minist Land & Resources, Fujian Key Lab Geohazard Prevent, Key Lab Geohazard Prevent Hilly Mt, Fuzhou 350002, Fujian, Peoples R China 8.Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Zhenxin,Sun, Lan,Zhong, Ruofei,et al. 3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2019,16(12):1904-1908.
APA	Zhang, Zhenxin.,Sun, Lan.,Zhong, Ruofei.,Chen, Dong.,Xu, Zhihua.,...&Li, Roujing.(2019).3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,16(12),1904-1908.
MLA	Zhang, Zhenxin,et al."3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 16.12(2019):1904-1908.