Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes

doi:10.1007/s00371-018-1492-z

	Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes
	Wang, Wei 1; Gao, Wei2,3
刊名	VISUAL COMPUTER
	2019-05-01
卷号	35 期号:5 页码:625-638
关键词	Plane fitting 3D reconstruction Piecewise planar assumption Markov Random Field
ISSN号	0178-2789
DOI	10.1007/s00371-018-1492-z
通讯作者	Wang, Wei(wangwei@zknu.cn)
英文摘要	In modeling large-scale urban scenes, extracting reliable dominant planes from initial 3D points plays an important role for inferring the complete scene structures. However, traditional local and global methods are frequently prone to missing many real planes and also appear powerless when massive 3D points are present. To solve these problems, the paper presents an efficient multi-plane extraction method based on scene structure priors. The proposed method first explores the potential relations between the planes by detecting 2D line segments in the projection map produced from initial 3D points (i.e., simplify 3D model to 2D model), including: (1) multi-line detection in regions by the guidance of scene structure priors; (2) multi-line detection between regions under the Markov Random Field framework incorporating scene structure priors. Then, according to the resulting plane relations, a rapid multi-plane generation is carried out instead of the time-consuming plane fitting over 3D points. Experimental results confirm that the proposed method can efficiently produce sufficient and reliable dominant planes from a vast number of noisy 3D points (only about 8s on 2000K 3D points) and can be applied for modeling large-scale urban scenes.
资助项目	National Key R&D Program of China[2016YFB0502002] ; National Laboratory of Pattern Recognition[201700004] ; National Natural Science Foundation of China[61472419] ; Natural Science Foundation of Henan Province[162300410347] ; College Key Research Project of Henan Province[17A520018] ; College Key Research Project of Henan Province[17A520019] ; Zhoukou Normal University[zknuc2015103] ; Zhoukou Normal University[zknub2201705]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000468524900002
资助机构	National Key R&D Program of China ; National Laboratory of Pattern Recognition ; National Natural Science Foundation of China ; Natural Science Foundation of Henan Province ; College Key Research Project of Henan Province ; Zhoukou Normal University
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24175]
专题	中国科学院自动化研究所
通讯作者	Wang, Wei
作者单位	1.Zhoukou Normal Univ, Sch Network Engn, Zhoukou 466000, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Wei,Gao, Wei. Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes[J]. VISUAL COMPUTER,2019,35(5):625-638.
APA	Wang, Wei,&Gao, Wei.(2019).Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes.VISUAL COMPUTER,35(5),625-638.
MLA	Wang, Wei,et al."Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes".VISUAL COMPUTER 35.5(2019):625-638.