A Novel Framework for 2.5-D Building Contouring From Large-Scale Residential Scenes

doi:10.1109/TGRS.2019.2901539

	A Novel Framework for 2.5-D Building Contouring From Large-Scale Residential Scenes
	Du, Jianli 1,2; Chen, Dong 3,4; Wang, Ruisheng 4; Peethambaran, Jiju 5; Mathiopoulos, P. Takis 6; Xie, Lei 4; Yun, Ting 7
刊名	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
	2019-06-01
卷号	57 期号:6 页码:4121-4145
关键词	airborne laser scanning (ALS) building abstraction building contour decomposition building contours building regularization large-scale airborne point clouds LoD1 building models
ISSN号	0196-2892
DOI	10.1109/TGRS.2019.2901539
通讯作者	Chen, Dong(chendong@njfu.edu.cn) ; Wang, Ruisheng(ruiswang@ucalgary.ca)
英文摘要	This paper introduces a novel methodology for residential building contouring from large-scale airborne point clouds. Unlike other methods that handle linearization and regularization of the linear primitives separately by imposing rigid constraints, we propose an optimization-based linearization and global regularization to form accurate, topologically error-free, and lightweight polygons. To this end, we enhance the classic density-based spatial clustering of applications with noise algorithm to segment individual building entities at the instance level. The initial contours of each individual building are then delineated and further decomposed by a novel topologically aware propagation process and a global optimization technique. The decomposed linear primitives are fed into the global regularization step, from which the regular shapes are learned and enforced hierarchically by imposing constraints, such as parallelism, homogeneity, orthogonality, and collinearity. Based on the concept of hybrid representation, the regularized and unaltered linear primitives are jointly connected in an esthetic way. Various experiments using representative buildings and large-scale residential scenes from the Dutch AHN3 data set have shown that the proposed methodology generates meaningful building contouring representation in terms of accuracy, compactness, topology, and levels of detail abstraction while being robust and scalable.
WOS关键词	AUTOMATIC CONSTRUCTION ; RECONSTRUCTION ; MODEL ; REGULARIZATION ; ALGORITHMS ; EXTRACTION ; FOOTPRINTS ; IMAGES
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:000470019800079
内容类型	期刊论文
源URL	[http://libir.pmo.ac.cn/handle/332002/26997]
专题	中国科学院紫金山天文台
通讯作者	Chen, Dong; Wang, Ruisheng
作者单位	1.Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Hubei, Peoples R China 2.Chinese Acad Sci, Purple Mt Observ, Nanjing 210034, Jiangsu, Peoples R China 3.Nanjing Forestry Univ, Coll Civil Engn, Nanjing 210037, Jiangsu, Peoples R China 4.Univ Calgary, Dept Geomat Engn, Calgary, AB T2N 1N4, Canada 5.St Marys Univ, Dept Math & Comp Sci, Halifax, NS B3P 2M6, Canada 6.Univ Athens, Dept Informat & Telecommun, Athens 15784, Greece 7.Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Du, Jianli,Chen, Dong,Wang, Ruisheng,et al. A Novel Framework for 2.5-D Building Contouring From Large-Scale Residential Scenes[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2019,57(6):4121-4145.
APA	Du, Jianli.,Chen, Dong.,Wang, Ruisheng.,Peethambaran, Jiju.,Mathiopoulos, P. Takis.,...&Yun, Ting.(2019).A Novel Framework for 2.5-D Building Contouring From Large-Scale Residential Scenes.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,57(6),4121-4145.
MLA	Du, Jianli,et al."A Novel Framework for 2.5-D Building Contouring From Large-Scale Residential Scenes".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 57.6(2019):4121-4145.