Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes

doi:10.1109/TIP.2021.3106811

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes
	Han, Jiali 1,2,3; Zhu, Lingjie 4,5; Gao, Xiang 6; Hu, Zhanyi 1,2,3; Zhou, Liyang 7; Liu, Hongmin 8; Shen, Shuhan 1,2,3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2021
卷号	30 页码:7458-7471
关键词	Solid modeling Three-dimensional displays Buildings Semantics Image segmentation Computational modeling Shape Urban reconstruction building modeling Markov random field segment based modeling
ISSN号	1057-7149
DOI	10.1109/TIP.2021.3106811
通讯作者	Liu, Hongmin(hmliu_82@163.com) ; Shen, Shuhan(shshen@nlpr.ia.ac.cn)
英文摘要	Urban scene modeling is a challenging task for the photogrammetry and computer vision community due to its large scale, structural complexity, and topological delicacy. This paper presents an efficient multistep modeling framework for large-scale urban scenes from aerial images. It takes aerial images and a textured 3D mesh model generated by an image-based modeling system as the input and outputs compact polygon models with semantics at different levels of detail (LODs). Based on the key observation that urban buildings usually have piecewise planar rooftops and vertical walls, we propose a segment-based modeling method, which consists of three major stages: scene segmentation, roof contour extraction, and building modeling. By combining the deep neural network predictions with geometric constraints of the 3D mesh, the scene is first segmented into three classes. Then, for each building mesh, the 2D line segments are detected and used to slice the ground into polygon cells, followed by assigning each cell a roof plane via a MRF optimization. Finally, the LOD model is obtained by extruding cells to their corresponding planes. Compared with direct modeling in 3D space, we transform the mesh into a uniform 2D image grid representation and most of the modeling work is performed in 2D space, which has the advantages of low computational complexity and high robustness. In addition, our method doesn't require any global prior, such as the Manhattan or Atlanta world assumption, making it flexible to model scenes with different characteristics and complexity. Experiments on both single buildings and large-scale urban scenes demonstrate that by combining 2D photometric with 3D geometric information, the proposed algorithm is robust and efficient in urban scene LOD vectorized modeling compared with the state-of-the-art approaches.
资助项目	National Natural Science Foundation of China[61991423] ; National Natural Science Foundation of China[61873265] ; National Natural Science Foundation of China[61632003]
WOS关键词	ENERGY MINIMIZATION ; POINT ; RECONSTRUCTION ; SEGMENTATION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000692208400004
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45932]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者	Liu, Hongmin; Shen, Shuhan
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.CASIA SenseTime Res Grp, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 5.Alibaba AI Labs, Hangzhou 311100, Peoples R China 6.Ocean Univ China, Coll Engn, Qingdao 266100, Peoples R China 7.SenseTime Grp Ltd, Beijing 100080, Peoples R China 8.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Han, Jiali,Zhu, Lingjie,Gao, Xiang,et al. Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:7458-7471.
APA	Han, Jiali.,Zhu, Lingjie.,Gao, Xiang.,Hu, Zhanyi.,Zhou, Liyang.,...&Shen, Shuhan.(2021).Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,7458-7471.
MLA	Han, Jiali,et al."Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):7458-7471.