卢露媛,颜青松,曲英杰,李鹏,邓非

• 1:武汉大学测绘学院
• 2:自然资源部城市国土资源监测与仿真重点实验室

摘要(Abstract)：

针对城市建筑通常是由平面屋顶和垂直墙体连接而成的分段平面对象,该文提出了一个大规模城市建筑物的有效建模框架,在该框架中有两个主要步骤:分类和建模。首先采用基于征集的随机森林分类方法将大范围场景进行分割,然后采用假设和选择的建模策略对多种建筑物进行三维建模。该算法以多视点立体视觉系统生成的曲面网格为输入,输出具有不同细节层次的简化三维模型。实验表明,该方法能对多种外观的建筑物进行不同细节层次的建模,模型外观简洁规整,并能在一定程度上弥补原始数据中的噪声和遮挡问题。

关键词(KeyWords)： 网格分割;随机森林;建筑三维建模;多边形表面重建

Abstract:

Keywords:

基金项目(Foundation): 自然资源部城市国土资源监测与仿真重点实验室开放基金资助课题项目(KF-2018-03-025)

作者(Author): 卢露媛,颜青松,曲英杰,李鹏,邓非

DOI: 10.16251/j.cnki.1009-2307.2021.08.016

参考文献(References)：

• [1] MUSIALSKI P,WONKA P,ALIAGA D G,et al.A survey of urban reconstruction[J].Computer Graphics Forum,2013,32(6):146-177.
• [2] ZHOU Q Y,NEUMANN U.2.5D dual contouring:a robust approach to creating building models from aerial LiDAR point clouds[C]//European Conference on Computer Vision(ECCV).Berlin:Springer,2010:115-128.
• [3] FURUKAWA Y,PONCE J.Accurate camera calibration from multi-view stereo and bundle adjustment[J].International Journal of Computer Vision,2009,84(3):257-268.
• [4] Pix4D[DB/OL].[2020-07-21].https://pix4d.com/.
• [5] Acute3D[DB/OL].[2020-07-21].https://www.acute3d.com/.
• [6] HOFER M,MAURER M,BISCHOF H.Efficient 3D scene abstraction using line segments[J].Computer Vision and Image Understanding,2017,157:167-178.
• [7] VERDIE Y,LAFARGE F,ALLIEZ P.LOD generation for urban scenes[J].ACM Transactions on Graphics,2015,34(3):30.
• [8] ROUHANI M,LAFARGE F,ALLIEZ P.Semantic segmentation of 3D textured meshes for urban scene analysis[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,123:124-139.
• [9] LIU Jingbo,WANG Jinglu,FANG Tian,et al.Higher-order CRF structural segmentation of 3D reconstructed surfaces[C]//2015 IEEE International Conference on Computer Vision(ICCV).Santiago,Chile:IEEE,2015:2093-2101.
• [10] LI M L,WONKA P,NAN L L.Manhattan-world urban reconstruction from point clouds[C]//Computer Vision:ECCV 2016.Cham:Springer,2016:54-69.
• [11] NAN L L,WONKA P.PolyFit:polygonal surface reconstruction from point clouds[C]//2017 IEEE International Conference on Computer Vision(ICCV).Venice,Italy:IEEE,2017:2372-2380.
• [12] LI M L,NAN L L,SMITH N,et al.Reconstructing building mass models from UAV images[J].Computers & Graphics,2016,54:84-93.
• [13] KELLY T,FEMIANI J,WONKA P,et al.BigSUR:large-scale structured urban reconstruction[J].ACM Transactions on Graphics,2017,36(6):204.
• [14] KELLY T,WONKA P.Interactive architectural modeling with procedural extrusions[J].ACM Transactions on Graphics,2011,30(2):1-15.
• [15] ZHU Lingjie,SHEN Shuhan,HU Lihua,et al.Variational building modeling from urban MVS meshes[C]//2017 International Conference on 3D Vision(3DV).Qingdao,China:IEEE,2017:318-326.
• [16] COHEN-STEINER D,ALLIEZ P,DESBRUN M.Variational shape approximation[C]//SIGGRAPH’04.New York:ACM Press,2004:905-914.
• [17] Computational geometry algorithms library[DB/OL].[2020-07-21].https://www.cgal.org/.
• [18] WALK S.ETH Zurich random forest template library[DB/OL].[2020-07-21].https://prs.igp.ethz.ch/research/Source_code_and_datasets.html.
• [19] LI S Z.Markov random field modeling in image analysis[M].3rd ed.London:Springer-Verlag,2009.
• [20] BOYKOV Y,KOLMOGOROV V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137.
• [21] SCHNABEL R,WAHL R,KLEIN R.Efficient RANSAC for point-cloud shape detection[J].Computer Graphics Forum,2007,26(2):214-226.
• [22] PAULY M,MITRA N J,GIESEN J,et al.Example-based 3D scan completion[C]//Symposium on Geometry Processing.[S.l.]:[s.n.],2005:23-32.
• [23] DA T K F.2D alpha shapes[DB/OL].[2020-07-21].https://www.cgal.org/.
• [24] GUROBI.Gurobi optimization[DB/OL].[2020-07-21].http://www.gurobi.com/.