Implicit Surface Reconstruction of Urban Scenes Based on Oblique Images

doi:10.13474/j.cnki.11-2246.2017.0372

Abstract

Abstract: In the process of urban scenes reconstruction based on oblique images,due to the scenes occlusion and large view-point changes in oblique imagery acquisition,dense image matching is quite challenging in scenarios like building facades and other vertical objects,leading to a sparse or leaky point cloud and can be hard to reconstruct the urban scenes precisely.A new urban scenes implicit surface reconstruction method is proposed based on oblique images.Firstly,it builds an adaptive tetrahedral decomposition of space by computing 3D Delaunay triangulation of the dense point cloud.Secondly,a triangular mesh is generated using the graph cut algorithm on Delaunay tetrahedron to make a more accurate estimation of the normal information of the point cloud.Finally,combined with Screened Poisson surface reconstruction method,an implicit surface reconstruction is conducted for the urban scenes.Experiments and comparison with other three implicit reconstruction methods show the accuracy and applicability of the proposed method.

Key words: oblique images, implicit surface reconstruction, ray, graph cut, Screened Poisson surface reconstruction

CLC Number:

P237

ZUO Zhiqiang, HUANG Xianfeng, YANG Chong, ZHANG Fan, GAO Yunlong. Implicit Surface Reconstruction of Urban Scenes Based on Oblique Images[J]. 测绘通报, 2017, 0(12): 21-28.

References

[1] GAO J,CHEN X,YILMAZ O,et al.An Integrated Adaptive Repair Solution for Complex Aerospace Components through Geometry Reconstruction[J].The International Journal of Advanced Manufacturing Technology,2008,36(11-12):1170-1179.
[2] YANG M D,CHAO C F,HUANG K S,et al.Image-Based 3D Scene Reconstruction and Exploration in Augmented Reality[J].Automation in Construction,2013(33):48-60.
[3] WANG J,GU D,YU Z,et al.A Framework for 3D Model Reconstruction in Reverse Engineering[J].Computers & Industrial Engineering,2012,63(4):1189-1200.
[4] JAMES M,ROBSON S.Straightforward Reconstruction of 3D Surfaces and Topography with a Camera:Accuracy and Geoscience Application[J].Journal of Geophysical Research:Earth Surface,2012,117(F3).DOI:10.1029/2011JF002289.
[5] 史文中,曹辉,张剑清.基于高分辨率影像的城市三维建模[J].武汉大学学报(信息科学版),2004,29(9):783-787.
[6] 朱庆,徐冠宇,杜志强,等.倾斜摄影测量技术综述[J].北京:中国科技论文在线,2012.
[7] LIM S P,HARON H.Surface Reconstruction Techniques:A Review[J].Artificial Intelligence Review,2014,42(1):59-78.
[8] AMENTA N,BERN M,KAMVYSSELIS M.A New Voronoi-based Surface Reconstruction Algorithm[C]//Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM,1998:415-421.
[9] EDELSBRUNNER H.Shape Reconstruction with Delaunay Complex[J].Lecture Notes in Computer Science,1980,1380(1380):119-132.
[10] AMENTA N,BERN M,EPPSTEIN D.The Crust and the β-Skeleton:Combinatorial Curve Reconstruction[J].Graphical Models and Image Processing,1998,60(2):125-135.
[11] DECARLO D,DIMITRI.Blended Deformable Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(4):443-448.
[12] HE Y,QIN H.Surface Reconstruction with Triangular B-splines[C]//Geometric Modeling and Processing.Beijing:[s.n.],2004:279-287.
[13] MARR D,NISHIHARA H K.Representation and Recognition of the Spatial Organization of Three-dimensional Shapes[J].Proceedings of the Royal Society of London,1978,200(1140):269-294.
[14] LIANG J,PARK F,ZHAO H.Robust and Efficient Implicit Surface Reconstruction for Point Clouds Based on Convexified Image Segmentation[J].Journal of Scientific Computing,2013,54(2-3):577-602.
[15] OHTAKE Y,BELYAEV A,ALEXA M,et al.Multi-level Partition of Unity Implicits[J].ACM Siggraph,2003,22(3):463-470.
[16] CALAKLI F,TAUBIN G.SSD:Smooth Signed Distance Surface Reconstruction[J].Computer Graphics Forum,2011,30(7):1993-2002.
[17] LORENSEN W E,CLINE H E.Marching Cubes:A High Resolution 3D Surface Construction Algorithm[J].ACM Siggraph Computer Graphics,1987,21(4):163-169.
[18] KAZHDAN M,HOPPE H.Screened Poisson Surface Reconstruction[J].ACM Transactions on Graphics (TOG),2013,32(3):1-13.
[19] HIEP V H,KERIVEN R,LABATUT P,et al.Towards High-resolution Large-scale Multi-view Stereo[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2009:1430-1437.
[20] MITRA N J,NGUYEN A.Estimating Surface Normals in Noisy Point Cloud Data[C]//Proceedings of the 19th Annual Symposium on Computational Geometry.[S.l.]:ACM,2003:322-328.
[21] HOPPE H,DEROSE T,DUCHAMP T,et al.Surface Reconstruction from Unorganized Points[C]//Proceedings of ACM Siggraph.[S.l.]:ACM,1992.
[22] LABATUT P,PONS J-P,KERIVEN R.Efficient Multi-view Reconstruction of Large-scale Scenes Using Interest Points,Delaunay Triangulation and Graph Cuts[C]//IEEE 11th International Conference on Computer Vision.[S.l.]:IEEE,2007:1-8.
[23] 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.
[24] BOYKOV Y Y,JOLLY M P.Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in ND Images[C]//Proceedings of Eighth IEEE International Conference on Computer Vision.Vancouver:IEEE,2001:105-112.
[25] KAZHDAN M,BOLITHO M,HOPPE H.Poisson Surface Reconstruction[C]//Proceedings of the 4th Eurographics Symposium on Geometry Processing.[S.l.]:[s.n.],2006:61-70.
[26] HIRSCHM LLER H.Stereo Processing by Semiglobal Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(2):328-341.
[27] BOISSONNAT J D,DEVILLERS O,TEILLAUD M,et al.Triangulations in CGAL[C]//Proceedings of the 16th Annual Symposium on Computational Geometry.[S.l.]:ACM,2000:11-18.
[28] MANSON J,PETROVA G,SCHAEFER S.Streaming Surface Reconstruction Using Wavelets[C]//Computer Graphics Forum.[S.l.]:[s.n.],2008:1411-1420.
[29] CIGNONI P,ROCCHINI C,SCOPIGNO R.Metro:Measuring Error on Simplified Surfaces[C]//Computer Graphics Forum.[S.l.]:[s.n.],1998:167-174.