Comparison of an ℓ1-regression-based and a RANSAC-based planar segmentation procedure for urban terrain data with many outliers

For urban terrain data with many outliers, we compare an ℓ1-regression-based and a RANSAC-based planar segmentation procedure. The procedure consists of 1) calculating the normal at each of the points using ℓ1 regression or RANSAC, 2) clustering the normals thus generated using DBSCAN or fuzzy c-means, 3) within each cluster, identifying segments (roofs, walls, ground) by DBSCAN-based-subclustering of the 3D points that correspond to each cluster of normals and 4) fitting the subclusters by the same method as that used in Step 1 (ℓ1 regression or RANSAC). Domain decomposition is used to handle data sets that are too large for processing as a whole. Computational results for a point cloud of a building complex in Bonnland, Germany obtained from a depth map of seven UAV-images are presented. The ℓ1-regression-based procedure is slightly over 25% faster than the RANSAC-based procedure and produces better dominant roof segments. However, the roof polygonalizations and cutlines based on these dominant segments are roughly equal in accuracy for the two procedures. For a set of artificial data, ℓ1 regression is much more accurate and much faster than RANSAC. We outline the complete building reconstruction procedure into which the ℓ1-regression-based and RANSAC-based segmentation procedures will be integrated in the future.

[1]  George Vosselman,et al.  3D BUILDING MODEL RECONSTRUCTION FROM POINT CLOUDS AND GROUND PLANS , 2001 .

[2]  Jan-Michael Frahm,et al.  Detailed Real-Time Urban 3D Reconstruction from Video , 2007, International Journal of Computer Vision.

[3]  Andrea Fusiello,et al.  Robust Multiple Structures Estimation with J-Linkage , 2008, ECCV.

[4]  Vladimir Kolmogorov,et al.  Graph Based Algorithms for Scene Reconstruction from Two or More Views , 2004 .

[5]  C. Heipke,et al.  Multi-view dense matching supported by triangular meshes , 2011 .

[6]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  H. Gross,et al.  3D-MODELING OF URBAN STRUCTURES , 2005 .

[8]  Cyrus Shahabi,et al.  Web data retrieval: solving spatial range queries using k-nearest neighbor searches , 2009, GeoInformatica.

[9]  Franz Rottensteiner,et al.  Roof plane segmentation by combining multiple images and point clouds , 2010 .

[10]  Hermann Gross,et al.  On Applications of Sequential Multi-view Dense Reconstruction from Aerial Images , 2012, ICPRAM.

[11]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[12]  Ruiliang Pu,et al.  Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery , 2011 .

[13]  Karsten Schulz,et al.  CONTEXT-BASED URBAN TERRAIN RECONSTRUCTION FROM IMAGES AND VIDEOS , 2012 .

[14]  Martin Ester,et al.  Density‐based clustering , 2019, WIREs Data Mining Knowl. Discov..

[15]  Franz Leberl,et al.  Vertical- or Oblique Imagery for Semantic Building Interpretation , 2010 .

[16]  Horst Bischof,et al.  Fusion of Feature- and Area-Based Information for Urban Buildings Modeling from Aerial Imagery , 2008, ECCV.

[17]  Frank Nielsen,et al.  On weighting clustering , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  J. Lavery,et al.  Reconstruction and Texturing of 3D Urban Terrain from Uncalibrated Monocular Images Using L 1 Splines , 2010 .

[19]  Stephen P. Boyd,et al.  Graph Implementations for Nonsmooth Convex Programs , 2008, Recent Advances in Learning and Control.

[20]  H. Hirschmüller.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Stereo Processing by Semi-global Matching and Mutual Information , 2022 .