Contour Detection in Unstructured 3D Point Clouds

We describe a method to automatically detect contours, i.e. lines along which the surface orientation sharply changes, in large-scale outdoor point clouds. Contours are important intermediate features for structuring point clouds and converting them into high-quality surface or solid models, and are extensively used in graphics and mapping applications. Yet, detecting them in unstructured, inhomogeneous point clouds turns out to be surprisingly difficult, and existing line detection algorithms largely fail. We approach contour extraction as a two-stage discriminative learning problem. In the first stage, a contour score for each individual point is predicted with a binary classifier, using a set of features extracted from the point's neighborhood. The contour scores serve as a basis to construct an overcomplete graph of candidate contours. The second stage selects an optimal set of contours from the candidates. This amounts to a further binary classification in a higher-order MRF, whose cliques encode a preference for connected contours and penalize loose ends. The method can handle point clouds > 107 points in a couple of minutes, and vastly outperforms a baseline that performs Canny-style edge detection on a range image representation of the point cloud.

[1]  D. Cohen-Or,et al.  Robust moving least-squares fitting with sharp features , 2005, ACM Trans. Graph..

[2]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[3]  Stefan Gumhold,et al.  Feature Extraction From Point Clouds , 2001, IMR.

[4]  Pascal Fua,et al.  Automated reconstruction of tree structures using path classifiers and Mixed Integer Programming , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Henrik I. Christensen,et al.  RGB-D edge detection and edge-based registration , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Benjamin B. Kimia,et al.  A Multi-stage Approach to Curve Extraction , 2014, ECCV.

[7]  陈宝权 GlobFit: Consistently Fitting Primitives by Discovering Global Relations , 2011 .

[8]  Sebastian Nowozin,et al.  A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Michael M. Kazhdan,et al.  Screened poisson surface reconstruction , 2013, TOGS.

[10]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[11]  Jianxiong Xiao,et al.  Reconstructing the World's Museums , 2012, ECCV.

[12]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Dimitri Lague,et al.  3D Terrestrial LiDAR data classification of complex natural scenes using a multi-scale dimensionality criterion: applications in geomorphology , 2011, ArXiv.

[14]  Benjamin B. Kimia,et al.  3D curve sketch: Flexible curve-based stereo reconstruction and calibration , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Florent Lafarge,et al.  Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation , 2012, International Journal of Computer Vision.

[16]  Jean-Francois Mangin,et al.  Detection of linear features in SAR images: application to road network extraction , 1998, IEEE Trans. Geosci. Remote. Sens..

[17]  Jitendra Malik,et al.  Reconstructing Polyhedral Models of Architectural Scenes from Photographs , 1996, ECCV.

[18]  F. Dornaika,et al.  EXTRACTING WIRE-FRAME MODELS OF STREET FACADES FROM 3D POINT CLOUDS AND THE CORRESPONDING CADASTRAL MAP , 2010 .

[19]  Jan Dirk Wegner,et al.  Mind the Gap: Modeling Local and Global Context in (Road) Networks , 2014, GCPR.

[20]  Vladimir Kolmogorov,et al.  Graph cut based image segmentation with connectivity priors , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Markus H. Gross,et al.  Feature Preserving Point Set Surfaces based on Non‐Linear Kernel Regression , 2009, Comput. Graph. Forum.

[22]  Samia Boukir,et al.  Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests , 2011 .

[23]  Uwe Soergel,et al.  Matching of straight line segments from aerial stereo images of urban areas , 2012 .

[24]  Christian Briese,et al.  THREE-DIMENSIONAL MODELLING OF BREAKLINES FROM AIRBORNE LASER SCANNER DATA , 2004 .

[25]  Horst Bischof,et al.  Line3D: Efficient 3D Scene Abstraction for the Built Environment , 2015, GCPR.

[26]  Zoltan-Csaba Marton,et al.  On fast surface reconstruction methods for large and noisy point clouds , 2009, 2009 IEEE International Conference on Robotics and Automation.

[27]  Markus H. Gross,et al.  Multi‐scale Feature Extraction on Point‐Sampled Surfaces , 2003, Comput. Graph. Forum.

[28]  Pascal Fua,et al.  Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Priors , 2011, Neuroinformatics.

[29]  Boris Jutzi,et al.  Feature relevance assessment for the semantic interpretation of 3D point cloud data , 2013 .

[30]  Cordelia Schmid,et al.  Automatic line matching across views , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.