Difference of Normals as a Multi-scale Operator in Unorganized Point Clouds

A novel multi-scale operator for unorganized 3D point clouds is introduced. The Difference of Normals (DoN) provides a computationally efficient, multi-scale approach to processing large unorganized 3D point clouds. The application of DoN in the multi-scale filtering of two different real-world outdoor urban LIDAR scene datasets is quantitatively and qualitatively demonstrated. In both datasets the DoN operator is shown to segment large 3D point clouds into scale-salient clusters, such as cars, people, and lamp posts towards applications in semi-automatic annotation, and as a pre-processing step in automatic object recognition. The application of the operator to segmentation is evaluated on a large public dataset of outdoor LIDAR scenes with ground truth annotations.

[1]  Nico Blodow,et al.  Persistent Point Feature Histograms for 3D Point Clouds , 2008 .

[2]  Bao Li,et al.  Robust normal estimation for point clouds with sharp features , 2010, Comput. Graph..

[3]  Daniel Cohen-Or,et al.  Consolidation of unorganized point clouds for surface reconstruction , 2009, ACM Trans. Graph..

[4]  Yu Liu,et al.  Automatic segmentation of unorganized noisy point clouds based on the Gaussian map , 2008, Comput. Aided Des..

[5]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[6]  Chia-Hsiang Menq,et al.  Automatic data segmentation for geometric feature extraction from unorganized 3-D coordinate points , 2001, IEEE Trans. Robotics Autom..

[7]  Martial Hebert,et al.  Multi-scale interest regions from unorganized point clouds , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[8]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[9]  Marc Alexa,et al.  Computing and Rendering Point Set Surfaces , 2003, IEEE Trans. Vis. Comput. Graph..

[10]  Semyung Wang,et al.  A new segmentation method for point cloud data , 2002 .

[11]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[12]  Babak Taati,et al.  Local shape descriptor selection for object recognition in range data , 2011, Comput. Vis. Image Underst..

[13]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[14]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[15]  Yaorong Ge,et al.  Minimum reliable scale selection in 3D , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Thomas A. Funkhouser,et al.  Min-cut based segmentation of point clouds , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[17]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[18]  Craig Glennie.  A Kinematic Terrestrial LIDAR Scanning System , 2007 .

[19]  Michael A. Greenspan,et al.  Real-time Object Recognition in Sparse Range Images Using Error Surface Embedding , 2010, International Journal of Computer Vision.

[20]  Radu Bogdan Rusu,et al.  Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments , 2010, KI - Künstliche Intelligenz.

[21]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[22]  T. Lindeberg.  Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales , 1994 .

[23]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.