A 3D classifier trained without field samples

This paper presents a 3D classifier that is shown to maintain performance whether trained with real sensor data from the field or purely trained with 3D geometric (Computer Aided Design, CAD, like) models (downloaded from the Internet for instance). The proposed classifier is a global 3D template matching technique which exploits the location of the ground surface for more accurate alignment. The segmentation and position of the ground is given by the segmentation technique in [7] (which does not assumed the ground to be flat). The proposed classifier outperforms Spin Image and Fast Point Feature Histogram (FPFH) based classifiers by up to 30% (the latter being tested at different scales), in the case of sparse 3D data acquired with a Velodyne sensor. In addition, the experimental results suggest that field samples may not be required in the training set of alignment-based 3D classifiers. This finding implies that the laborious task of gathering hand labelled field data for training may be avoidable for this type of classifier.

[1]  Sebastian Thrun,et al.  Upsampling range data in dynamic environments , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[3]  Olivier Colot,et al.  Local visual patch for 3d shape retrieval , 2010, 3DOR '10.

[4]  Surya P. N. Singh,et al.  A Pipeline for the Segmentation and Classification of 3D Point Clouds , 2010, ISER.

[5]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[6]  Luc Van Gool,et al.  Orientation invariant 3D object classification using hough transform based methods , 2010, 3DOR '10.

[7]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .

[8]  David Fofi,et al.  A review of recent range image registration methods with accuracy evaluation , 2007, Image Vis. Comput..

[9]  R. Kimmel,et al.  Matching shapes by eigendecomposition of the Laplace-Beltrami operator , 2010 .

[10]  Frank B. ter Haar,et al.  Single spin image-ICP matching for efficient 3D object recognition , 2010, 3DOR '10.

[11]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[12]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[13]  Edmond Boyer,et al.  Temporally Coherent Segmentation of 3D Reconstructions , 2010 .

[14]  Dieter Fox,et al.  Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation , 2010, Int. J. Robotics Res..

[15]  Yi Liu,et al.  Shape Topics: A Compact Representation and New Algorithms for 3D Partial Shape Retrieval , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[17]  Andrew E. Johnson,et al.  Spin-Images: A Representation for 3-D Surface Matching , 1997 .

[18]  Gary R. Bradski,et al.  Fast 3D recognition and pose using the Viewpoint Feature Histogram , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Christoph Stiller,et al.  Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[21]  Bertrand Douillard,et al.  On the segmentation of 3D LIDAR point clouds , 2011, 2011 IEEE International Conference on Robotics and Automation.

[22]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.