‘misspelled’ visual words in unsupervised range data classification: the effect of noise on classification performance

Recent work in the domain of classification of point clouds has shown that topic models can be suitable tools for inferring class groupings in an unsupervised manner. However, point clouds are frequently subject to non-negligible amounts of sensor noise. In this paper, we analyze the effect on classification accuracy of noise added to both an artificial data set and data collected from a Light Detection and Ranging (LiDAR) scanner, and show that topic models are less robust to ‘misspelled’ words than the more näive k-means classifier. Furthermore, standard spin images prove to be a more robust feature under noise than their derivative, ‘angular’ spin images. We additionally show that only a small subset of local features are required in order to give comparable classification accuracy to a full feature set.

[1]  Michael Himmelsbach,et al.  LIDAR-based 3D Object Perception , 2008 .

[2]  Richard S. Zemel,et al.  Learning Parts-Based Representations of Data , 2006, J. Mach. Learn. Res..

[3]  Wolfram Burgard,et al.  Unsupervised discovery of object classes from range data using latent Dirichlet allocation , 2009, Robotics: Science and Systems.

[4]  Leonidas J. Guibas,et al.  Estimating surface normals in noisy point cloud data , 2004, Int. J. Comput. Geom. Appl..

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

[6]  Pietro Perona,et al.  Unsupervised learning of visual taxonomies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Martin Buss,et al.  Development of a Multi-modal Multi-user Telepresence and Teleaction System , 2010, Int. J. Robotics Res..

[8]  Bernt Schiele,et al.  3D object recognition from range images using local feature histograms , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Martial Hebert,et al.  Parts-based 3D object classification , 2004, CVPR 2004.

[10]  H. Quynh Dinh,et al.  Multi-Resolution Spin-Images , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  P. Newman,et al.  Using Naturally Salient Regions for SLAM with 3 D Laser Data ∗ , 2005 .

[12]  Martial Hebert,et al.  3D measurements from imaging laser radars: how good are they? , 1992, Image Vis. Comput..

[13]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  Vladimir G. Kim,et al.  Shape-based recognition of 3D point clouds in urban environments , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[17]  Paul H. Lewis,et al.  Towards Automatic Classification of 3-D Museum Artifacts Using Ontological Concepts , 2005, CIVR.

[18]  Alberto Del Bimbo,et al.  Content-Based Retrieval of 3-D Objects Using Spin Image Signatures , 2007, IEEE Transactions on Multimedia.

[19]  Alexei A. Efros,et al.  Unsupervised discovery of visual object class hierarchies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Shourya Roy,et al.  How Much Noise Is Too Much: A Study in Automatic Text Classification , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

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

[22]  Martial Hebert,et al.  3-D measurements from imaging laser radars: how good are they? , 1991, Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91.

[23]  Geoffrey E. Hinton,et al.  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-' Washington , D . C . , June , 1983 OPTIMAL PERCEPTUAL INFERENCE , 2011 .