Support Vector Machines for Classification of Geometric Primitives in Point Clouds

  • Manuel Caputo
  • Klaus Denker
  • Mathias O. Franz
  • Pascal LaubeEmail author
  • Georg Umlauf
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9213)


Classification of point clouds by different types of geometric primitives is an essential part in the reconstruction process of CAD geometry. We use support vector machines (SVM) to label patches in point clouds with the class labels tori, ellipsoids, spheres, cones, cylinders or planes. For the classification features based on different geometric properties like point normals, angles, and principal curvatures are used. These geometric features are estimated in the local neighborhood of a point of the point cloud. Computing these geometric features for a random subset of the point cloud yields a feature distribution. Different features are combined for achieving best classification results. To minimize the time consuming training phase of SVMs, the geometric features are first evaluated using linear discriminant analysis (LDA).

LDA and SVM are machine learning approaches that require an initial training phase to allow for a subsequent automatic classification of a new data set. For the training phase point clouds are generated using a simulation of a laser scanning device. Additional noise based on an laser scanner error model is added to the point clouds. The resulting LDA and SVM classifiers are then used to classify geometric primitives in simulated and real laser scanned point clouds.

Compared to other approaches, where all known features are used for classification, we explicitly compare novel against known geometric features to prove their effectiveness.


Support Vector Machine Point Cloud Linear Discriminant Analysis Geometric Feature Principal Curvature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. [AFB+12]
    Arbeiter, G., Fuchs, S., Bormann, R., Fischer, J., Verl, A.: Evaluation of 3D feature descriptors for classification of surface geometries in point clouds. In: International Conference on Intelligent Robots and Systems, pp. 1644–1650 (2012)Google Scholar
  2. [CGA]
    CGAL, Computational Geometry Algorithms Library.
  3. [CP05]
    Cazals, F., Pouget, M.: Estimating differential quantities using polynomial fitting of osculating jets. Comput. Aided Geom. Des. 22(2), 121–146 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  4. [CST00]
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and other kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)CrossRefGoogle Scholar
  5. [DHR+13]
    Denker, K., Hagel, D., Raible, J., Umlauf, G., Hamann, B.: On-line reconstruction of CAD geometry. In: International Conference on 3D Vision, pp. 151–158 (2013)Google Scholar
  6. [DHS01]
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)zbMATHGoogle Scholar
  7. [EYO12]
    Endoh, M., Yanagimachi, T., Ohbuchi, R.: Efficient manifold learning for 3D model retrieval by using clustering-based training sample reduction. In: International Conference on Acoustics, Speech and Signal Processing pp. 2345–2348 (2012)Google Scholar
  8. [FB81]
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  9. [GKF09]
    Golovinskiy, A., Kim, V.G., Funkhouser, T.: Shape-based recognition of 3D point clouds in urban environments. In:International Conference on Computer Vision (2009)Google Scholar
  10. [HHYR12]
    Hwang, H., Hyung, S., Yoon, S., Roh, K.: Robust descriptors for 3D point clouds using geometric and photometric local feature. In: International Conference on Intelligent Robots and Systems (IROS), pp. 4027–4033 (2012)Google Scholar
  11. [HLLS01]
    Hetzel, G., Leibe, B., Levi, P., Schiele, B.: 3D object recognition from range images using local feature histograms. In: CVPR, pp. 394–399 (2001)Google Scholar
  12. [IHMG08]
    Igel, C., Heidrich-Meisner, V., Glasmachers, T.: Shark. J. Mach. Learn. Res. 9, 993–996 (2008)zbMATHGoogle Scholar
  13. [KvD92]
    Koenderink, J.J., van Doorn, A.J.: Surface shape and curvature scales. Image Vis. Comput. 10(8), 557–565 (1992)CrossRefGoogle Scholar
  14. [LC87]
    Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: SIGGRAPH 1987, pp. 163–169 (1987)Google Scholar
  15. [MS09]
    Mahmoudi, M., Sapiro, G.: Three-dimensional point cloud recognition via distributions of geometric distances. Graph. Models 71(1), 22–31 (2009)CrossRefGoogle Scholar
  16. [OFCD02]
    Osada, R., Funkhouser, T., Chazelle, B., Dobkin, D.: Shape distributions. ACM Trans. Graph. 21(4), 807–832 (2002)CrossRefGoogle Scholar
  17. [RMBB08]
    Rusu, R.B., Marton, Z.C., Blodow, N., Beetz, M.: Persistent point feature histograms for 3D point clouds. In: 10th International Conference on Intelligent Autonomous Systems (2008)Google Scholar
  18. [SS01]
    Schoelkopf, B., Smola, A.J.: Learning with Kernels. MIT Press, Cambridge (2001)Google Scholar
  19. [WHH03]
    Wahl, E., Hillenbrand, U., Hirzinger, G.: Surflet-pair-relation histograms: a statistical 3D-shape representation for rapid classification. In: 3DIM, pp. 474–482. IEEE (2003)Google Scholar
  20. [YTSO08]
    Yamamoto, A., Tezuka, M., Shimizu, T., Ohbuchi, R.: SHREC 2008 entry: semi-supervised learning for semantic 3D model retrieval. In: International Conference on Shape Modeling and Applications (2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Manuel Caputo
    • 1
  • Klaus Denker
    • 1
  • Mathias O. Franz
    • 1
  • Pascal Laube
    • 1
    Email author
  • Georg Umlauf
    • 1
  1. 1.Institute for Optical SystemsUniversity of Applied Sciences ConstanceKonstanzGermany

Personalised recommendations