A Pipeline for the Segmentation and Classification of 3D Point Clouds

  • B. Douillard
  • J. Underwood
  • V. Vlaskine
  • A. Quadros
  • S. Singh
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 79)


This paper presents algorithms for fast segmentation of 3D point clouds and subsequent classification of the obtained 3D segments. The method jointly determines the ground surface and segments individual objects in 3D, including overhanging structures. When compared to six other terrain modelling techniques, this approach has minimal error between the sensed data and the representation; and is fast (processing a Velodyne scan in approximately 2 seconds). Applications include improved alignment of successive scans by enabling operations in sections (Velodyne scans are aligned 7% sharper compared to an approach using raw points) and more informed decision-making (paths move around overhangs). The use of segmentation to aid classification through 3D features, such as the Spin Image or the Spherical Harmonic Descriptor, is discussed and experimentally compared. Moreover, the segmentation facilitates a novel approach to 3D classification that bypasses feature extraction and directly compares 3D shapes via the ICP algorithm. This technique is shown to achieve accuracy on par with the best feature based classifier (92.1%) while being significantly faster and allowing a clearer understanding of the classifier’s behaviour.


Point Cloud Path Planning Iterative Close Point Spin Image Iterative Close Point 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Anguelov, D., Taskar, B., Chatalbashev, V., Koller, D., Gupta, D., Heitz, G., Ng, A.: Discriminative learning of Markov random fields for segmentation of 3D scan data. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR (2005)Google Scholar
  2. 2.
    Bosse, M., Zlot, R.: Place recognition using regional point descriptors for 3d mapping. In: Proc. of the International Conference on Field and Service Robotics, FSR (2009)Google Scholar
  3. 3.
    Choset, H., Lynch, K.M., Hutchinson, S., Kantor, G., Burgard, W., Kavraki, L.E., Thrun, S.: Principles of Robot Motion: Theory, Algorithms, and Implementations. MIT Press, Cambridge (2005)Google Scholar
  4. 4.
  5. 5.
    Johnson, A.: Spin-Images: A Representation for 3-D Surface Matching. PhD thesis, Carnegie Mellon University (1997)Google Scholar
  6. 6.
    Johnson, A., Hebert, M.: Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 25(1), 433–449 (1999)CrossRefGoogle Scholar
  7. 7.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3d shape descriptors. In: Proceedings of the 2003 Eurographics/ACM SIGGRAPH Symposium on Geometry Processing (2003)Google Scholar
  8. 8.
    Kelly, A., Stentz, A., Amidi, O., Bode, M., Bradley, D., Diaz-Calderon, A., Happold, M., Herman, H., Pilarski, T., Rander, P., Thayer, S., Vallidis, N., Warner, R.: Toward reliable off road autonomous vehicles operating in challenging environments. International Journal of Robotics Research (IJRR) 25(5-6), 449–483 (2006)CrossRefGoogle Scholar
  9. 9.
    Lai, K., Fox, D.: 3D laser scan classification using web data and domain adaptation. In: Proceedings of Robotics: Science and Systems, Seattle, USA (June 2009)Google Scholar
  10. 10.
    Lalonde, J., Vandapel, N., Huber, D., Hebert, M.: Natural terrain classification using three-dimensional ladar data for ground robot mobility. Journal of Field Robotics 23(10), 839–861 (2006)CrossRefGoogle Scholar
  11. 11.
    Malisiewicz, T., Efros, A.: Improving spatial support for objects via multiple segmentations. In: British Machine Vision Conference, pp. 282–289 (2007)Google Scholar
  12. 12.
    Melkumyan, N.: Surface-based Synthesis of 3D Maps for Outdoor Unstructured Environments. PhD thesis, University of Sydney, Australian Centre for Field Robotics (2008)Google Scholar
  13. 13.
    Moosmann, F., Pink, O., Stiller, C.: Segmentation of 3D Lidar Data in non-flat Urban Environments using a Local Convexity Criterion. In: Intl. Conf. Information Visualisation (2009)Google Scholar
  14. 14.
    Munoz, D., Vandapel, N., Hebert, M.: Onboard contextual classification of 3-d point clouds with learned high-order markov random fields. In: Proc. of the IEEE International Conference on Robotics & Automation, ICRA (2009)Google Scholar
  15. 15.
    Pfaff, P., Burgard, W.: An efficient extension to elevation maps for outdoor terrain mapping and loop closing. International Journal of Robotics Research (IJRR) 26(2), 217–230 (2007)CrossRefGoogle Scholar
  16. 16.
    Rusinkiewicz, S., Levoy, M.: Efficient variants of the ICP algorithm. In: Proc. 3DIM, pp. 145–152 (2001)Google Scholar
  17. 17.
    Siciliano, B., Khatib, O.: Springer handbook of robotics. Springer (2008)Google Scholar
  18. 18.
    Simmons, R., Henriksen, L., Chrisman, L., Whelan, G.: Obstacle avoidance and safeguarding for a lunar rover. In: AIAA Forum on Advanced Developments in Space Robotics (1996)Google Scholar
  19. 19.
    Thrun, S., et al.: Stanley: The robot that won the darpa grand challenge. Journal of Field Robotics 23(9), 661–692 (2006)CrossRefGoogle Scholar
  20. 20.
    Triebel, R., Kersting, K., Burgard, W.: Robust 3D scan point classification using associative Markov networks. In: Proc. of the IEEE International Conference on Robotics & Automation (ICRA), pp. 2603–2608 (2006)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2014

Authors and Affiliations

  • B. Douillard
    • 1
  • J. Underwood
    • 1
  • V. Vlaskine
    • 1
  • A. Quadros
    • 1
  • S. Singh
    • 1
  1. 1.The Australian Centre for Field RoboticsThe University of SydneySydneyAustralia

Personalised recommendations