Recognizing Objects in Range Data Using Regional Point Descriptors

  • Andrea Frome
  • Daniel Huber
  • Ravi Kolluri
  • Thomas Bülow
  • Jitendra Malik
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3023)


Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.


Point Cloud Basis Point Recognition Rate Spin Image Support Region 
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. 1.
    E. Bardinet, S. F. Vidal, Arroyo S. D., Malandain G., de la Capilla, N. P.B.: Structural object matching. Technical Report DECSAI-000303, University of Granada, Dept. of Computer Science and AI, Granada, Spain (February 2000) Google Scholar
  2. 2.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(4), 509–522 (2002)CrossRefGoogle Scholar
  3. 3.
    Binford, T.O.: Visual perception by computer. Presented at IEEE Conference on Systems and Control, Miami, FL (1971)Google Scholar
  4. 4.
    Bloomenthal, Lim, C.: Skeletal methods of shape manipulation. In: International Conference on Shape Modeling and Applications, pp. 44–47 (1999)Google Scholar
  5. 5.
    Chua, C.S., Jarvis, R.: Point signatures: a new representation for 3D object recognition. International Journal of Computer Vision 25(1), 63–85 (1997)CrossRefGoogle Scholar
  6. 6.
    Zhang, D., Herbert, M.: Experimental analysis of harmonic shape images. In: Proceedings of Second International Conference on 3-D Digital Imaging and Modeling, October 1999, pp. 191–200 (1999)Google Scholar
  7. 7.
    Solina, F., Bajcsy, R.: Recovery of parametric models from range images: The case for superquadrics with global deformations. IEEE Trans. on Pattern Analysis and Machine Intelligence (February 1990)Google Scholar
  8. 8.
    Funkhouser, T., Min, P., Kazhdan, M., Chen, J., Halderman, A., Dobkin, D., Jacobs, D.: A search engine for 3d models. ACM Transactions on Graphics 22, 83–105 (2003)CrossRefGoogle Scholar
  9. 9.
    Roth, G.: Registering two overlapping range images. In: Proceedings of Second International Conference on 3-D Digital Imaging and Modeling, October 1999, pp. 191–200 (1999)Google Scholar
  10. 10.
    Huber, D.F., Hebert, M.: Fully automatic registration of multiple 3D data sets. Img. and Vis. Comp. 21(7), 637–650 (2003)CrossRefGoogle Scholar
  11. 11.
    Indyk, P., Motwani, R.: Approximate nearest neighbor - towards removing the curse of dimensionality. In: Proceedings of the 30th Symposium on Theory of Computing (1998)Google Scholar
  12. 12.
    De Infografica, E.: De Espona 3D Models Enciclopedia,
  13. 13.
    Johnson, A.E., Hebert, M.: Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(5), 433–449 (1999)CrossRefGoogle Scholar
  14. 14.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3d shape descriptors. In: Proceedings of the Eurographics/ACM SIGGRAPH symposium on Geometry processing, pp. 156–164. Eurographics Association (2003)Google Scholar
  15. 15.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV, September 1999, pp. 1000–1015 (1999)Google Scholar
  16. 16.
    Matei, B., Meer, P.: A general method for errors-in-variables problems in computer vision. In: CVPR, June 2000, vol. 2 (2000)Google Scholar
  17. 17.
    Mikolajczk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR, June 2003, vol. II, pp. 257–263 (2003)Google Scholar
  18. 18.
    Mori, G., Belongie, S., Malik, J.: Shape contexts enable efficient retrieval of similar shapes. In: CVPR, vol. 1, pp. 723–730 (2001)Google Scholar
  19. 19.
    Osada, R., Funkhouser, T., Chayelle, B., Dobkin, D.: Matching 3d models with shape distributions. In: Shape Modeling International (May 2001)Google Scholar
  20. 20.
    Ruiz-Correa, S., Shapiro, L., Miela, M.: A new paradigm for recognizing 3d object shapes from range data. In: ICCV (October 2003)Google Scholar
  21. 21.
    Stein, F., Medioni, G.: Structural indexing: efficient 3D object recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 14(2), 125–145 (1992)CrossRefGoogle Scholar
  22. 22.
    Sun, Y., Abidi, M.A.: Surface matching by 3d point’s fingerprint. In: ICCV, July 2001, pp. 263–269 (2001)Google Scholar
  23. 23.
    Wu, K.: Levine M. Recovering parametrics geons from multiview range data. In: CVPR (June 1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Andrea Frome
    • 1
  • Daniel Huber
    • 2
  • Ravi Kolluri
    • 1
  • Thomas Bülow
    • 1
  • Jitendra Malik
    • 1
  1. 1.University of California BerkeleyBerkeleyUSA
  2. 2.Carnegie Mellon UniversityPittsburghUSA

Personalised recommendations