Advertisement

A direct recovery of superquadric models in range images using recover-and-select paradigm

  • Aleš Leonardis
  • Franc Solina
  • Alenka Macerl
Shape Modelling
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)

Abstract

We present a novel approach to reliable and efficient recovery of part-descriptions from range images. We show that a set of superquadric models can be directly recovered from unsegmented range data, as opposed to methods which attempt the recovery of volumetric models only after the data has been pre-segmented using extensive pre-processing. The approach is based on the recover-and-select paradigm which consists of two intertwined stages: model-recovery and model-selection. At the model-recovery stage a redundant set of superquadrics is initiated in the image and allowed to grow, which involves an iterative procedure combining data classification and parameter estimation. All the recovered models are passed to the model-selection procedure where only the models resulting in the simplest overall description are selected.

Keywords

Computer Vision Range Image Model Recovery Volumetric Model Final Description 
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.

References

  1. 1.
    P. K. Allen and P. Michelman. Acquisition and interpretation of 3-D sensor data from touch. IEEE Trans. on Robotics and Autom., 6(4):397–404, 1990.Google Scholar
  2. 2.
    R. Bajcsy, F. Solina, and A. Gupta. Segmentation versus object representation — are they separable? In R. Jain and A. Jain, editors, Analysis and Interpretation of Range Images, Springer-Verlag, New York, 1990.Google Scholar
  3. 3.
    A. H. Barr. Superquadrics and angle-preserving transformations. IEEE Comp. Graph. and Appl., 1(1):11–23, 1981.Google Scholar
  4. 4.
    P. J. Besl. Surfaces in Range Image Understanding. Springer-Verlag, 1988.Google Scholar
  5. 5.
    M. Brady, J. Ponce, A. Yuille, and H. Asada. Describing surfaces. Computer Vision, Graphics, and Image Processing, 32(1):1–28, 1985.Google Scholar
  6. 6.
    F. P. Ferrie, J. Lagarde, and P. Whaite. Darboux frames, snakes, and super-quadrics: Geometry from the bottom up. IEEE Trans. on PAMI-15(8):771–784, 1993.Google Scholar
  7. 7.
    P. Fua and A. J. Hanson. Objective functions for feature discrimination. In Proc. 11th Int. Joint Conf. on Artif. Intell., pp. 1596–1602, Detroit, MI, 1989.Google Scholar
  8. 8.
    A. Gupta and R. Bajcsy. Volumetric segmentation of range images of 3D objects using superquadric models. Computer Vision, Graphics, and Image Processing: Image Understanding, 58(3):302–326, 1993.Google Scholar
  9. 9.
    Y. G. Leclerc. Constructing simple stable descriptions for image partitioning. Int. Journal of Computer Vision, 3:73–102, 1989.Google Scholar
  10. 10.
    A. Leonardis. Image Analysis Using Parametric Models: Model-Recovery and Model-Selection Paradigm. A Dissertation in Computer Science. University of Ljubljana, Faculty of EE & CS. May 1993.Google Scholar
  11. 11.
    A. Leonardis and R. Bajcsy. Finding parametric curves in an image. In G. Sandini, editor, Proc. of The Second European Conf. on Computer Vision-ECCV-92, pp. 653–657. Springer-Verlag, 1992. LNCS-Series Vol. 588.Google Scholar
  12. 12.
    A. Leonardis, A. Gupta, and R. Bajcsy. Segmentation of range images as the search for geometric parametric models. Int. Journal of Computer Vision, To appear.Google Scholar
  13. 13.
    D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Trans. on PAMI 15(6):580–591, 1993.Google Scholar
  14. 14.
    A. P. Pentland. Perceptual organization and the representation of natural form. Artif. Intell., 28(2):293–331, 1986.Google Scholar
  15. 15.
    A. P. Pentland. Recognition by parts. In Proc. First Int. Conf. on Computer Vision, London, pp. 612–620, 1987.Google Scholar
  16. 16.
    A. P. Pentland. Automatic extraction of deformable part models. Int. Journal of Computer Vision, 4:107–126, 1990.Google Scholar
  17. 17.
    A. P. Pentland and S. Sclaroff. Closed-form solutions for physically based shape modeling and recognition. IEEE Trans. on PAMI 13(7):715–729, 1991.Google Scholar
  18. 18.
    N. S. Raja and A. K. Jain. Recognizing geons from superquadrics fitted to range data. Image and Vision Computing Journal, 10(3):179–190, 1992.Google Scholar
  19. 19.
    F. Solina and R. Bajcsy. Recovery of parametric models from range images: The case for superquadrics with global deformations. IEEE Trans. on PAMI-12(2):131–147, 1990.Google Scholar
  20. 20.
    F. Solina and A. Leonardis. Selective scene modeling. In Proc. of the 11th Int. Conf. on Pattern Recognition, pp. A:87–90, The Hague, The Netherlands, 1992.Google Scholar
  21. 21.
    D. Terzopoulos and D. Metaxas. Dynamic 3D models with local and global deformations: Deformable superquadrics. IEEE Trans. on PAMI 13(7):703–714, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Aleš Leonardis
    • 1
  • Franc Solina
    • 1
  • Alenka Macerl
    • 1
  1. 1.Computer Vision Laboratory, Faculty of Electrical Engineering and Computer ScienceUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations