Parametrized SOMs for Object Recognition and Pose Estimation (original) (raw)

Abstract

We present the “Parametrized Self-Organizing Map” (PSOM) as a method for 3D object recognition and pose estimation. The PSOM can be seen as a continuous extension of the standard Self-Organizing Map which generalizes the discrete set of reference vectors to a continuous manifold. In the context of visual learning, manifolds based on PSOMs can be used to represent the appearance of various objects. We demonstrate this approach and its merits in an application example.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. J.L. Crowley and F. Pourraz. Continuity properties of the appearance manifold formobile robot position estimation. Image and Vision Computing, 2001.
    Google Scholar
  2. Teuvo Kohonen. Self-Organizing maps. Springer series in information science. Springer, Berlin, Heidelberg, New York, third edition, 2001.
    MATH Google Scholar
  3. H. Murase and S.K. Nayar. Visual learning and recognition of 3-d objects from appearance. Int’l J. Computer Vision, 14:5–24, 1995.
    Article Google Scholar
  4. S. A. Nene, S. K. Nayar, and H. Murase. Columbia Object Image Library (COIL-20). Technical Report CUCUS-006-96, Dept. Computer Science, Columbia Univ. New York, N.Y. 10027, 1996.
    Google Scholar
  5. C. Nölker and H. Ritter. Parametrized SOMs for hand posture reconstruction. In S.-I. Amari, C.L. Giles, M. Gori, and V. Piuri, editors, Proc. IEEE-INNS-ENNS Int’l Joint Conf. on Neural Networks IJCNNY’2000, 2000.
    Google Scholar
  6. T.D. Sanger. Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks, 2:459–473, 1989.
    Article Google Scholar
  7. Michael A. Sipe and David Casasent. Global feature space neural network for active object recognition. In IJCNN’99, Washington, D.C., 1999.
    Google Scholar
  8. Jörg Walter and Helge Ritter. Local PSOMs and Chebyshev PSOMs-improving the parametrised self-organizing maps. In Proc. ICANN, Paris, volume 1, pages 95–102, October 1995.
    Google Scholar
  9. Jörg Walter and Helge Ritter. Rapid learning with parametrized self-organizing maps. Neurocomputing, 12:131–153, 1996.
    Article MATH Google Scholar

Download references

Author information

Authors and Affiliations

  1. Faculty of Technology, Bielefeld University, D-33501, Bielefeld, Germany
    Axel Saalbach, Gunther Heidemann & Helge Ritter

Authors

  1. Axel Saalbach
  2. Gunther Heidemann
  3. Helge Ritter

Editor information

Editors and Affiliations

  1. ETS Informática, Universidad Autónoma de Madrid, 28049, Madrid, Spain
    José R. Dorronsoro

Rights and permissions

© 2002 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Saalbach, A., Heidemann, G., Ritter, H. (2002). Parametrized SOMs for Object Recognition and Pose Estimation. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5\_146

Download citation

Keywords

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.

Publish with us