Visual Form pp 593-602 | Cite as

3-D Pose Estimation by an Improved Kohonen-Net

  • Brigitte Wirtz
  • Christoph Maggioni


A primary task in the process of three-dimensional object recognition given a two-dimensional image lies in the model-based pose estimation in space. Given a known set of correspondences between three-dimensional model points or different model features and two-dimensional image points or image features: What are the transformation and model parameters which convert the three-dimensional model into the observed two-dimensional image.


Input Space Input Pattern Rotational Parameter Perspective Transformation Camera Coordinate System 
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]
    W.G. Giloi: Interactive Computer Graphics, Prentice-Hall, Inc., Englewood Cliffs, N.J., 1978.Google Scholar
  2. [2]
    R.M. Haralick: Using Perspective Transformations in Scene Analysis, Computer Vision, Graphics and Image Processing 13, 1980, pp. 191–221.CrossRefGoogle Scholar
  3. [3]
    J.A. Kangas, T. Kohonen, T. Laaksonen: Variants of Self-Organizing Maps, IEEE Trans. on Neural Networks, vol. 1, no. 1, pp. 93–99, 1990.CrossRefGoogle Scholar
  4. [4]
    T. Kohonen: Analysis of a Simple Self-Organizing Process, Biological Cybernetics, pp. 135-140, 1982.Google Scholar
  5. [5]
    T. Kohonen: Clustering, Taxonomy, and Topological Maps of Features, Proc. 6th International Conference on Pattern Recognition, pp. 114-128, 1982.Google Scholar
  6. [6]
    T. Kohonen, K. Mäkisara: Representation of Sensory Information in Self-Organizing Feature Maps, AIP Conference Proceedings, pp. 271-276, 1986.Google Scholar
  7. [7]
    T. Kohonen, K. Mäkisara: The Self-Organizing Feature Maps, Phys. Scr. (Sweden), vol. 39, no. 1, pp. 168–172, 1989.CrossRefGoogle Scholar
  8. [8]
    T. Kohonen, K. Mäkisara, T. Saramäki: Phonotopic Maps — Insightful Representation of Phonological Features for Speech Recognition, Proc. IEEE, pp. 182-185, 1984.Google Scholar
  9. [9]
    D.G. Lowe: Perceptual Organization and Visual Recognition, Boston, Mass: Kluwer Academic Publishers, 1985.CrossRefGoogle Scholar
  10. [10]
    Th. Martinetz, H.J. Ritter, K. Schulten: 3D-Neural-Net for Learning Visuomotor-Coordination of a Robot Arm, Proceedings of the IJCNN, pp. 11-351-II-356, 1989.Google Scholar
  11. [11]
    H.J. Ritter, Th. Martinetz, K. Schulten: Neuronale Netze, Addison-Wesley, 1990.Google Scholar
  12. [12]
    S. Ullman, R. Basri: Recognition of Linear Combinations of Models, MIT, A.I. Memos, No. 1152, pp. 1-42, 1989.Google Scholar
  13. [13]
    B. Wirtz, Ch. Maggioni: SINAI — Ein objektorientiertes Bildverarbeitungssystem, Proceedings 11. DAGM-Symposium, Hamburg, Informatik Fachberichte Nr. 219, Springer Verlag, pp. 420-425, 1989.Google Scholar

Copyright information

© Springer Science+Business Media New York 1992

Authors and Affiliations

  • Brigitte Wirtz
    • 1
  • Christoph Maggioni
    • 1
  1. 1.Central Department of Research and DevelopmentSiemens AGMunichGermany

Personalised recommendations