Growing Multi-Dimensional Self-Organizing Maps for Motion Detection

  • Udo Seiffert
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 78)


The standard Self-Organizing Map consists of a two-dimensional rectangular grid of neurons. For many applications this represents a very good target to reduce the dimensionality of the input data. However, occasionally a multi-dimensional layer, keeping more than two dimensions of the input data, might be more advantageous. This sometimes also called hypercube topology can be considered as the universal case of the standard topology. This chapter gives an introduction and demonstrates basic properties by means of applications from motion picture analysis.


Motion Vector Motion Detection Basic Pattern Image Block Winning Neuron 
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.

Bibliography on Chapter 5

  1. 1.
    Kohonen, T. (1995): Self-Organizing Maps, 2nd Edition. Springer, Berlin.CrossRefGoogle Scholar
  2. 2.
    Singh, A. (1991): Optic Flow Computation. IEEE Press, Los Alamitos.Google Scholar
  3. 3.
    Fleet, D.J. (1992): Measurement of Image Velocity. Kluwer Academic Publishers, Amsterdam.CrossRefMATHGoogle Scholar
  4. 4.
    Koller, D., Daniilidis, K., Nagel, H.H. (1993): Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes. International Journal of Computer Vision, 10, 257–281.CrossRefGoogle Scholar
  5. 5.
    Jain, J.R., Jain, A.K. (1981): Displacement Measurement and its Application in Inter-Frame Image Coding. IEEE Transactions on Communications, 29, 1799–1808.CrossRefGoogle Scholar
  6. 6.
    Yamaguchi, H., Sugi, T., Kinuhata, K. (1987): Movement-Compensated Frame-Frequency Conversion of Television Signals. IEEE Transactions on Communications, 35, 1069–1082.CrossRefGoogle Scholar
  7. 7.
    The Open MPEG (Moving Picture Expert Group) Consortium (1990): MPEG-1 Specification ISO 11172–1 and 11172–2.Google Scholar
  8. 8.
    The Open MPEG (Moving Picture Expert Group) Consortium (1990): MPEG-2/DVD Specification ISO 13818–1 and 13818–2.Google Scholar
  9. 9.
    Hogden, J., Saltzman, E., Rubin, P. (1993): Tracking Moving Objects with Unsupervised Neural Networks. In: Proceedings of World Congress on Neural Networks. Lawrence Erlbaum, Hillsdale, 409–412.Google Scholar
  10. 10.
    Tsukamoto, A., Lee, C.W., Tsuji, S. (1993): Detection and Tracking of Human Face with Synthesised Templates. In: Proceedings of Asian Conference on Computer Vision. IEEE Press, Osaka, 183–186.Google Scholar
  11. 11.
    Wimbauer, S., Gerstner, W., van Hemmen, J.L. (1994): Motion Detection in a Linsker Network. In: Proceedings of International Conference on Artificial Neural Networks. Springer, Berlin, 1001–1004.Google Scholar
  12. 12.
    Jiang, J. (1995): Algorithm Design of an Image Compression Neural Network. In: Proceedings of World Congress on Neural Networks. INNS Press, New York, 792–798.Google Scholar
  13. 13.
    Szu, H., Telfer, B., Garcia, J. (1996): Wavelet Transforms and Neural Networks for Compression and Recognition. Neural Networks, 4, 695–708.CrossRefGoogle Scholar
  14. 14.
    Wang, R. (1996): A Network Model for the Optic Flow Computation of the MST Neurons. Neural Networks, 3, 411–426.CrossRefGoogle Scholar
  15. 15.
    Michaelis, B., Schnelting, O., Seiffert, U., Mecke, R. (1995): Motion Estimation Using a Compounded SOM-MLP Network. In: Proceedings of World Congress on Neural Networks. INNS Press, New York, 103–106.Google Scholar
  16. 16.
    Michaelis, B., Schnelting, O., Seifert, U., Mecke, R. (1996): Adaptive Filtering of Distorted Displacement Vector Fields Using Artificial Neural Networks. In: Proceedings of International Conference on Pattern Recognition, Vol. IV. IEEE Press, Los Alamitos, 335–339.CrossRefGoogle Scholar
  17. 17.
    Lippmann, R.P. (1987): An Introduction to Computing with Neural Nets. IEEE ASSP Magazine, 4, 4–23.CrossRefGoogle Scholar
  18. 18.
    Arbib, M.A. (1993): Brains, Machines and Mathematics. Springer, New York.Google Scholar
  19. 19.
    Kosslyn, S.M. (1994): Image and Brain. Bradford, Cambridge.Google Scholar
  20. 20.
    Rolls E.T. (1987): Information Representation, Processing and Storage in the Brain: Analysis at the Single Neuron Level. In: Changeux, J.-P., Konishi, M. (Eds.): The Neural and Molecular Bases of Learning. Wiley, New York, 503–539.Google Scholar
  21. 21.
    Ullman, S. (1979): The Interpretation of Visual Motion. MIT Press, Cambridge.Google Scholar
  22. 22.
    Van Essen, D.C., Maunsell J.H. (1983): Hierarchical Organization and Functional Streams in the Visual Cortex. Trends in Neurosciences, 6, 370–375.CrossRefGoogle Scholar
  23. 23.
    Van Essen, D.C., Anderson C.H., Felleman, D.J. (1992): Information Processing in the Primate Visual System: An Integrated Systems Perspective. Science, 255, 419–423.Google Scholar
  24. 24.
    Talairach, J., Tournoux, D.P. (1988): Coplanar Stereotaxic Atlas of the Human Brain. Thieme, New York.Google Scholar
  25. 25.
    Mumford, D. (1991): On the Computational Architecture of the Neocortex I. Biological Cybernetics, 65, 135–145.CrossRefGoogle Scholar
  26. 26.
    Mumford, D. (1992): On the Computational Architecture of the Neocortex II. Biological Cybernetics, 66, 241–251.CrossRefGoogle Scholar
  27. 27.
    Kohonen, T. (1982): Self-Organizing Formation of Topologically Correct Feature Maps. Biological Cybernetics, 43, 59–69.MathSciNetCrossRefMATHGoogle Scholar
  28. 28.
    Kangas, J., Kohonen, T., Laaksonen, J. (1990): Variants of Self-Organizing Maps. IEEE Transactions on Neural Networks, 1, 93–99.CrossRefGoogle Scholar
  29. 29.
    Oja, E., Kaski, S. (Eds.) (1999): Kohonen Maps. Elesevier, Amsterdam.MATHGoogle Scholar
  30. 30.
    Fritzke, B. (1995): Growing Grid-A Self-Organizing Network with Constant Neighborhood Range and Adaption Strength. Neural Processing Letters, 5, 1–5.Google Scholar
  31. 31.
    Fritzke, B. (1995): Growing Self-Organizing Networks-Why? In: Proceedings of European Symposium on Artificial Neural Networks. D-Facto Publishers, Brussels, 61–72.Google Scholar
  32. 32.
    Bauer, H.-U., Villmann, T. (1997): Growing a Hypercubical Output Space in a Self-Organizing Feature Map. IEEE Transactions on Neural Networks, 2, 218–226.CrossRefGoogle Scholar
  33. 33.
    Martinetz, T., Schulten, K. (1991): A `Neural Gas’ Learns Topologies. In: Kohonen, T. et al. (Eds.): Artificial Neural Networks. North-Holland, Amsterdam, 397–402.Google Scholar
  34. 34.
    Fritzke, B. (1995): A Growing Neural Gas Network Learns Topologies. In: Tesauro G., Touretzky, D.S., Leen, T.K. (Eds.): Advances in Neural Information Processing Systems. MIT Press, Cambridge.Google Scholar
  35. 35.
    Seiffert U., Michaelis, B. (1998): Growing Multi-Dimensional Self-Organizing Maps. International Journal of Knowledge-Based Intelligent Engineering Systems, 2, 42–48.Google Scholar
  36. 36.
    Seiffert, U., Michaelis, B. (1998): Quasi-Four-Dimensional Neuroncube and its Application to Motion Estimation. In: Bulsari, A.B., de Canete, J.F., Kallio, S. (Eds.): Engineering Benefits from Neural Networks. SEA, Turku, 78–81.Google Scholar
  37. 37.
    Sommerkorn, G., Seifert, U., Surmeli, D., Herzog, A., Michaelis, B., Braun, K. (1997): Classification of 3-D Dendritic Spines Using Self-Organizing Maps. In: Smith, G.D. et al. (Eds.): Artificial Neural Nets and Genetic Algorithms. Series Computer Science. Springer, Vienna, 129–132.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Udo Seiffert

There are no affiliations available

Personalised recommendations