3-D Visual Object Classification with Hierarchical Radial Basis Function Networks

  • F. Schwenker
  • H. A. Kestler
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 67)


In this chapter we present a 3-D visual object recognition system for an autonomous mobile robot. This object recognition system performs the following three tasks: Object localization in the camera images, feature extraction, and classification of the extracted feature vectors with hierarchical radial basis function (RBF) networks.


Support Vector Machine Feature Vector Radial Basis Function Support Vector Machine Classifier Camera Image 
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]
    Brooks, R. (1983), “Model-based three-dimensional interpreations of two-dimensional images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 5, pp. 140–149.CrossRefGoogle Scholar
  2. [2]
    Lowe, D. (1987), “Three-dimensional object recognition from single two-dimensional images,” Artificial Intelligence, vol. 31, pp. 355–395.CrossRefGoogle Scholar
  3. [3]
    Little, J., Poggio, T., and Gamble, E. (1988), “Seeing in parallel: The vision machine,” International Journal of Supercomputing Applications, vol. 2, pp. 13–28.CrossRefGoogle Scholar
  4. [4]
    Poggio, T. and Edelman, S. (1990), “A network that learns to recognize tree-dimensional objects,” Nature, vol. 343, pp. 263–266.CrossRefGoogle Scholar
  5. [5]
    Schiele, B. and Crowley, J. (1996), “Probabilistic object recognition using multidimensional receptive field histograms,” Proc. of the 13th Int. Conf. on Pattern Recognition, IEEE Computer Press, pp. 50–54.Google Scholar
  6. [6]
    Man, D. and Nishihara, H. (1978), “Representation and recognition of the spatial organization of three dimensional structure,” Proceedings of the Royal Society of London B, vol. 200, pp. 269–294.CrossRefGoogle Scholar
  7. [7]
    Man, D. (1982), Vision, Freeman, San Fransisco.Google Scholar
  8. [8]
    Ullman, S. (1996), High-level Vision. Object Recognition and Visual Cognition, The MIT Press, Cambridge.MATHGoogle Scholar
  9. [9]
    Basri, R. (1996), “Recognition by prototypes,” International Journal of Computer Vision, vol. 19, pp. 147–168.CrossRefGoogle Scholar
  10. [10]
    Edelman, S. and Duvdevani-Bar, S. (1997), “A model of visual recognition and categorization,” Phil. Trans. R. Soc. London B, vol. 352, pp. 1191–1202.CrossRefGoogle Scholar
  11. [11]
    Edelman, S. and Bülthoff, H. (1992), “Orientation dependence in the recognition of familiar and novel views of three-dimensional objects,” Vision Research, vol. 32, pp. 2385–2400.CrossRefGoogle Scholar
  12. [12]
    Bülthoff, H., Edelman, S., and Tarr, M. (1995), “How are three-dimensional objects represented in the brain?” Cerebal Cortex, vol. 5, pp. 247–260.CrossRefGoogle Scholar
  13. [13]
    Logothetis, N. and Scheinberg, D. (1996), “Visual object recognition,” Annual Review of Neuroscience, vol. 19, pp. 577–621.CrossRefGoogle Scholar
  14. [14]
    Mel, B. (1997), “SEEMORE: combining colour, shape, and texture histogramming in a neurally-inspired approach to visual object recognition,” Neural Computation, vol. 9, pp. 777–804.CrossRefGoogle Scholar
  15. [15]
    Zhu, S. and Yuille, A. (1996), “FORMS: aFlexible Object Recognition and Modeling System,” International Journal of Computer Vision, vol. 20, pp. 1–39.CrossRefGoogle Scholar
  16. [16]
    Murase, H. and Nayar, S. (1995), “Visual learning and recognition of 3D objects from appearance,” International Journal of Computer Vision, vol. 14, pp. 5–24.CrossRefGoogle Scholar
  17. [17]
    Lades, M., Vorbrtiggen, J., Buhmann, J., Lange, J., von der Mals-burg, C., Wirtz, R., and Konen, W. (1993), “Distortion invariant object recognition in the dynamic link architecture,” IEEE Transactions on Computers, vol. 42, pp. 300–311.CrossRefGoogle Scholar
  18. [18]
    Biederman, I. (1987), “Recognition by components: a theory of hu man image understanding,” Psychol. Review, vol. 94, pp. 115–147.CrossRefGoogle Scholar
  19. [19]
    ] Biederman, I. (1985), “Human image understanding: recent research and a theory computer vision,” Graphics and Image Processing, vol. 32, pp. 29–73.CrossRefGoogle Scholar
  20. [20]
    Itti, L., Koch, C., and Niebur, E. (1998), “A model of saliency-based visual attention for rapid scene analysis,” IEEE Transactions on Pattern Analysis, vol. 20, no. 11, pp. 1254–1259.CrossRefGoogle Scholar
  21. [21]
    Koch, C. and Ullman, S. (1985), “Shifts in selective visual attention: towards the underlying neural circuitry,” Human Neurobiology, vol. 4, pp. 219–227.Google Scholar
  22. [22]
    Niebur, E. and Koch, C. (1994), “A model for the neuronal implementation of selective visual attention based on temporal correlation among neurons,” Journal of Computational Neuroscience, vol. 1, pp. 141–158.CrossRefGoogle Scholar
  23. [23]
    Kestler, H., Simon, S., Baune, A., Schwenker, F., and Palm, G. (1999), “Object classification using simple, colour based visual attention and a hierarchical neural network for neuro-symbolic integration,” in Burgard, W., Christaller, T., and Cremers, A. (Eds.), KI-99: Advances in Artificial Intelligence, Springer Verlag, pp. 267279.Google Scholar
  24. [24]
    Smith, A.R. (1978), “Color gamut transform pairs,” in Phillips, R.L. (Ed.), 5th Annual Conf. on Computer Graphics and Interactive Techniques, ACM, New York, pp. 12–19.Google Scholar
  25. [25]
    Roth, M. and Freeman, W. (1995), “Orientation histograms for hand gesture recognition,” Technical Report 94–03, Mitsubishi Electric Research Laboratorys, Cambridge Research Center.Google Scholar
  26. [26]
    Broomhead, D. and Lowe, D. (1988), “Multivariable functional interpolation and adaptive networks,” Complex Systems, vol. 2, pp. 321–355.MathSciNetMATHGoogle Scholar
  27. [27]
    Micchelli, C. (1986), “Interpolation of scattered data: distance matrices and conditionally positive definite functions,” Constructive Approximation, vol. 2, pp. 11–22.MathSciNetMATHCrossRefGoogle Scholar
  28. [28]
    Light, W. (1992), “Some aspects of radial basis function approximation,” in Singh, S. (Ed.), Approximation Theory, Spline Functions and Applications, Kluwer, vol. 365 of Kluwer Mathematical and Physical Sciences Series, pp. 163–190.CrossRefGoogle Scholar
  29. [29]
    Powell, M.J.D. (1992), “The theory of radial basis function approximation in 1990,” in Light, W. (Ed.), Advances in Numerical Analysis, Oxford Science Publications, vol. II. pp. 105–210.Google Scholar
  30. [30]
    Park, J. and Sandberg, I.W. (1993), “Approximation and radial basis function networks,” Neural Computation, vol. 5, pp. 305–316.CrossRefGoogle Scholar
  31. [31]
    Poggio, T. and Girosi, F (1990), “Networks for approximation and learning,” Proceedings of the IEEE, vol. 78, pp. 1481–1497.CrossRefGoogle Scholar
  32. [32]
    Cristianini, N. and Shawe-Taylor, J. (2000), An introduction to support vector machines,Cambridge University Press.Google Scholar
  33. [33]
    Schölkopf, B., Burges, C., and Smola, A. (1998), Advances in Kernel Methods — Support Vector Learning,MIT Press.Google Scholar
  34. [34]
    Vapnik, V. (1998), Statistical Learning Theory,John Wiley and Sons.Google Scholar
  35. [35]
    Friedman, J. (1996), “Another approach to polychotomous classification,” Tech. Rep., Stanford University, Department of Statistics.Google Scholar
  36. [36]
    Kreßel, U. (1999), “Pairwise classification and support vector machines,” in Schölkopf, B., Burges, C., and Smola, A. (Eds.), Advances in Kernel Methods, The MIT Press, chap. 15. pp. 255–268.Google Scholar
  37. [37]
    Weston, J. and Watkins, C. (1998), “Multi-class support vector machines,” Tech. Rep. CSD-TR-98–04, Royal Holloway, University of London, Department of Computer Science.Google Scholar
  38. [38]
    Nadler, M. and Smith, E. (1992), Pattern Recognition Engineering,John Wiley and Sons.Google Scholar
  39. [39]
    Schwenker, F., Kestler, H.A., and Palm, G. (2000), “An algorithm for adaptive clustering and visualisation of highdimensional data sets,” in Riccia, G., Kruse, R., and Lenz, H.J. (Eds.), Computational Intelligence in Data Mining, Springer, pp. 127–140.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • F. Schwenker
  • H. A. Kestler

There are no affiliations available

Personalised recommendations