Visual Person Localization with Dynamic Neural Fields: Towards a Gesture Recognition System

  • Andrea Corradini
  • Ulf-Dietrich Braumann
  • Anja Brakensiek
  • Markus Krabbes
  • Hans-Joachim Boehme
  • Horst-Michael Gross
Conference paper
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

For any visually-based interaction between persons and acting systems within a real-world environment the localization of a user by the system is a necessary condition. The presented work deals with this visual localization problem of a user concretely referred to the autonomous mobile robot system MILVA of our department. Since this system is applied under real-world conditions especially for the localization some proper techniques are needed which have an adequate robustness. In our opinion, this requires the combination of several components of saliency towards a multi-cue approach, consisting of structure- and color-based features [2].

This paper introduces one of them: the localization based on a typical shape of contour. A simple contour shape prototype model consists of an arrangement of oriented filters doing a piecewise approximation of the upper shape (head, shoulder) of a frontally aligned person. Applying such filter arrangement in a multiresolution manner, this leads to a robust localization of frontally aligned persons even in depth. The central problem of selecting the most promising (salient) image region is treated by means of a three-dimensional dynamic neural field performing a dynamic winner-take-all process (WTA, [1,6]).

After a successful localization of a person one can start a more detailed analysis of the gesture’s meaning: besides the recognition of static gestures we also concentrate on the acquisition and later the recognition of dynamic gestures.

Keywords

Attenuation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Amari S.: Dynamics of Pattern Formation in Lateral-Inhibition Type Neural Fields. Biol. Cyb., 27:77–87, 1977.MathSciNetMATHCrossRefGoogle Scholar
  2. [2]
    Boehme H.-J., Braumann U.-D., Brakensiek A., Corradini A., Krabbes M. and Gross H.-M.: User Localization for Visually-based Human-Machine-Interaction, In Proc. of the Third IEEE Int. Conf. on Automatic Face and Gesture Recognition, pp. 486–491, 1998Google Scholar
  3. [3]
    Davis, J. W. and Bobick, A. F.: The Representation and Recognition of Action Using Temporal Templates. In Proc. of the IEEE Computer Society Conference on Comp. Vis. and Patt. Rec., pp. 928–934, 1997.Google Scholar
  4. [4]
    Jähne, B.: Digital Image Processing Springer-Verlag, 1995.Google Scholar
  5. [5]
    Jones, J. P. and Palmer, L. A.: An Evaluation of the Two-Dimensional Gabor Filter Model of Simple Receptive Fields in Cat Striate Cortex. J. Neurophysiol., 58(6):1233–1258, 1987.Google Scholar
  6. [6]
    Kaski, S. and Kohonen, T.: WTA Networks for Physiological Models of Competitive Learning. Neural Networks, 7(6/7):973–984, 1994.MATHCrossRefGoogle Scholar
  7. [7]
    Koenderink, J. J. and v. Doorn, A. J.: Receptive Field Families. Biol. Cyb., 63:291–297, 1990.MATHCrossRefGoogle Scholar
  8. [8]
    Koffka, K.: Principles of the Gestalt Psychology. Brace & World, 1935.Google Scholar
  9. [9]
    Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., and Poggio, T.: Pedestrian Detection Using Wavelet Templates. In Proc. of the IEEE Computer Society Conference on Comp. Vis. and Patt. Rec., pp. 193–199, 1997.Google Scholar
  10. [10]
    Reichardt, W., Poggio, T., and Hausen, K.: Figure-Ground Discrimination by Relative Movement in the Visual System of the Fly — Part II: Towards a Neural Circuitry. Biol Cyb., 46(suppl.):1–30, 1983.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1999

Authors and Affiliations

  • Andrea Corradini
    • 1
  • Ulf-Dietrich Braumann
    • 1
  • Anja Brakensiek
    • 1
  • Markus Krabbes
    • 1
  • Hans-Joachim Boehme
    • 1
  • Horst-Michael Gross
    • 1
  1. 1.Department of NeuroinformaticsTechnical University of IImenauIlmenauGermany

Personalised recommendations