Using Neural Field Dynamics in the Context of Attentional Control (original) (raw)

Abstract

We present an application of dynamic neural fields for selection and tracking in the attentional control part of an active vision system. We propose a novel two-stage selection mechanism, in which the fields are used for the first selection stage. We discuss different variants, introducing 3D neural fields and systems of interconnected fields. The dynamics can be shown to achieve important goals in active vision like robust selection, multi-object tracking, and spatiotemporal integration.

We thank the DFG for their support on this research (Project ESAB-2 Me1289/3-2).

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. C. Koch and S. Ullman, “Shifts in selective visual attention: Towards the underlying neural circuitry,” Human Neurobiology, vol. 4, pp. 219–227, 1985.
    Google Scholar
  2. L. Itti and C. Koch, “(Feature combination strategies for saliency-based visual attention Systems,” Journal of Electronie Imaging, vol. 10, no. 1, 2001.
    Google Scholar
  3. F. Miau and L. Itti, “A neural model combining attentional orienting to object recognition: Preliminary explorations on the interplay between where and what,” in Proceedings IEEE Engineering in Medicine and Biology Society (EMBS), 2001.
    Google Scholar
  4. B. Olshausen, C. Anderson, and D. V. Essen, “A multiscale dynamic routing circuit for forming size-and position-invariant object representations,” Journal of Computational Neuroscience, vol. 2, no. 1, pp. 45–62, 1995.
    Article Google Scholar
  5. J. K. Tsotsos, S. Culhane, W. Wai, Y. Lai, N. Davis, and F. Nuflo, “Modelling visual attention via selective tuning,” Artificial Intelligence, vol. 78, pp. 507–545, 10 1995.
    Article Google Scholar
  6. F. H. Hamker, “Distributed competition in directed attention,” in Dynamische Perzeption (G. Baratoff and H. Neumann, eds.), pp. 39–44, 2000.
    Google Scholar
  7. G. Deco, Emergent Neural Computation Architectures, ch. Biased Competition Mechanism for Visual Attention in a Multimodular Neurodynamical System, pp. 114–126. 2001.
    Google Scholar
  8. S.-I. Amari, “Dynamics of Pattern formation in lateral inhibition type neural field,” BioZogicaZ Cybernetic, vol. 27, pp. 77–87, 1977.
    Article MATH MathSciNet Google Scholar
  9. K. Kopecz, “Neural field dynamics provide robust control of attentional resources,” in Aktives Sehen in technischen und natürlichen Systemen (B. Mertsching, ed.), pp. 137–144, 1996.
    Google Scholar
  10. M. Pauly, K. Kopecz, and R. Eckhorn, “Model of a fixation control network performs saccades, smooth pursuit, and provides the basis for segmentation of unknown objects in dynamic real-world scenes,” in Proceedings Workshop Dynamische Perzeption, 1998.
    Google Scholar
  11. A. Corradini, U. Braumann, H. Boehme, and H. Gross, “3d neural fields and steerable filters for tontour-based person localization,” in Proceedings of the Workshop of Virtual Intelligence-Dynamic Neural Networks (VI-DYNN’98), (Stockholm, Sweden), June 1998.
    Google Scholar
  12. G. Backer, B. Mertsching, and M. Bollmann, ‘(Data-and model-driven gaze control for an active vision system,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 12, pp. 1415–1429, 2001.
    Article Google Scholar
  13. G. Backer and B. Mertsching, “Integrating time and depth into the attentional control of an active vision system,” in Dynamische Perzeption. Workshop der GI-Fachgruppe 1.0.4 Bildverstehen, Ulm, November 2000 (G. Baratoff and H. Neumann, eds.), pp. 69–74, 2000.
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. IMA-Lab, Dept. of Computer Science, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany
    Gerriet Backer & Bärbel Mertsching

Authors

  1. Gerriet Backer
  2. Bärbel Mertsching

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

Backer, G., Mertsching, B. (2002). Using Neural Field Dynamics in the Context of Attentional Control. 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\_200

Download citation

Keywords

Publish with us