• DocumentCode
    2753661
  • Title

    Using neural dynamics to switch attention

  • Author

    Vitay, Julien ; Rougier, Nicolas

  • Author_Institution
    Loria, Vandoeuvre-les-Nancy, France
  • Volume
    5
  • fYear
    2005
  • fDate
    31 July-4 Aug. 2005
  • Firstpage
    2891
  • Abstract
    We present a distributed and dynamic model of visual attention based on the continuum neural field theory that allows to sequentially focusing salient locations in an image. A working memory system ensures that the corresponding objects are only focused once, even if they are moving around, such that the visual search is efficient. The model has been implemented on a robotic platform in order to search for natural objects such as fruits.
  • Keywords
    neural nets; object recognition; robot vision; visual perception; continuum neural field theory; memory system; neural dynamics; robotics; switch attention; visual attention; visual search; Electronic mail; Filters; Focusing; Layout; Neurons; Parallel architectures; Robot sensing systems; Switches; Target recognition; Visual perception;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
  • Print_ISBN
    0-7803-9048-2
  • Type

    conf

  • DOI
    10.1109/IJCNN.2005.1556384
  • Filename
    1556384