• DocumentCode
    2534423
  • Title

    Collision prediction via the CNN Universal Machine

  • Author

    Gál, V. ; Roska, T.

  • Author_Institution
    Comput. & Autom. Inst., Hungarian Acad. of Sci., Budapest, Hungary
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    105
  • Lastpage
    110
  • Abstract
    We present an analogic CNN algorithm that estimates the time to an impending collision between an approaching object and the observer. Calculation is based on a context insensitive method, which is well known in neurobiology, using only two specific cues of the expanding two-dimensional image of the looming object
  • Keywords
    analogue processing circuits; cellular neural nets; image processing; neural chips; physiological models; visual perception; CNN Universal Machine; analogic CNN algorithm; collision prediction; context insensitive method; expanding two-dimensional image; Animals; Cellular neural networks; Detectors; Equations; Geometrical optics; Image edge detection; Object detection; Optical arrays; Pixel; Turing machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cellular Neural Networks and Their Applications, 2000. (CNNA 2000). Proceedings of the 2000 6th IEEE International Workshop on
  • Conference_Location
    Catania
  • Print_ISBN
    0-7803-6344-2
  • Type

    conf

  • DOI
    10.1109/CNNA.2000.876829
  • Filename
    876829