Models for motion detection with artificial neural networks are inspired in physiological data of simple visual systems. Local speed estimation is a problem that involves more complicated architecture than a single lateral connection. We proposed an extension of these pioneer models. It considers bigger receptive fields that provide a larger zone of influence from receptors, allowing speed estimation on a wide range of velocities. The essence of this neural model is to estimate local speed from comparison between edge detection at the current position and delayed activities of neighboring input receptive fields.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A connectionist model for local speed estimation


    Contributors:
    Vico, F.J. (author) / Garrido, F.J. (author) / Sandoval, F. (author) / Leibovic, N. (author)


    Publication date :

    1994-01-01


    Size :

    352149 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Connectionist Model for Local Speed Estimation

    Vico, F. J. / Garrido, F. J. / Sandoval, F. et al. | British Library Conference Proceedings | 1994


    Local constraint integration in a connectionist model of stereo vision

    Stewart, Charles V. / Dyer, Charles R. | TIBKAT | 1987


    Toward a modular connectionist model of local chlorophyll concentration from satellite images

    Trentin, E. / Magnoni, L. / Andronico, A. | Tema Archive | 2003


    A connectionist model for dynamic control

    Whitfield, Kevin C. / Goodall, Sharon M. / Reggia, James A. | NTRS | 1989


    Hybrid Connectionist Systems

    Jain | Online Contents | 1995