An approach to active vision based on information theory and statistical mechanics is presented. Density of entropy production measured along a spatio-chromatic diffusion of a colour image is used to build a conspicuity map of the image. The map is successively given as input to a dynamic neural network in order to drive a focus-of-attention scanpath.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An information-theoretic approach to active vision


    Contributors:
    Boccignone, G. (author) / Ferraro, M. (author) / Caelli, T. (author)


    Publication date :

    2001-01-01


    Size :

    645403 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    An Information-Theoretic Approach to Active Vision

    Boccignone, G. / Ferraro, M. / Caelli, T. et al. | British Library Conference Proceedings | 2001


    An Information-Theoretic Active Localization Approach during Relative Circumnavigation in Orbit

    Kontitsis, Michail / Tsiotras, Panagiotis / Theodorou, Evangelos | AIAA | 2016


    Particle filter based information-theoretic active sensing

    Ryan, Allison / Hedrick, J.Karl | Tema Archive | 2010


    Information-Theoretic Active Polygons for Unsupervised Texture Segmentation

    Unal, G. / Yezzi, A. / Krim, H. | British Library Online Contents | 2004