We describe an enhanced method for the selection of optimal sensor actions in a probabilistic state estimation framework. We apply this to the selection of optimal focal lengths for cameras with a variable motor zoom in a real-time visual object tracking task. The optimal camera action is determined by the expected state estimate entropy for each candidate action. Varying action costs are taken into account by predicting the entropy several steps into the future. Our contribution is the use of the sequential Kalman filter to deal transparently with a variable number of cameras, potential object loss in a subset of the cameras, and to reduce the calculation time through independent optimization.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-step active object tracking with entropy based optimal actions using the sequential Kalman filter


    Contributors:
    Deutsch, B. (author) / Niemann, H. (author) / Denzler, J. (author)


    Publication date :

    2005-01-01


    Size :

    134227 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-Step Active Object Tracking with Entropy Based Optimal Actions using the Sequential Kalman Filter

    Deutsch, B. / Niemann, H. / Denzler, J. | British Library Conference Proceedings | 2005




    Combined Algorithm with Modified Camshift and Kalman Filter for Multi-object Tracking

    Sun, K. / Liu, S.-r. | British Library Online Contents | 2009