Tracking with deformable contours in a filtering framework requires a dynamical model for prediction. For any given application, tracking is improved by having an accurate model, learned from training data. We develop a method for learning dynamical models from training sequences, explicitly taking account of the fact that training data are noisy measurements and not true states. By introducing an 'augmented-state smoothing filter' we show how the technique of Expectation-Maximisation can be applied to this problem, and show that the resulting algorithm produces more robust and accurate tracking.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning dynamical models using expectation-maximisation


    Contributors:
    North, B. (author) / Blake, A. (author)


    Publication date :

    1998-01-01


    Size :

    849259 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Dynamical Models Using Expectation-Maximisation

    North, B. / Blake, A. / IEEE; Computer Society | British Library Conference Proceedings | 1998


    Using expectation-maximisation to learn dynamical models from visual data

    North, B. / Blake, A. | British Library Online Contents | 1999


    Image Segmentation via Multiresolution Diffused Expectation-Maximisation

    Boccignone, G. / Caggiano, V. / Napoletano, P. et al. | British Library Conference Proceedings | 2005


    Image segmentation via multiresolution diffused expectation-maximisation

    Boccignone, G. / Caggiano, V. / Napoletano, P. et al. | IEEE | 2005


    An expectation-maximisation framework for segmentation and grouping

    Robles-Kelly, A. / Hancock, E. R. | British Library Online Contents | 2002