A new exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models and problems with changes of topology. Using exemplars in place of a parameterized model poses several challenges, addressed here with what we call the "Metric Mixture" (M/sup 2/) approach. The M/sup 2/ model has several valuable properties. Principally, it provides alternatives to standard learning algorithms by allowing the use of metrics that are not embedded in a vector space. Secondly, it uses a noise model that is learned from training data. Lastly, it eliminates any need for an assumption of probabilistic pixelwise independence. Experiments demonstrate the effectiveness of the M/sup 2/ model in two domains tracking walking people using chamfer distances on binary edge images and tracking mouth movements by means of a shuffle distance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Probabilistic tracking in a metric space


    Beteiligte:
    Toyama, K. (Autor:in) / Blake, A. (Autor:in)


    Erscheinungsdatum :

    2001-01-01


    Format / Umfang :

    999131 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Probabilistic Tracking in a Metric Space

    Toyama, K. / Blake, A. / IEEE | British Library Conference Proceedings | 2001


    Probabilistic Tracking with Exemplars in a Metric Space

    Toyama, K. / Blake, A. | British Library Online Contents | 2002



    Dempster-Schafer Inspired Association Framework and Tracking Metric for Space Objects

    Murphy, Timothy S. | British Library Conference Proceedings | 2020


    Developing a Probabilistic Metric of Midair Collision Risk

    Knecht, William R. | Online Contents | 1997