The mean-shift algorithm is an efficient technique for tracking 2D blobs through an image. Although the scale of the mean-shift kernel is a crucial parameter, there is presently no clean mechanism for choosing or updating scale while tracking blobs that are changing in size. We adapt Lindeberg's (1998) theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking. We show that a difference of Gaussian (DOG) mean-shift kernel enables efficient tracking of blobs through scale space. Using this kernel requires generalizing the mean-shift algorithm to handle images that contain negative sample weights.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Mean-shift blob tracking through scale space


    Beteiligte:
    Collins, R.T. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    485304 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Mean-Shift Blob Tracking through Scale Space

    Collins, R. / IEEE | British Library Conference Proceedings | 2003


    Vehicle Classification and Violation Detection on Traffic Light Area using BLOB and Mean-Shift Tracking Method

    Bachtiar, Mochamad Mobed / Rahman Mawardi, Achmad / Anom Besari, Adnan Rachmat | IEEE | 2020


    Scale-space color blob and ridge detection

    Khanina, N. A. / Semeikina, E. V. / Yurin, D. V. | British Library Online Contents | 2012


    Color Blob and line detection in scale-space

    Khanina, N. A. / Semeikina, E. V. / Yurin, D. V. | British Library Online Contents | 2011


    Blob tracking technique to range image segmentation

    D'Cunha, Ivan / Alvertos, Nicolas | SPIE | 1994