Objects often constitute the desired level of access for browsing and retrieval in video databases. We present an approach to create links between video segments that contain objects of interest, based on video structuring, object definition, and stochastic localization in the video structure. Localization is formulated in the metric mixture model framework, which allows for the joint probabilistic modeling of a (user-defined) set of color appearance exemplars and their geometric transformations. Candidate configurations are drawn from a prior distribution using importance sampling, guiding the search towards regions of the configuration space likely to contain the true configuration, thus avoiding exhaustive processing, and evaluated using Bayes' rule. Experimental results on a small database of real colored objects extracted from home videos, with variations of scale and pose across video shots, show promising performance of the method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object localization in metric spaces for video linking


    Contributors:


    Publication date :

    2002-01-01


    Size :

    502234 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object Localization in Metric Spaces for Video Linking

    Gatica-Perez, D. / Sun, M.-T. | British Library Conference Proceedings | 2002


    Localization performance metric

    DUENAS ARANA GUILLERMO / KAISER NATHANIEL JON / REBSAMEN BRICE | European Patent Office | 2025

    Free access

    Depths in random recursive metric spaces

    Colin Desmarais (Faculty of Mathematics, University of Vienna) | BASE | 2024

    Free access

    Visual comfort assessment metric based on salient object motion information in stereoscopic video

    Jung, Y.J. / Lee, S.-i. / Sohn, H. et al. | British Library Online Contents | 2012


    Colour Perceptual Video Quality Metric

    Ong, E. / Lin, W. / Lu, Z. et al. | British Library Conference Proceedings | 2005