A number of recent systems for unsupervised feature-based learning of object models take advantage of co-occurrence: broadly, they search for clusters of discriminative features that tend to coincide across multiple still images or video frames. An intuition behind these efforts is that regularly co-occurring image features are likely to refer to physical traits of the same object, while features that do not often co-occur are more likely to belong to different objects. In this paper we discuss a refinement to these techniques in which multiple segmentations establish meaningful contexts for co-occurrence, or limit the spatial regions in which two features are deemed to co-occur. This approach can reduce the variety of image data necessary for model learning and simplify the incorporation of less discriminative features into the model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video


    Contributors:


    Publication date :

    2005-01-01


    Size :

    320711 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object segmentation using feature based conditional morphology

    Hamid, M.R. / Baloch, A. / Bilal, A. et al. | IEEE | 2003


    Object Segmentation Using Feature Based Conditional Morphology

    Hamid, M. / Baloch, A. / Bilal, A. et al. | British Library Conference Proceedings | 2003



    Video Object Segmentation Using Eulerian Region-Based Active Contours

    Jehan-Besson, S. / Barlaud, M. / Aubert, G. et al. | British Library Conference Proceedings | 2001


    Video object segmentation using Eulerian region-based active contours

    Jehan-Besson, S. / Barlaud, M. / Aubert, G. | IEEE | 2001