This paper addresses the fundamental problem of automatically discovering an unknown moving deformable object in a monocular video sequence. No prior model of the object is used; it is only assumed that the object is composed of a set of apparently rigid parts that are not necessarily visible simultaneously, making it possible to circumvent the typical constraint of model initialization. A set of rigid parts describing the object is incrementally extracted in a modeling-tracking loop with reinforced memory. In this framework, low-level segmentation is considered as a necessary but non reliable process that helps initiating hypotheses. Motion-based layer segmentation from feature points and edges is applied only when and where no modeled parts can be tracked. Using the quantity of motion measure, it is further shown how to deal with temporal scale. The interest for this approach in applications such as human tracking is demonstrated for a set of various sequences including a rapidly evolving shape.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Incremental discovery of object parts in video sequences


    Contributors:
    Drouin, S. (author) / Hebert, P. (author) / Parizeau, M. (author)


    Publication date :

    2005-01-01


    Size :

    596510 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Incremental discovery of object parts in video sequences

    Drouin, S. / Hebert, P. / Parizeau, M. | British Library Online Contents | 2008


    Incremental Discovery of Object Parts in Video Sequences

    Drouin, S. / Hebert, P. / Parizeau, M. et al. | British Library Conference Proceedings | 2005


    Incremental recognition of traffic situations from video image sequences

    Haag, M. / Nagel, H.-H. | British Library Online Contents | 2000


    Video retrieval based on object discovery

    Liu, D. / Chen, T. | British Library Online Contents | 2009


    Unsupervised learning of object features from video sequences

    Leordeanu, M. / Collins, R. | IEEE | 2005