We address the problem of interpreting visual surveillance data by learning appropriate spatio-temporal subspaces of active image regions caused by scene activities. We focus on identifying regions of sustained change for recognising key stages of a visual behaviour. Our behaviour representation is based on the asynchrony or delay patterns of occurrence among local events which need not be spatially connected. We use an automatic normalised cut structure discovery algorithm with a hybrid similarity criterion for simultaneously identifying relevant spatio-temporal subspaces and clustering similar behaviour patterns in those subspaces. We compare the automatically discovered classes with conceptual classes of behaviours in a semi-constrained "shopping" scenario.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On the binding mechanism of synchronised visual events


    Contributors:
    Ng, J. (author) / Shaogang Gong, (author)


    Publication date :

    2002-01-01


    Size :

    526645 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On the Binding Mechanism of Synchronized Visual Events

    Ng, J. / Gong, S. | British Library Conference Proceedings | 2002


    Cost-effective solution to synchronised audio-visual data capture using multiple sensors

    Lichtenauer, J. / Shen, J. / Valstar, M. et al. | British Library Online Contents | 2011


    CAE-Mastermodels - the cornerstone of synchronised

    Pohl, Thorsten | Tema Archive | 2010


    Synchronised shift device for a vehicle

    HEINDL RICHARD / KNOBLOCH FLORIAN | European Patent Office | 2016

    Free access

    Augumenting GPS Using Synchronised Pseudolite Technology

    Subramanian, Hariram / Rajendran, Ramya | AIAA | 2004