Local image features or interest points provide compact and abstract representations of patterns in an image. We propose to extend the notion of spatial interest points into the spatio-temporal domain and show how the resulting features often reflect interesting events that can be used for a compact representation of video data as well as for its interpretation. To detect spatio-temporal events, we build on the idea of the Harris and Forstner interest point operators and detect local structures in space-time where the image values have significant local variations in both space and time. We then estimate the spatio-temporal extents of the detected events and compute their scale-invariant spatio-temporal descriptors. Using such descriptors, we classify events and construct video representation in terms of labeled space-time points. For the problem of human motion analysis, we illustrate how the proposed method allows for detection of walking people in scenes with occlusions and dynamic backgrounds.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Space-time interest points


    Beteiligte:
    Laptev, (Autor:in) / Lindeberg, (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    1052086 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Space-time Interest Points

    Laptev, I. / Lindeberg, T. / IEEE | British Library Conference Proceedings | 2003


    On Space-Time Interest Points

    Laptev, I. | British Library Online Contents | 2005


    Image Matching Using Generalized Scale-Space Interest Points

    Lindeberg, T. | British Library Online Contents | 2015


    Time to contact estimation using interest points

    Muller, Dennis / Pauli, Josef / Nunn, Christian et al. | IEEE | 2009


    Interesting Interest Points

    Aanæs, H. / Dahl, A. L. / Steenstrup Pedersen, K. | British Library Online Contents | 2012