A method for learning, tracking, and recognizing human gestures using a view-based approach to model articulated objects is presented. Objects are represented using sets of view models, rather than single templates. Stereotypical space-time patterns, i.e., gestures, are then matched to stored gesture patterns using dynamic time warping. Real-time performance is achieved by using special purpose correlation hardware and view prediction to prune as much of the search space as possible. Both view models and view predictions are learned from examples. Results showing tracking and recognition of human hand gestures at over 10 Hz are presented.<>


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Space-time gestures


    Beteiligte:
    Darrell, T. (Autor:in) / Pentland, A. (Autor:in)


    Erscheinungsdatum :

    01.01.1993


    Format / Umfang :

    484445 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Florid gestures

    British Library Online Contents | 1992


    INTELLIGENT TUTORIAL FOR GESTURES

    OCHIAI YUICHI / NAGATA KATSUMI / SASAKI AKIRA | Europäisches Patentamt | 2017

    Freier Zugriff

    Intelligent tutorial for gestures

    OCHIAI YUICHI / NAGATA KATSUMI / SASAKI AKIRA | Europäisches Patentamt | 2018

    Freier Zugriff

    Everyday life and mnemonic gestures

    Ana Sofia Almeida | DOAJ | 2023

    Freier Zugriff

    Everyday life and mnemonic gestures

    Almeida, Ana Sofia | DataCite | 2023

    Freier Zugriff