We address the problem of image sequence analysis by classification. As an example we consider the recognition of walking pedestrians in complex traffic scenes. Polynomial support vector machines are applied to complete image sequences, representing extremely high-dimensional input patterns, and to reduced feature sets obtained by standard 'global' principal component analysis. These approaches are compared to the adaptable time delay neural network (ATDNN) algorithm based on receptive fields that perform a 'local' spatio-temporal processing of the image sequence, generating feature sets that are classified by polynomial support vector-machines in an extended version of the ATDNN algorithm. The computational complexity of the local approaches is up to two and the memory demand up to four orders of magnitude lower than the corresponding values for the global approaches while the recognition performance of the local approaches is even higher than that of the global ones.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pedestrian recognition by classification of image sequences - global approaches vs. local spatio-temporal processing


    Beteiligte:
    Wohler, C. (Autor:in) / Kressel, U. (Autor:in) / Anlaur, J.K. (Autor:in)


    Erscheinungsdatum :

    2000


    Format / Umfang :

    5 Seiten, 16 Quellen




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    STGT: FORECASTING PEDESTRIAN MOTION USING SPATIO-TEMPORAL GRAPH TRANSFORMER

    Syed, Arsal / Morris, Brendan | British Library Conference Proceedings | 2021



    Local velocity-adapted motion events for spatio-temporal recognition

    Laptev, I. / Caputo, B. / Schuldt, C. et al. | British Library Online Contents | 2007


    Vehicle recognition based on spatio-temporal image analysis

    Hirahara, K. / Ikeuchi, K. | IEEE | 2004


    Detection of distant eye-contact using spatio-temporal pedestrian skeletons

    Hata, Ryusei / Deguchi, Daisuke / Hirayama, Takatsugu et al. | IEEE | 2022