In this paper, we address the problem of motion recognition using event-based local motion representations. We assume that similar patterns of motion contain similar events with consistent motion across image sequences. Using this assumption, we formulate the problem of motion recognition as a matching of corresponding events in image sequences. To enable the matching, we present and evaluate a set of motion descriptors that exploit the spatial and the temporal coherence of motion measurements between corresponding events in image sequences. As the motion measurements may depend on the relative motion of the camera, we also present a mechanism for local velocity adaptation of events and evaluate its influence when recognizing image sequences subjected to different camera motions. When recognizing motion patterns, we compare the performance of a nearest neighbor (NN) classifier with the performance of a support vector machine (SVM). We also compare event-based motion representations to motion representations in terms of global histograms. A systematic experimental evaluation on a large video database with human actions demonstrates that (i) local spatio-temporal image descriptors can be defined to carry important information of space-time events for subsequent recognition, and that (ii) local velocity adaptation is an important mechanism in situations when the relative motion between the camera and the interesting events in the scene is unknown. The particular advantage of event-based representations and velocity adaptation is further emphasized when recognizing human actions in unconstrained scenes with complex and non-stationary backgrounds. ; QC 20100525 QC 20111115


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Local velocity-adapted motion events for spatio-temporal recognition


    Beteiligte:
    Laptev, Ivan (Autor:in) / Caputo, Barbara (Autor:in) / Schüldt, Christian (Autor:in) / Lindeberg, Tony (Autor:in)

    Erscheinungsdatum :

    2007-01-01


    Anmerkungen:

    Scopus 2-s2.0-35548930762



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Local velocity-adapted motion events for spatio-temporal recognition

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


    Missile-tracking algorithm using target-adapted spatio-temporal wavelets

    Mujica, F. / Leduc, J.P. / Smith, M.J.T. et al. | Tema Archiv | 1997


    Image acquisition using aperture control adapted to spatio-temporal properties

    Huber, R. / Nowak, C. / Spatzek, B. | British Library Online Contents | 2004


    Action recognition via spatio-temporal local features: A comprehensive study

    Zhen, X. / Shao, L. | British Library Online Contents | 2016


    Learning spatio-temporal dependency of local patches for complex motion segmentation

    Xu, J. / Yuan, J. / Wu, Y. | British Library Online Contents | 2011