This paper investigates the pedestrian tracking problem with short-term occlusion and proposes an adaptive UpdateNet (AUNet) framework as the improvement over state-of-the-art. We find that the templates in the original UpdateNet framework are usually ‘corrupted’ when the tracking target is temporarily occluded, and hence, it is very difficult to recover when the target reappears in the following image frames. We therefore construct an evaluation network, which determines whether the current input image frame is occluded or not, and hence adapt the current image frame's influence in the update process of the object tracking template. In this way, we are able to successfully maintain a good set of templates, and hence improve the network's tracking performance when facing short-term occlusions. Experimental results with the canonical dataset (OTB100) and a real world use case show the superior tracking performance of AUNet over state-of-the-art.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AUNet: Adaptive UpdateNet for Dynamic Pedestrian Tracking with Short-Term Occlusion


    Beteiligte:
    Shen, Lyuyu (Autor:in) / Guo, Hongliang (Autor:in) / Bai, Yechao (Autor:in) / Ang, Marcelo (Autor:in) / Rus, Daniela (Autor:in)


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    2480261 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Occlusion-Robust Pedestrian Tracking in Crowded Scenes

    Gastel, Jeroen S. van / Zwemer, Matthijs H. / Wijnhoven, Rob G. J. et al. | IEEE | 2015


    OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking

    Gao, Jianjun / Wang, Yi / Yap, Kim-Hui et al. | IEEE | 2025


    Occlusion Robust Adaptive Template Tracking

    Nguyen, H. / Worring, M. / van den Boomgaard, R. et al. | British Library Conference Proceedings | 2001


    Occlusion robust adaptive template tracking

    Nguyen, H.T. / Worring, M. / van den Boomgaard, R. | IEEE | 2001


    Occlusion aware sensor fusion for early crossing pedestrian detection

    Palffy, Andras / Kooij, Julian F. P. / Gavrila, Dariu M. | IEEE | 2019