Gestures from traffic police give the authorized information, especially in some urgent situation. Thus, understanding of traffic police instruction accurately and promptly is particularly crucial for the automated driving system. However, this task is a great challenge not only because of the dynamic and diversity characteristics of the human gesture, but also the high requirement for real-time performance in each frame. We propose an online activity recognition method based on pose estimation and Graph Convolutional Networks (GCN) to recognize the traffic police gesture in frame level. The main contribution in this work is the development of an online framework based on graph convolutional networks for traffic police recognition. Our approach obtained the state-of-the-art results on Traffic Police Gesture Recognition (TPGR) dataset.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic Police Gesture Recognition by Pose Graph Convolutional Networks


    Beteiligte:
    Fang, Zhijie (Autor:in) / Zhang, Wuqiang (Autor:in) / Guo, Zijie (Autor:in) / Zhi, Rong (Autor:in) / Wang, Baofeng (Autor:in) / Flohr, Fabian (Autor:in)


    Erscheinungsdatum :

    2020-10-19


    Format / Umfang :

    2092879 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Traffic police gesture recognition method based on cloud communication and support vector machine

    YANG ZHONG / SONG AIGUO / XU BAOGUO et al. | Europäisches Patentamt | 2020

    Freier Zugriff


    Traffic direction gesture recognition

    SIVARAMAN SAYANAN V | Europäisches Patentamt | 2021

    Freier Zugriff

    TRAFFIC DIRECTION GESTURE RECOGNITION

    SIVARAMAN SAYANAN V | Europäisches Patentamt | 2018

    Freier Zugriff