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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Police Gesture Recognition by Pose Graph Convolutional Networks


    Contributors:
    Fang, Zhijie (author) / Zhang, Wuqiang (author) / Guo, Zijie (author) / Zhi, Rong (author) / Wang, Baofeng (author) / Flohr, Fabian (author)


    Publication date :

    2020-10-19


    Size :

    2092879 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    TRAFFIC POLICE GESTURE RECOGNITION BY POSE GRAPH CONVOLUTIONAL NETWORKS

    Fang, Zhijie / Zhang, Wuqiang / Guo, Zijie et al. | British Library Conference Proceedings | 2020





    Traffic Police Gesture Recognition Based on Openpose and GRU

    Wang, Dengwen / Wang, Wangmeng / Chen, Yanbing et al. | IEEE | 2022