At present, the auto-driving technology is becoming more and more mature, but how the auto-driving car recognizes the traffic police gesture information under special road conditions has become an urgent problem to be solved. In this paper, based on transfer learning, eight kinds of gesture signals of Chinese traffic police are recognized. The dataset is "Chinese Traffic Police Gesture Dataset"(CTPGD). The total loss value is 0.2174, and good results have been achieved.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognition of Traffic Police Gestures Based on Transfer Learning


    Contributors:


    Publication date :

    2023-09-22


    Size :

    3944684 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English






    Traffic Police Gesture Recognition Based on Openpose and GRU

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


    Traffic police gesture recognition and judgment based on Openpose

    Zhu, Qingxiang / Dang, Xueming | SPIE | 2024