The 3D perception system functions as one of the core components for the safe operation of autonomous-rail rapid tram. Addressing the limitations of LiDAR systems used for autonomous-rail rapid tram in complex urban environments, such as challenges in perceiving distant objects, insensitivity to color, and potential failure, this paper proposes a pure-vision monocular 3D perception system for autonomous-rail rapid tram. Comprising data preprocessing, model training and model deployment, this vision-based scheme with a full coverage from data collection to on-board deployment enables the 3D perception of obstacles around autonomous-rail rapid tram, thereby improving the operational reliability in complex urban environments. The test results based on the autonomous-rail rapid transit dataset and Waymo open dataset show that the system can effectively perceive the complex road scenes in autonomous-rail rapid transit, achieving a final 3D average precision (AP) of 0.53, reasoning a single-frame of image about 56 ms, and meeting the real-time requirements of autonomous-rail rapid tram for the obstacle perception algorithm.


    Access

    Download


    Export, share and cite



    Title :

    Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram


    Contributors:
    WANG Zeyuan (author) / LIN Jun (author) / YUAN Xiwen (author) / XU Yanghan (author) / YUE Wei (author) / XIONG Qunfang (author)


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Research on Longitudinal Intelligent Control of Autonomous-rail Rapid Tram

    TANG Liang / SHEN Mengyu / XIAO Lei | DOAJ | 2023

    Free access

    Research on Lateral Control of Autonomous Driving for Autonomous-rail Rapid Tram

    LIU Xiaocong / ZHOU Sheng / XIAO Lei et al. | DOAJ | 2023

    Free access

    Research on Key Technologies of Virtual Coupling Control System for Autonomous-rail Rapid Tram

    HUANG Qiang / YUAN Xiwen / HU Yunqing et al. | DOAJ | 2023

    Free access

    Hydrogen Hybrid Power System and Its Control Strategy for Autonomous-rail Rapid Tram

    YU Zhuo / XIAO Lei / XIE Jun et al. | DOAJ | 2023

    Free access

    RAIL-BOUND TRAM

    LASKOVSKIJ MANFRED | European Patent Office | 2019

    Free access