Monocular online map segmentation is of great significance to mapless autonomous driving, and the core step is the View Transformation Module (VTM), which is used to transfer feature from the image perspective to the Bird-Eye-View (BEV). Most existing methods directly draw from the field of 3D object perception, either projecting 2D features into 3D space based on depth estimation, or projecting 3D coordinates into 2D images to query corresponding features, while ignoring the geometry and semantics from the ground surface. In this paper, we proposed a ground aware forward-backward view transformation module. The forward projection is used to generate the initial sparse BEV features and the geometric and semantic prior information of the ground surface. The backward module refines the BEV features based on the geometric and semantic priors, thereby improving the accuracy of map segmentation. In addition, the data partitioning of most previous related works has the problem of data leakage, so we repartitioned and experimented on the nuScense data set to conduct a fair evaluation. Experimental results demonstrate that our method achieves the highest accuracy on the test set. Code will be released at https://github.com/Brickzhuantou/MonoBEVseg.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    GAFB-Mapper: Ground aware Forward-Backward View Transformation for Monocular BEV Semantic Mapping


    Contributors:
    Zhu, Jiangtong (author) / Yuan, Yibo (author) / Yin, Zhuo (author) / Zhou, Yang (author) / Li, Shizhen (author) / Fang, Jianwu (author) / Xue, Jianru (author)


    Publication date :

    2024-06-02


    Size :

    1711535 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    OCCUPANCY PREDICTION USING FORWARD-BACKWARD VIEW TRANSFORMATION

    LI ZHIQI / YU ZHIDING / AUSTIN DAVID et al. | European Patent Office | 2024

    Free access

    Instance-Aware Monocular 3D Semantic Scene Completion

    Xiao, Haihong / Xu, Hongbin / Kang, Wenxiong et al. | IEEE | 2024


    Fast semi-dense 3D semantic mapping with monocular visual SLAM

    Li, Xuanpeng / Ao, Huanxuan / Belaroussi, Rachid et al. | IEEE | 2017


    Monocular 3D Ray-Aware RPN For Roadside View Object Detection

    Zhang, Caiji / Tian, Bin / Sun, Yang et al. | IEEE | 2023


    Road Curb Detection and Localization With Monocular Forward-View Vehicle Camera

    Panev, Stanislav / Vicente, Francisco / De la Torre, Fernando et al. | IEEE | 2019