This study proposed a method that integrates multi-view image processing, depth estimation, and point cloud generation to accurately reconstruct a 3D model of a rail. The method is tested by positioning two webcams on the left and right sides of the rail and capturing three images of the entire rail. These images are combined into a panorama using image stitching techniques. Depth estimation is then performed using Monocular Depth Estimation, followed by background separation using Mask R-CNN to isolate the rail. The 3D model is reconstructed through 3D Reconstruction, and its quality is evaluated using an accuracy assessment. The resulting 3D model of the rail demonstrated an accuracy of 84.56% when compared to the ground truth, with the rail head 99.87%, the rail web 65.67%, and the rail foot 72.66%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    3D Reconstruction of Steel Rail using Multi-view Cameras and Mask R-CNN




    Publication date :

    2025-03-05


    Size :

    1107459 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Linear Multi-View Reconstruction of Points, Lines, Planes and Cameras Using a Reference Plane

    Rother, C. / IEEE | British Library Conference Proceedings | 2003


    Motorcycle rear view cameras

    FLANAGAN PAUL / LAWSON CLIFFORD / POWELL JOHN et al. | European Patent Office | 2016

    Free access

    Geometric calibration of digital cameras through multi-view rectification

    Lucchese, L. | British Library Online Contents | 2005


    Lane fusion system using forward-view and rear-view cameras

    ZENG SHUQING | European Patent Office | 2015

    Free access

    Multi-View Surface Reconstruction Using Polarization

    Atkinson, G. / Hancock, E. / IEEE | British Library Conference Proceedings | 2005