In the frontend visual odometry of SLAM, the traditional feature matching method has poor extraction effect and instability in the case of changes in viewpoint and illumination, while the feature matching method based on deep learning cannot meet the real-time requirements on embedded devices with low computing power. To solve the above problems, this paper improves the SuperPoint network using depthwise separable convolution and designs a lightweight feature extraction network named L_SuperPoint. Based on the L_SuperPoint network, this paper designs a visual SLAM system, and the system not only has a better mapping effect than ORB-SLAM2 but also can run in real-time on embedded devices. The results of dataset simulation experiments and real scene experiments show that the L_SuperPoint network has both the robust feature extraction of the SuperPoint network and the real-time mapping capability of ORB-SLAM2, which effectively improves the operating efficiency and accuracy of the SLAM.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Visual SLAM Based on Lightweight SuperPoint Network


    Contributors:
    Liu, Yunhong (author) / Li, Zhibin (author)


    Publication date :

    2022-10-12


    Size :

    2603398 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Visual SLAM: Why filter?

    Strasdat, H. / Montiel, J. M. / Davison, A. J. | British Library Online Contents | 2012


    D3VIL-SLAM: 3D Visual Inertial LiDAR SLAM for Outdoor Environments

    Frosi, Matteo / Matteucci, Matteo | IEEE | 2023


    Visual SLAM for flying vehicles

    B. Steder / GRISETTI, GIORGIO / C. Stachniss et al. | BASE | 2008

    Free access

    Event-Based Visual SLAM : An Explorative Approach

    Rideg, Johan | BASE | 2023

    Free access

    UVS: Underwater Visual SLAM - A Robust Monocular Visual SLAM System for Lifelong Underwater Operations

    Leonardi, Marco / Ludvigsen, Martin / Stahl, Annette et al. | BASE | 2023

    Free access