Monocular visual odometry (VO) is a fundamental technique for unmanned ground vehicle (UGV) navigation. However, traditional monocular VO methods always suffer from sparse environment maps which cannot be directly used for navigation because of the lack of structural information. In this article, we propose a navigation-oriented LiDAR-guided monocular visual odometry and mapping (NALO-VOM) to obtain scale-consistent camera poses and a semi-dense environment map which is more suitable for navigation of UGVs. The structure representation ability of the 3D LiDAR point cloud is learned by a major-plane prediction network and then transferred into the monocular VO system in NALO-VOM. As a result, NALO-VOM can construct a more dense and high-quality map using only a monocular camera. To be specific, the major-plane prediction network is trained offline using 3D LiDAR geometric information, which predicts major-plane mask (MP-Mask) for each frame of the visual image during the localization. Then, MP-Mask is used for scale optimization and semi-dense map building. Experiments are performed on the public dataset and self-collected sequences. The results show the competitive performance on the localization accuracy and mapping quality compared with other visual odometry methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    NALO-VOM: Navigation-Oriented LiDAR-Guided Monocular Visual Odometry and Mapping for Unmanned Ground Vehicles


    Contributors:
    Hu, Ziqi (author) / Yuan, Jing (author) / Gao, Yuanxi (author) / Wang, Boran (author) / Zhang, Xuebo (author)

    Published in:

    Publication date :

    2024-01-01


    Size :

    4117576 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Ground Vehicle Monocular Visual Odometry

    Sabry, Mohamed / Al-Kaff, Abdulla / Hussein, Ahmed et al. | IEEE | 2019


    Attention Guided Unsupervised learning of Monocular Visual-inertial Odometry

    Wang, Zhenke / Zhu, Yuan / Lu, Ke et al. | IEEE | 2022



    GROUND VEHICLE MONOCULAR VISUAL-INERTIAL ODOMETRY VIA LOCALLY FLAT CONSTRAINTS

    RAMIREZ LLANOS EDUARDO JOSE / YU XIN / VERMA DHIREN | European Patent Office | 2022

    Free access

    Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry

    Zhou, Dingfu / Dai, Yuchao / Li, Hongdong | IEEE | 2020