The state-of-the-art geopositioning is the Global Navigation Satellite System (GNSS), which operates based on the satellite constellation providing positioning, navigation, and timing services. While the Global Positioning System (GPS) is widely used to position an Unmanned Aerial System (UAS), it is not always available and can be jammed, introducing operational liabilities. When the GPS signal is degraded or denied, the UAS navigation solution cannot rely on incorrect positions GPS provides, resulting in potential loss of control. This paper presents a real-time pipeline for geopositioning functionality using a down-facing monocular camera. The proposed approach is deployable using only a few initialization parameters, the most important of which is the map of the area covered by the UAS flight plan. Our pipeline consists of an offline geospatial quad-tree generation for fast information retrieval, a choice from a selection of landmark detection and matching schemes, and an attitude control mechanism that improves reference to acquired image matching. To evaluate our method, we collected several image sequences using various flight patterns with seasonal changes. The experiments demonstrate high accuracy and robustness to seasonal changes.


    Access

    Download


    Export, share and cite



    Title :

    A Visual Odometry Pipeline for Real-Time UAS Geopositioning


    Contributors:
    Jianli Wei (author) / Alper Yilmaz (author)


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Visual Odometry

    Nister, D. / Naroditsky, O. / Bergen, J. et al. | British Library Conference Proceedings | 2004


    Visual odometry

    Nister, D. / Naroditsky, O. / Bergen, J. | IEEE | 2004


    A real-time method for depth enhanced visual odometry

    Zhang, J. | British Library Online Contents | 2017


    Real-Time Visual Odometry Covariance Estimation for Unmanned Air Vehicle Navigation

    Anderson, Michael L. / Brink, Kevin M. / Willis, Andrew R. | AIAA | 2019

    Free access

    Motion-without-structure: Real-time multipose optimization for accurate visual odometry

    Lategahn, Henning / Geiger, Andreas / Kitt, Bernd et al. | IEEE | 2012