Considering the accelerated development of Unmanned Aerial Vehicles (UAVs) applications in both industrial and research scenarios, there is an increasing need for localizing these aerial systems in non-urban environments, using GNSS-Free, vision-based methods. Our paper proposes a vision-based localization algorithm that utilizes deep features to compute geographical coordinates of a UAV flying in the wild. The method is based on matching salient features of RGB photographs captured by the drone camera and sections of a pre-built map consisting of georeferenced open-source satellite images. Experimental results prove that vision-based localization has comparable accuracy with traditional GNSS-based methods, which serve as ground truth. Compared to state-of-the-art Visual Odometry (VO) approaches, our solution is designed for long-distance, high-altitude UAV flights. Code a nd d atasets are available at https://github.com/TIERS/wildnav.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Vision-Based GNSS-Free Localization for UAVs in the Wild


    Contributors:


    Publication date :

    2022-12-09


    Size :

    6958888 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    GNSS Software Receiver for UAVs

    Olesen, Daniel | Online Contents | 2016


    Vision-Based Target Localization with Cooperative UAVs Towards Indoor Surveillance

    Niu, Guanchong / Cao, Qi / Chen, Chung Shue | IEEE | 2023


    Vision-based Positioning for UAVs

    Hu, Xiao | BASE | 2021

    Free access

    Vision-Based Collision Detection for UAVs

    Carnie, R. J. | British Library Conference Proceedings | 2005


    Vision-Based Obstacle Avoidance for UAVs

    Watanabe, Yoko / Calise, Anthony / Johnson, Eric | AIAA | 2007