Global visual localization is critical for UAVs operating in environments where global navigation satellite systems (GNSS) are unreliable or unavailable. While many methods, such as visual odometry (VIO), rely on optical flow for localization, they often require prior knowledge of the current coordinates. In this paper, we propose an enhanced UAV localization method using the vector of locally aggregated descriptors (VLAD) combined with a cycle generative adversarial network (GAN) architecture. Unlike traditional approaches, our method does not require knowledge of the current coordinates; it only requires a pre-downloaded flight map, enabling location determination through image matching.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparing UAV camera data with satellite imagery for global localization


    Contributors:


    Publication date :

    2024-10-22


    Size :

    492187 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Comparing Deep Learning Performance for Aircraft Detection in Satellite Imagery

    Vergara, Victor M. / Wojcik, Jeremy J. / Kain, Evan T. et al. | IEEE | 2023


    Identifying Truck Activity from Global Positioning System Data Based on Satellite Imagery

    Hu, Jian / Yang, Shiyao / Yang, Yun et al. | Transportation Research Record | 2024



    Connecting swath satellite data with imagery in mapping applications

    Zhou, Amy / Penteado, Paulo / Roberts, Joe T. et al. | NTRS | 2016