Ground-based imaging of objects in Low Earth Orbit (LEO) is complicated by atmospheric turbulence, which make it difficult to identify key features or components on the object of interest. Many automated image reconstruction techniques are in use, but expert labor is needed to subjectively discern and identify truth features on a partially reconstructed image. In this paper, we present a deep learning approach for semantic segmentation of ground-based images of LEO objects. We investigate the performance under various atmospheric turbulence strengths in terms of the Fried parameter ($r_{0}$) and show the viability of this method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Semantic Segmentation of Low Earth Orbit Satellites using Convolutional Neural Networks


    Beteiligte:
    Yang, Julia (Autor:in) / Lucas, Jacob (Autor:in) / Kyono, Trent (Autor:in) / Abercrombie, Michael (Autor:in) / Berg, Andrew Vanden (Autor:in) / Fletcher, Justin (Autor:in)


    Erscheinungsdatum :

    05.03.2022


    Format / Umfang :

    3593762 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Semantic Segmentation of Low Earth Object Satellites using Convolutional Neural Networks

    Yang, Julia | British Library Conference Proceedings | 2021



    Networks of Low-Earth Orbit Store-and-Forward Satellites

    Havlicek, J.P. | Online Contents | 1995


    Networks of low-Earth orbit store-and-forward satellites

    Havlicek, J.P. / McKeeman, J.C. / Remaklus, P.W. | IEEE | 1995