Detecting unregistered buildings from aerial images is an important task for urban management such as inspection of illegal buildings in green belt or update of GIS database. Moreover, the data acquisition platform of photogrammetry is evolving from manned aircraft to UAVs (Unmanned Aerial Vehicles). However, it is very costly and time-consuming to detect unregistered buildings from UAV images since the interpretation of aerial images still relies on manual efforts. To overcome this problem, we propose a system which automatically detects unregistered buildings from UAV images based on deep learning methods. Specifically, we train a deconvolutional network with publicly opened geospatial data, semantically segment a given UAV image into a building probability map and compare the building map with existing GIS data. Through this procedure, we could detect unregistered buildings from UAV images automatically and efficiently. We expect that the proposed system can be applied for various urban management tasks such as monitoring illegal buildings or illegal land-use change.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    SEMANTIC SEGMENTATION AND UNREGISTERED BUILDING DETECTION FROM UAV IMAGES USING A DECONVOLUTIONAL NETWORK


    Beteiligte:
    S. Ham (Autor:in) / Y. Oh (Autor:in) / K. Choi (Autor:in) / I. Lee (Autor:in)


    Erscheinungsdatum :

    2018




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Building 3-D Models from Unregistered Range Images

    Higuchi, K. / Hebert, M. / Ikeuchi, K. | British Library Online Contents | 1995


    UNREGISTERED BICYCLE DETECTION DEVICE, UNREGISTERED BICYCLE DETECTION METHOD, AND PROGRAM

    KINOSHITA KOKI / NAKAMURA TOYOKAZU | Europäisches Patentamt | 2023

    Freier Zugriff


    Deconvolutional Speckle Reducing Anisotropic Diffusion

    Acton, S. T. | British Library Conference Proceedings | 2005


    Unregistered drone identification system

    CHO SEOK JE / CHOI SE CHAN / JIN GANG IK et al. | Europäisches Patentamt | 2020

    Freier Zugriff