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.


    Access

    Download


    Export, share and cite



    Title :

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


    Contributors:
    S. Ham (author) / Y. Oh (author) / K. Choi (author) / I. Lee (author)


    Publication date :

    2018




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    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 | European Patent Office | 2023

    Free access


    Deconvolutional Speckle Reducing Anisotropic Diffusion

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


    Building 3-D City Models from Multiple Unregistered Profile Maps

    Jokinen, O. / National Research Council of Canada | British Library Conference Proceedings | 1997