Volume XLII-2
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 419-424, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-419-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 419-424, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-419-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 May 2018

30 May 2018

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

S. Ham, Y. Oh, K. Choi, and I. Lee S. Ham et al.
  • Dept. of Geoinformatics, University of Seoul, Seoul, Republic of Korea

Keywords: Deep learning, UAV image, segmentation, building detection, illegal buildings

Abstract. 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.