ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2020, 517–524, 2020
https://doi.org/10.5194/isprs-annals-V-2-2020-517-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2020, 517–524, 2020
https://doi.org/10.5194/isprs-annals-V-2-2020-517-2020

  03 Aug 2020

03 Aug 2020

DETECTION OF UNDOCUMENTED BUILDINGS USING CONVOLUTIONAL NEURAL NETWORK AND OFFICIAL GEODATA

Q. Li1,2, Y. Shi3, S. Auer1, R. Roschlaub4, K. Möst4, M. Schmitt2, and X. X. Zhu1,2 Q. Li et al.
  • 1Remote Sensing Technology Institute, German Aerospace Center, Oberpfaffenhofen, Germany
  • 2Signal Processing in Earth Observation, Technical University of Munich, Munich, Germany
  • 3Remote Sensing Technology, Technical University of Munich, Munich, Germany
  • 4Bavarian Agency for Digitization, High-Speed Internet and Surveying, Munich, Germany

Keywords: Building Detection, Convolutional Neural Network, Deep Learning, Semantic Segmentation, Decision Fusion

Abstract. Undocumented buildings are buildings which were built years ago, but were never recorded in official digital cadastral maps. Detection of undocumented buildings is of great importance for urban planning and monitoring. The state of Bavaria, Germany, pursues this task based on high resolution optical data and digital surface models, using semi-automatic detection methods, which suffer from a high false alarm rate. In order to study the influence of sampling strategies on the performance of building detection, we have firstly designed a transferability analysis experiment, which has not been adequately addressed in the current literature. In this experiment, we test whether the trained model from a district contains valuable information for building detection in a different district. It was found that the large-scale building detection results can be considerably improved when training samples are collected from different districts. Based on the building detection results, we propose a novel framework for the detection of undocumented buildings using Convolutional Neural Network (CNN) and official geodata. More specifically, buildings are identified as undocumented, when their pixels in the output of the CNN are predicted as “building”, whereas they belong to the “non-building” in the Digital Cadastral Map (DFK). The detected undocumented building pixels are subsequently divided into the class of old or new undocumented building with the aid of a Temporal Digital Surface Model (tDSM) in the stage of decision fusion. By doing so, a seamless map of undocumented buildings is generated for 1/4th of the state of Bavaria, Germany at a spatial resolution of 0.4 m, which has demonstrated the use of CNN for the robust detection of undocumented buildings at large-scale.