ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-5-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-5-2020, 109–116, 2020
https://doi.org/10.5194/isprs-annals-V-5-2020-109-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-5-2020, 109–116, 2020
https://doi.org/10.5194/isprs-annals-V-5-2020-109-2020

  03 Aug 2020

03 Aug 2020

SEMCITY TOULOUSE: A BENCHMARK FOR BUILDING INSTANCE SEGMENTATION IN SATELLITE IMAGES

R. Roscher1,2, M. Volpi3, C. Mallet4, L. Drees1, and J. D. Wegner5 R. Roscher et al.
  • 1Institute of Geodesy and Geoinformation, University of Bonn, Germany
  • 2Institute of Computer Science, University of Osnabrueck, Germany
  • 3Swiss Data Science Center, ETHZ and EPF Lausanne, Switzerland
  • 4Univ. Gustave Eiffel, IGN-ENSG, LaSTIG/Strudel, Saint-Mandé, France
  • 5EcoVision Lab, ETH Zurich, Switzerland

Keywords: benchmark, machine learning, instance segmentation, buildings

Abstract. In order to reach the goal of reliably solving Earth monitoring tasks, automated and efficient machine learning methods are necessary for large-scale scene analysis and interpretation. A typical bottleneck of supervised learning approaches is the availability of accurate (manually) labeled training data, which is particularly important to train state-of-the-art (deep) learning methods. We present SemCity Toulouse, a publicly available, very high resolution, multi-spectral benchmark data set for training and evaluation of sophisticated machine learning models. The benchmark acts as test bed for single building instance segmentation which has been rarely considered before in densely built urban areas. Additional information is provided in the form of a multi-class semantic segmentation annotation covering the same area plus an adjacent area 3 times larger. The data set addresses interested researchers from various communities such as photogrammetry and remote sensing, but also computer vision and machine learning.