The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2021, 15–22, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B4-2021-15-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2021, 15–22, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B4-2021-15-2021

  30 Jun 2021

30 Jun 2021

GENERATIVE ADVERSARIAL NETWORKS TO GENERALISE URBAN AREAS IN TOPOGRAPHIC MAPS

A. Courtial1, G. Touya1, and X. Zhang2 A. Courtial et al.
  • 1Univ. Gustave Eiffel, IGN-ENSG, LaSTIG – Saint-Mandé, France
  • 2School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China

Keywords: Map generalisation, deep learning, Image generation, Urban area, GAN

Abstract. This article presents how a generative adversarial network (GAN) can be employed to produce a generalised map that combines several cartographic themes in the dense context of urban areas. We use as input detailed buildings, roads, and rivers from topographic datasets produced by the French national mapping agency (IGN), and we expect as output of the GAN a legible map of these elements at a target scale of 1:50,000. This level of detail requires to reduce the amount of information while preserving patterns; covering dense inner cities block by a unique polygon is also necessary because these blocks cannot be represented with enlarged individual buildings. The target map has a style similar to the topographic map produced by IGN. This experiment succeeded in producing image tiles that look like legible maps. It also highlights the impact of data and representation choices on the quality of predicted images, and the challenge of learning geographic relationships.