Journal cover Journal topic
AGILE: GIScience Series Open-access proceedings of the Association of Geographic Information Laboratories in Europe
Journal topic
Articles | Volume 2
AGILE GIScience Ser., 2, 39, 2021
AGILE GIScience Ser., 2, 39, 2021

  04 Jun 2021

04 Jun 2021

Detecting OpenStreetMap missing buildings by transferring pre-trained deep neural networks

Jan Pisl1, Hao Li2, Sven Lautenbach1, Benjamin Herfort1,2, and Alexander Zipf1,2 Jan Pisl et al.
  • 1HeiGIT at Heidelberg University, Schloss-Wolfsbrunnenweg 33, 69118 Heidelberg, Germany
  • 2GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany

Keywords: OpenStreetMap, deep learning, building detection, humanitarian mapping, DeepVGI

Abstract. Accurate and complete geographic data of human settlements is crucial for effective emergency response, humanitarian aid and sustainable development. Open- StreetMap (OSM) can serve as a valuable source of this data. As there are still many areas missing in OSM, deep neural networks have been trained to detect such areas from satellite imagery. However, in regions where little or no training data is available, training networks is problematic. In this study, we proposed a method of transferring a building detection model, which was previously trained in an area wellmapped in OSM, to remote data-scarce areas. The transferring was achieved via fine-tuning the model on limited training samples from the original training area and the target area. We validated the method by transferring deep neural networks trained in Tanzania to a site in Cameroon with straight distance of over 2600 km, and tested multiple variants of the proposed method. Finally, we applied the fine-tuned model to detect 1192 buildings missing OSM in a selected area in Cameroon. The results showed that the proposed method led to a significant improvement in f1-score with as little as 30 training examples from the target area. This is a crucial quality of the proposed method as it allows to fine-tune models to regions where OSM data is scarce.

Publications Copernicus