EGU21-9903, updated on 04 Mar 2021
EGU General Assembly 2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Street-Level Imagery and Deep Learning for Characterization of Exposed Buildings

Patrick Aravena Pelizari1, Christian Geiß1, Elisabeth Schoepfer1, Torsten Riedlinger1, Paula Aguirre2,3, Hernán Santa María2,4, Yvonne Merino Peña2,4, Juan Camilo Gómez Zapata5,6, Massimiliano Pittore7, and Hannes Taubenböck1,8
Patrick Aravena Pelizari et al.
  • 1German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Weßling-Oberpfaffenhofen, Germany (
  • 2National Research Center for Integrated Natural Disaster Management (CIGIDEN), Santiago de Chile, Chile
  • 3Institute for Mathematical and Computational Engineering, School of Engineering, Pontifical Catholic University of Chile, Santiago de Chile, Chile
  • 4Department of Structural and Geotechnical Engineering, Pontifical Catholic University of Chile, Santiago de Chile, Chile
  • 5GFZ German Research Centre for Geosciences, Seismic Hazard and Risk Dynamics, Potsdam, Germany
  • 6University of Potsdam, Potsdam, Germany
  • 7EURAC Research, Institute for Earth Observation, Bolzano, Italy
  • 8University of Würzburg, Institute of Geography and Geology, Chair of Remote Sensing, Würzburg, Germany

Knowledge on the key structural characteristics of exposed buildings is crucial for accurate risk modeling with regard to natural hazards. In risk assessment this information is used to interlink exposed buildings with specific representative vulnerability models and is thus a prerequisite to implement sound risk models. The acquisition of such data by conventional building surveys is usually highly expensive in terms of labor, time, and money. Institutional data bases such as census or tax assessor data provide alternative sources of information. Such data, however, are often inappropriate, out-of-date, or not available. Today, the large-area availability of systematically collected street-level data due to global initiatives such as Google Street View, among others, offers new possibilities for the collection of in-situ data. At the same time, developments in machine learning and computer vision – in deep learning in particular – show high accuracy in solving perceptual tasks in the image domain. Thereon, we explore the potential of an automatized and thus efficient collection of vulnerability related building characteristics. To this end, we elaborated a workflow where the inference of building characteristics (e.g., the seismic building structural type, the material of the lateral load resisting system or the building height) from geotagged street-level imagery is tasked to a custom-trained Deep Convolutional Neural Network. The approach is applied and evaluated for the earthquake-prone Chilean capital Santiago de Chile. Experimental results are presented and show high accuracy in the derivation of addressed target variables. This emphasizes the potential of the proposed methodology to contribute to large-area collection of in-situ information on exposed buildings.

How to cite: Aravena Pelizari, P., Geiß, C., Schoepfer, E., Riedlinger, T., Aguirre, P., Santa María, H., Merino Peña, Y., Gómez Zapata, J. C., Pittore, M., and Taubenböck, H.: Street-Level Imagery and Deep Learning for Characterization of Exposed Buildings, EGU General Assembly 2021, online, 19–30 Apr 2021, EGU21-9903,, 2021.