New Publication on Automated building characterization

New Publication on Automated building characterization

September 15, 2021

A new publication by Hannes Taubenböck and colleagues is online about “Automated building characterization for seismic risk assessment using street-level imagery and deep learning”. From the abstract: “Accurate seismic risk modeling requires knowledge of key structural characteristics of buildings. However, to date, the collection of such data is highly expensive in terms of labor, time and money and thus prohibitive for a spatially continuous large-area monitoring. This study quantitatively evaluates the potential of an automated and thus more efficient collection of vulnerability-related structural building characteristics based on Deep Convolutional Neural Networks (DCNNs) and street-level imagery such as provided by Google Street View. The proposed approach involves a tailored hierarchical categorization workflow to structure the highly heterogeneous street-level imagery in an application-oriented fashion. Thereupon, we use state-of-the-art DCNNs to explore the automated inference of Seismic Building Structural Types. These reflect the main-load bearing structure of a building, and thus its resistance to seismic forces. Additionally, we assess the independent retrieval of two key building structural parameters, i.e., the material of the lateral-load-resisting system and building height to investigate the applicability for a more generic structural characterization of buildings. Experimental results obtained for the earthquake-prone Chilean capital Santiago show accuracies beyond κ = 0.81 for all addressed classification tasks. This underlines the potential of the proposed methodology for an efficient in-situ data collection on large spatial scales with the purpose of risk assessments related to earthquakes, but also other natural hazards (e.g., tsunamis, or floods).”

read full article here:

P. Aravena Pelizari, C. Geiß, P. Aguirre, H. Santa María, Y. Merino Peña, and H. Taubenböck (2021) Automated building characterization for seismic risk assessment using street-level imagery and deep learning. ISPRS Journal of Photogrammetry and Remote Sensing

you may also like:

Successful fieldwork at the Naryn River in Kyrgyzstan

Successful fieldwork at the Naryn River in Kyrgyzstan

During the last week, EORC PI Florian Betz, EAGLE student Ariana Arguello-Cordero and FluBig team member Magdalena Lauermann from Catholic University Eichstätt-Ingolstadt have been on a field campaign in Kyrgyzstan to collect data for the FluBig project dedicated to...

EO4CAM Meeting in Oberpfaffenhofen

EO4CAM Meeting in Oberpfaffenhofen

On 5 June 2025, representatives from the Bavarian State Ministry of the Environment and Consumer Protection (StMUV), the Bavarian Environment Agency (LfU), and the German Aerospace Center (DLR) met at DLR Oberpfaffenhofen as part of the EO4CAM (Earth Observation...

EORC at the International Africa Festival 2025 in Würzburg

EORC at the International Africa Festival 2025 in Würzburg

If you know Würzburg, you certainly know the International Africa Festival, Europe's largest and oldest festival for African music and culture. For 15 years in a row now, the university tent has been an integral part of the festival. This is where the...

EO4CAM meeting at LfU in Augsburg on grassland in Bavaria

EO4CAM meeting at LfU in Augsburg on grassland in Bavaria

As part of the EO4CAM project (Earth Observation Laboratory for Climate Adaption and Mitigation), representatives of the Bavarian Environment Agency (LfU), the German Aerospace Centre (DLR), and the Earth Observation Research Cluster (EORC) met at the LfU in...

New R Package Enhances UAS Research and Planning

New R Package Enhances UAS Research and Planning

We’re excited to share the development of a new R package created by our PhD student, Antonio Castaneda Gomez, whose contributions to Uncrewed Aerial Systems (UAS) research continue to impress. Known as the brain behind many of our UAS data collection...