TAPEDA – Towards Automated Post-Earthquake Damage Assessment
- Katrin Beyer, EPFL
After earthquakes, engineers assess the damaged state of buildings through visual inspection and judge whether they are safe to enter or not. Damage evaluation is therefore at present a very labor-intensive task, which requires a visual inspection of all potentially affected buildings.
Recent advancements in several fields such as camera-mounted drones, the Structure from Motion (SfM) technique, convolutional neural networks (CNN) and capacity loss algorithms that connect visual image indicators to structural performance, will allow in the future for establishing automated post-earthquake assessment procedures. Our vision is to develop such a procedure for stone masonry buildings, which are among the most vulnerable buildings during earthquakes. This proposal develops two important components towards this vision, i.e., the identification of damage features (cracks) from images and the segmentation of a 3D point cloud model of a building in order to prepare the setting up of a finite element model. Other components, such as the development of models that connect the extent of damage to the loss in stiffness and strength of the structural element as well as the development of efficient and reliable finite element models for the post-earthquake assessment of stone masonry buildings are in the realm of the expertise of our laboratory and are currently under development.