This research involves the use of advanced Computer Vision tecquiques for the detection of damage occurences in builidings and infrascructures in the atfermath of earthquakes. The goal is to help first responders in quickly screeening images and videos acquired on field using cameras and UAVs. The activity is carried out in collaboration with Eucentre Foundation (European Centre for Training and Research in Earthquake Engineering), including the research contract TeamAware.

Related activities are:

• Generation of semi-synthetic image of damage instances starting from real-world 3D models
  
  
  
  
  
  
• Deep Learning methods for structural damage detection, including object detection, open-vocabulary detection, visual language models, segmentation
  
  
  
  
• Algorithms for tracking damage occurences in videos