Deep Learning Methods for Structural Damage Detection

The main objective of TeamAware project is to develop an integrated and cost-efficient situational awareness system for first responders from different sectors. The CVMLab is involved in Work Package 4, focusing on the development of deep learning-based methods for damage detection in buildings and infrastructures. The main objectives are: adding artificial damage on 3D models obtained from photogrammetry; rendering of a semi-synthetic dataset to train a neural network; damage detection on real videos acquired post-earthquake.

In collaboration with Eucentre Foundation (European Centre for Training and Research in Earthquake Engineering), that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101019808.
Duration: September 2021 - February 2024

Related publications

• Piercarlo Dondi, Alessio Gullotti, Michele Inchingolo, Ilaria Senaldi, Chiara Casarotti, Luca Lombardi, Marco Piastra (2025). Post-earthquake structural damage detection with tunable semi-synthetic image generation, in Engineering Applications of Artificial Intelligence, Volume 147, 1 May 2025, 110302, Elsevier, DOI:10.1016/j.engappai.2025.110302.
• Piercarlo Dondi, Alessio Gullotti, Michele Inchingolo, Ilaria Senaldi, Chiara Casarotti, Luca Lombardi, Marco Piastra (2025). Improving Post-Earthquake Crack Detection using Semi-Synthetic Generated Images, in Del Bue A., Canton C., Pont-Tuset J., Tommasi T. (eds), Computer Vision – ECCV 2024 Workshops. ECCV 2024, Lecture Notes in Computer Science, vol 15642, Springer, Cham, DOI:10.1007/978-3-031-91907-7_2.
• Piercarlo Dondi, Ilaria Senaldi, Luca Lombardi, Marco Piastra (2023). Many-to-Many metrics: a new approach to evaluate the performance of structural damage detection networks, in Foresti G.L., Fusiello A., Hancock E. (eds.), Image Analysis and Processing – ICIAP 2023, Lecture Notes in Computer Science, vol 14234, pp. 144-155, Springer, Cham, DOI:10.1007/978-3-031-43153-1_13.