Post-Disaster Building Damage Detection from Earth Observation Imagery using Unsupervised and Transferable Anomaly Detecting Generative Adversarial Networks

• Main Authors: Sofia Tilon, Francesco Nex, Norman Kerle, George Vosselman
• Format: Article
• Language: English
• Published: MDPI AG 2020-12-01
• Series: Remote Sensing
• Subjects: deep learning; Generative Adversarial Networks; post-disaster; building damage assessment; anomaly detection; Unmanned Aerial Vehicles (UAV), satellite
• Online Access: https://www.mdpi.com/2072-4292/12/24/4193

We present an unsupervised deep learning approach for post-disaster building damage detection that can transfer to different typologies of damage or geographical locations. Previous advances in this direction were limited by insufficient qualitative training data. We propose to use a state-of-the-art Anomaly Detecting Generative Adversarial Network (ADGAN) because it only requires pre-event imagery of buildings in their undamaged state. This approach aids the post-disaster response phase because the model can be developed in the pre-event phase and rapidly deployed in the post-event phase. We used the xBD dataset, containing pre- and post- event satellite imagery of several disaster-types, and a custom made Unmanned Aerial Vehicle (UAV) dataset, containing post-earthquake imagery. Results showed that models trained on UAV-imagery were capable of detecting earthquake-induced damage. The best performing model for European locations obtained a recall, precision and F1-score of 0.59, 0.97 and 0.74, respectively. Models trained on satellite imagery were capable of detecting damage on the condition that the training dataset was void of vegetation and shadows. In this manner, the best performing model for (wild)fire events yielded a recall, precision and F1-score of 0.78, 0.99 and 0.87, respectively. Compared to other supervised and/or multi-epoch approaches, our results are encouraging. Moreover, in addition to image classifications, we show how contextual information can be used to create detailed damage maps without the need of a dedicated multi-task deep learning framework. Finally, we formulate practical guidelines to apply this single-epoch and unsupervised method to real-world applications.