Automated Building Segmentation and Damage Assessment From Satellite Images for Disaster Relief

Abstract

Abstract. After a natural disaster or humanitarian crisis, rescue forces and relief organisations are dependent on fast, area-wide and accurate information on the damage caused to infrastructure and the situation on the ground. This study focuses on the assessment of building damage levels on optical satellite imagery with a two-step ensemble model performing building segmentation and damage classification trained on a public dataset. We provide an extensive generalization study on pre- and post-disaster data from the passage of the cyclone Idai over Beira, Mozambique, in 2019 and the explosion in Beirut, Lebanon, in 2020. Critical challenges are addressed, including the detection of clustered buildings with uncommon visual appearances, the classification of damage levels by both humans and deep learning models, and the impact of varying imagery acquisition conditions. We show promising building damage assessment results and highlight the strong performance impact of data pre-processing on the generalization capability of deep convolutional models.

Advances in Rapid Damage Identification Methods for Post-Disaster Regional Buildings Based on Remote Sensing Images: A Survey

“…Multi-disaster damage classification: Yuan et al [112] conducted comprehensive studies on pre-and post-disaster data from Hurricane Idai in Beira, Mozambique (2019) and the Beirut explosion in Lebanon (2020). Their research involved classifying damage levels using both human and deep learning models while also exploring the impact of various image acquisition conditions on classification accuracy.…”

Disaster impact analysis in Africa: EDDA - UAV building damage dataset of rural and urban Mozambique

“…[5][6][7] Due to its flexible deployment, low-altitude imaging, higher resolution and lessened obstruction by clouds, UAV imaging has increasingly become the preferred method of sensing for automated building damage assessment, especially in the context of disaster response. 3,[8][9][10][11] The capacity to cover large land areas in high resolution results in large data collections and further introduces the challenge of having to evaluate the same data in relatively short amount of time. Manual evaluation of the data would take a lot of time, without being able to provide an objective insight into data statistics and comprehend the complete extent of the disaster in various regions.…”

“…In this work we answer this need by extending the original dataset mentioned in the work done by Yuan et al 3 containing the Mozambican port city of Beira with rural settlements affected by Cyclone Idai and publishing the dataset publicly in order to minimize the disparity in dataset availability. We then show the results of testing conducted with the expanded dataset, focusing on the application of disaster impact assessment with regard to building detection and damage classification.…”

Using Earth Observation to Support First Aid Response in Crisis Situations– Lessons Learned From the Earthquake in Türkiye/Syria (2023)

“…Recent developments in computer vision and the rapid evolution of graphics processors have led to faster algorithms that open up new possibilities for disaster relief and humanitarian aid. Earlier studies showed that by combining remote sensing data with deep learning techniques, it becomes feasible to automate image analysis for large-scale impact assessments, specifically for the extraction of relevant features such as roads, buildings and building damage (Yuan et al, 2021). The extracted information can support rescue teams to understand the full extent of a disaster more quickly and to plan rescue missions to be more efficient.…”