Collapsed buildings should be detected with the highest priority during earthquake emergency response, due to the associated fatality rates. Although deep learning-based damage detection using vertical aerial images can achieve high performance, as depth information cannot be obtained, it is difficult to detect collapsed buildings when their roofs are not heavily damaged. Airborne LiDAR can efficiently obtain the 3D geometries of buildings (in the form of point clouds) and thus has greater potential to detect various collapsed buildings. However, there have been few previous studies on deep learning-based damage detection using point cloud data, due to a lack of large-scale datasets. Therefore, in this paper, we aim to develop a dataset tailored to point cloud-based building damage detection, in order to investigate the potential of point cloud data in collapsed building detection. Two types of building data are created: building roof and building patch, which contains the building and its surroundings. Comprehensive experiments are conducted under various data availability scenarios (pre–post-building patch, post-building roof, and post-building patch) with varying reference data. The pre–post scenario tries to detect damage using pre-event and post-event data, whereas post-building patch and roof only use post-event data. Damage detection is implemented using both basic and modern 3D point cloud-based deep learning algorithms. To adapt a single-input network, which can only accept one building’s data for a prediction, to the pre–post (double-input) scenario, a general extension framework is proposed. Moreover, a simple visual explanation method is proposed, in order to conduct sensitivity analyses for validating the reliability of model decisions under the post-only scenario. Finally, the generalization ability of the proposed approach is tested using buildings with different architectural styles acquired by a distinct sensor. The results show that point cloud-based methods can achieve high accuracy and are robust under training data reduction. The sensitivity analysis reveals that the trained models are able to locate roof deformations precisely, but have difficulty recognizing global damage, such as that relating to the roof inclination. Additionally, it is revealed that the model decisions are overly dependent on debris-like objects when surroundings information is available, which leads to misclassifications. By training on the developed dataset, the model can achieve moderate accuracy on another dataset with different architectural styles without additional training.
After an earthquake occurs, field surveys are conducted by relevant authorities to assess the damage suffered by buildings. The field survey is essential as it ensures the safety of residents and provides the necessary information to local authorities for post-disaster recovery. In Japan, a primary (mandatory) exterior survey is conducted first, and a secondary (voluntary) interior survey is performed subsequently if the residents request a reinvestigation. However, a major challenge associated with field surveys is the substantial time cost of determining the damage grades. Moreover, an interior survey is performed only after receiving the reinvestigation request from occupants, which further delays the decision-making process. In addition, the risk of incorrect damage estimation during the exterior survey must be considered because underestimating the damage can endanger the residents. Therefore, in this study, a three-part analysis (Parts I–III), where each part corresponds to a distinct stage of the standard damage assessment procedure, was performed to characterize the relationship between the building parameters and damage grades at different stages. To further explore the possibility of accelerating decision-making, predictive modeling was performed in each part. The Part I results indicate that estimating the final damage grade for all buildings immediately after the exterior survey is similar to treating the exterior survey results as the final ones. The Part II results show that buildings that potentially require an interior survey can be predicted with reasonable accuracy after the exterior survey. In buildings for which reinvestigations have been requested, Part III demonstrates that the risk of underestimation in the exterior survey can be predicted reliably.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.