A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Building damage detection from satellite images after natural disasters on extremely imbalanced datasets
Abstract Assessment of natural disasters caused damage(s) to buildings is important for rescue work coordination which, however, remains a difficult engineering task to be conducted effectively. To automatically detect building damages from satellite imagery, this paper presents a two-step solution approach, including building localization and damage classification. To handle the extremely imbalanced distributions of the building damages, where the minority class occupies less than 0.1%, the architecture is supplemented with a new learning strategy comprising normality-imposed data-subset generation and incremental training. The validity of the proposed architecture is evaluated on a recent open-source dataset named xBD. The experimental study achieves a testing accuracy of 0.9729 and an Intersection over Union (IoU) of 0.5378 on three historical disaster events (i.e., “Mexico-earthquake”, “Midwest-flooding”, “Palu-tsunami”) for the localization analysis, and a testing accuracy of 0.9955 and a weighted F1-score of 0.9953 on the extracted building patches from “Mexico-earthquake”, for the followed classification analysis
Highlights A two-step solution is provided to automatically detect building damages after natural disasters. Data normality imposition and incremental learning can handle extremely imbalanced problems. Additional feature reflecting spatial compactness is created in damage classification. It achieves a weighted F1-score of 0.9953 on an extremely imbalanced dataset. It is feasible to be applied in large-scale damage assessment and mapping.
Building damage detection from satellite images after natural disasters on extremely imbalanced datasets
Abstract Assessment of natural disasters caused damage(s) to buildings is important for rescue work coordination which, however, remains a difficult engineering task to be conducted effectively. To automatically detect building damages from satellite imagery, this paper presents a two-step solution approach, including building localization and damage classification. To handle the extremely imbalanced distributions of the building damages, where the minority class occupies less than 0.1%, the architecture is supplemented with a new learning strategy comprising normality-imposed data-subset generation and incremental training. The validity of the proposed architecture is evaluated on a recent open-source dataset named xBD. The experimental study achieves a testing accuracy of 0.9729 and an Intersection over Union (IoU) of 0.5378 on three historical disaster events (i.e., “Mexico-earthquake”, “Midwest-flooding”, “Palu-tsunami”) for the localization analysis, and a testing accuracy of 0.9955 and a weighted F1-score of 0.9953 on the extracted building patches from “Mexico-earthquake”, for the followed classification analysis
Highlights A two-step solution is provided to automatically detect building damages after natural disasters. Data normality imposition and incremental learning can handle extremely imbalanced problems. Additional feature reflecting spatial compactness is created in damage classification. It achieves a weighted F1-score of 0.9953 on an extremely imbalanced dataset. It is feasible to be applied in large-scale damage assessment and mapping.
Building damage detection from satellite images after natural disasters on extremely imbalanced datasets
Wang, Ying (author) / Chew, Alvin Wei Ze (author) / Zhang, Limao (author)
2022-05-02
Article (Journal)
Electronic Resource
English
Damage detection in earthquake disasters using high-resolution satellite images
| British Library Conference Proceedings | 2005
Estimating Damage Costs from Natural Disasters in Korea
| Online Contents | 2017
Cultural heritage: building resilience to natural disasters
| Catalogue agriculture | 2017