Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation

Asmae Mouradi, Shruti Kshirsagar

Abstract

Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) for disaster management, automated damage detection provides decision-makers with actionable situational awareness. However, models trained on multi-disaster benchmarks often underperform in unseen geographic regions due to domain shift - a distributional mismatch between training and deployment data that undermines human trust in automated assessments. We explore a two-stage ensemble approach using supervised domain adaptation (SDA) for building damage classification across four severity classes. The pipeline adapts the xView2 first-place method to the Ida-BD dataset using SDA and systematically investigates the effect of individual augmentation components on classification performance. Comprehensive ablation experiments on the unseen Ida-BD test split demonstrate that SDA is indispensable: removing it causes damage detection to fail entirely. Our pipeline achieves the most robust performance using SDA with unsharp-enhanced RGB input, attaining a Macro-F1 of 0.5552. These results underscore the critical role of domain adaptation in building trustworthy automated damage assessment modules for HMS-integrated disaster response.

Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation

Abstract

Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) for disaster management, automated damage detection provides decision-makers with actionable situational awareness. However, models trained on multi-disaster benchmarks often underperform in unseen geographic regions due to domain shift - a distributional mismatch between training and deployment data that undermines human trust in automated assessments. We explore a two-stage ensemble approach using supervised domain adaptation (SDA) for building damage classification across four severity classes. The pipeline adapts the xView2 first-place method to the Ida-BD dataset using SDA and systematically investigates the effect of individual augmentation components on classification performance. Comprehensive ablation experiments on the unseen Ida-BD test split demonstrate that SDA is indispensable: removing it causes damage detection to fail entirely. Our pipeline achieves the most robust performance using SDA with unsharp-enhanced RGB input, attaining a Macro-F1 of 0.5552. These results underscore the critical role of domain adaptation in building trustworthy automated damage assessment modules for HMS-integrated disaster response.
Paper Structure (19 sections, 4 equations, 4 figures, 4 tables)

This paper contains 19 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Two-stage classification approach
  4. Augmentation Methods
  5. Edge Detection
  6. Contrast Enhancement (CLAHE)
  7. Unsharp Masking
  8. Fusion Augmentation
  9. Experimental Setup
  10. Datasets
  11. xBD Dataset (Source Domain)
  12. Ida-BD Dataset (Target Domain)
  13. Benchmark System: xView2 Challenge
  14. Performance Measures
  15. Results and Discussion
  16. ...and 4 more sections

Figures (4)

  • Figure 1: Overview of the proposed two-stage pipeline for damage classification. Both stages incorporate fusion augmentation and supervised domain adaptation
  • Figure 2: Example from the Ida-BD dataset: pre-disaster image, post-disaster image, and building damage annotation mask.
  • Figure 3: Qualitative comparison of Stage-1 building localization: (a) pre-disaster image, (b) localization result without domain adaptation, and (c) localization result with supervised domain adaptation
  • Figure 4: Qualitative damage detection result using RGB + Unsharp + SDA: (a) pre-disaster image, (b) post-disaster image, and (c) predicted damage mask (green: no damage, yellow: minor, orange: major, red: destroyed).