Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model

TL;DR

This paper presents DAVI, a novel change detection method using vision foundation models for rapid, accurate, and domain-agnostic disaster damage assessment from satellite imagery, effective across diverse regions and disaster types.

Contribution

DAVI introduces a new approach combining task-specific and task-agnostic knowledge to detect damage without ground-truth labels, addressing domain disparities in disaster assessment.

Findings

Achieves high accuracy across multiple regions and disaster types

Operates effectively without ground-truth labels in target regions

Demonstrates robustness in a case study on the 2023 Türkiye earthquake

Abstract

The increasing frequency and intensity of natural disasters call for rapid and accurate damage assessment. In response, disaster benchmark datasets from high-resolution satellite imagery have been constructed to develop methods for detecting damaged areas. However, these methods face significant challenges when applied to previously unseen regions due to the limited geographical and disaster-type diversity in the existing datasets. We introduce DAVI (Disaster Assessment with VIsion foundation model), a novel approach that addresses domain disparities and detects structural damage at the building level without requiring ground-truth labels for target regions. DAVI combines task-specific knowledge from a model trained on source regions with task-agnostic knowledge from an image segmentation model to generate pseudo labels indicating potential damage in target regions. It then utilizes a two-stage refinement process, which operate at both pixel and image levels, to accurately identify changes in disaster-affected areas. Our evaluation, including a case study on the 2023 T\"urkiye earthquake, demonstrates that our model achieves exceptional performance across diverse terrains (e.g., North America, Asia, and the Middle East) and disaster types (e.g., wildfires, hurricanes, and tsunamis). This confirms its robustness in disaster assessment without dependence on ground-truth labels and highlights its practical applicability.