xBD: A Dataset for Assessing Building Damage from Satellite Imagery

TL;DR

xBD is a comprehensive large-scale dataset combining satellite imagery, building damage labels, and environmental annotations to facilitate the development of automated damage assessment tools for disaster response.

Contribution

The paper introduces xBD, the largest dataset of its kind, enabling improved machine learning models for damage detection and assessment from satellite imagery.

Findings

Contains 850,736 building annotations across diverse disaster events.

Provides pre- and post-disaster satellite imagery with damage labels.

Includes environmental factor annotations like fire and water.

Abstract

We present xBD, a new, large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. Natural disaster response requires an accurate understanding of damaged buildings in an affected region. Current response strategies require in-person damage assessments within 24-48 hours of a disaster. Massive potential exists for using aerial imagery combined with computer vision algorithms to assess damage and reduce the potential danger to human life. In collaboration with multiple disaster response agencies, xBD provides pre- and post-event satellite imagery across a variety of disaster events with building polygons, ordinal labels of damage level, and corresponding satellite metadata. Furthermore, the dataset contains bounding boxes and labels for environmental factors such as fire, water, and smoke. xBD is the largest building damage assessment dataset to date, containing 850,736 building annotations across 45,362 km\textsuperscript{2} of imagery.