Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion

TL;DR

This paper presents a novel approach for building disaster damage assessment using multi-temporal satellite imagery fusion, significantly improving accuracy and efficiency in change detection tasks with the xBD dataset.

Contribution

The paper introduces new data processing and training methods tailored for building damage assessment, achieving top results on the xView2 challenge.

Findings

Substantial improvement over baseline models

Top leaderboard ranking on xView2 challenge

Effective data processing techniques for damage assessment

Abstract

Automatic change detection and disaster damage assessment are currently procedures requiring a huge amount of labor and manual work by satellite imagery analysts. In the occurrences of natural disasters, timely change detection can save lives. In this work, we report findings on problem framing, data processing and training procedures which are specifically helpful for the task of building damage assessment using the newly released xBD dataset. Our insights lead to substantial improvement over the xBD baseline models, and we score among top results on the xView2 challenge leaderboard. We release our code used for the competition.