Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN

TL;DR

This paper introduces CVDisaster, a novel framework combining cross-view imagery analysis for geolocalization and disaster damage estimation, demonstrated on Hurricane IAN with high accuracy and minimal fine-tuning.

Contribution

The paper presents a new cross-view disaster mapping framework, CVDisaster, integrating geolocalization and damage perception models using innovative contrastive learning and vision transformer techniques.

Findings

Achieves over 80% accuracy in geolocalization

Attains 75% accuracy in damage perception estimation

Demonstrates effectiveness with limited fine-tuning

Abstract

Nature disasters play a key role in shaping human-urban infrastructure interactions. Effective and efficient response to natural disasters is essential for building resilience and a sustainable urban environment. Two types of information are usually the most necessary and difficult to gather in disaster response. The first information is about disaster damage perception, which shows how badly people think that urban infrastructure has been damaged. The second information is geolocation awareness, which means how people whereabouts are made available. In this paper, we proposed a novel disaster mapping framework, namely CVDisaster, aiming at simultaneously addressing geolocalization and damage perception estimation using cross-view Street-View Imagery (SVI) and Very High-Resolution satellite imagery. CVDisaster consists of two cross-view models, where CVDisaster-Geoloc refers to a cross-view geolocalization model based on a contrastive learning objective with a Siamese ConvNeXt image encoder, and CVDisaster-Est is a cross-view classification model based on a Couple Global Context Vision Transformer (CGCViT). Taking Hurricane IAN as a case study, we evaluate the CVDisaster framework by creating a novel cross-view dataset (CVIAN) and conducting extensive experiments. As a result, we show that CVDisaster can achieve highly competitive performance (over 80% for geolocalization and 75% for damage perception estimation) with even limited fine-tuning efforts, which largely motivates future cross-view models and applications within a broader GeoAI research community. The data and code are publicly available at: https://github.com/tum-bgd/CVDisaster.