Litcius/Paper detail

An Attention-Based System for Damage Assessment Using Satellite Imagery

Hanxiang Hao, Sriram Baireddy, Emily R. Bartusiak, Latisha Konz, Kevin J. LaTourette, Michael Gribbons, Moses W. Chan, Edward J. Delp, Mary L. Comer

202165 citationsDOI

Abstract

When a disaster strikes, accurate situational information and a fast, effective response are critical to save lives. High resolution satellite images enable emergency responders to estimate the location, cause, and severity of damage. In this paper, we present a Siam-U-Net-Attn model with an attention mechanism to assess the damage level of buildings given a pair of satellite images showing a scene before and after a disaster. We evaluate the proposed method on xView2, a building damage assessment dataset, and demonstrate that the proposed approach achieves accurate damage scale classification and building segmentation.

Topics & Concepts

Computer scienceSatelliteSatellite imageryScale (ratio)Situation awarenessSegmentationEmergency responseArtificial intelligenceSituation analysisRemote sensingComputer visionData miningCartographyGeologyGeographyEngineeringMarketingBusinessAerospace engineeringMedical emergencyMedicineRemote-Sensing Image ClassificationVideo Surveillance and Tracking MethodsRemote Sensing and Land Use