Hurricane Building Damage Assessment using Post-Disaster UAV Data

Abstract

Unmanned aerial vehicle (UAV) systems are becoming increasingly important since fine spatial and high temporal resolution data have been unobtainable from traditional remote sensing platforms. Advanced UAV data can provide a great opportunity for disaster monitoring, including building damage assessment. Hurricane Harvey struck southern Texas, U.S.A, on August 26, 2017, causing catastrophic flooding and storm damage. We visited Holiday Beach, which suffered severe building damage, and conducted UAV surveying for building damage assessment. In this study, a region growing scheme was proposed to estimate the building damage, considering building elevation change and the spectral difference of debris. In addition, different weight coefficients of a digital elevation model (DEM) were investigated. The results showed that the proposed method can be used for high-definition building damage assessment through accurate detection of the intact building regions.