Building Damage Annotation on Post-Hurricane Satellite Imagery Based on Convolutional Neural Networks

TL;DR

This paper presents a CNN-based method for rapid building damage assessment from post-hurricane satellite images, achieving over 97% accuracy in classifying flooded or damaged buildings, thus aiding emergency response.

Contribution

It introduces a CNN model trained from scratch for damage classification, improving efficiency over traditional ground surveys and comparing favorably with existing neural networks.

Findings

Over 97% classification accuracy on case study data

Effective use of satellite imagery and crowd-sourced labels

Potential for rapid damage assessment in disaster response

Abstract

After a hurricane, damage assessment is critical to emergency managers for efficient response and resource allocation. One way to gauge the damage extent is to quantify the number of flooded/damaged buildings, which is traditionally done by ground survey. This process can be labor-intensive and time-consuming. In this paper, we propose to improve the efficiency of building damage assessment by applying image classification algorithms to post-hurricane satellite imagery. At the known building coordinates (available from public data), we extract square-sized images from the satellite imagery to create training, validation, and test datasets. Each square-sized image contains a building to be classified as either 'Flooded/Damaged' (labeled by volunteers in a crowd-sourcing project) or 'Undamaged'. We design and train a convolutional neural network from scratch and compare it with an existing neural network used widely for common object classification. We demonstrate the promise of our damage annotation model (over 97% accuracy) in the case study of building damage assessment in the Greater Houston area affected by 2017 Hurricane Harvey.