Disaster impact analysis in Africa: EDDA - UAV building damage dataset of rural and urban Mozambique

Damjan Hatic; Markus Rauhut; Vladyslav Polushko; Marco Codastefano; Sophia Rosa; Patrick McKay; Francesco Stompanato; Antonio Beleza; Hans Hagen

doi:10.1117/12.2683882

19 October 2023 Disaster impact analysis in Africa: EDDA - UAV building damage dataset of rural and urban Mozambique

Damjan Hatic, Markus Rauhut, Vladyslav Polushko, Marco Codastefano, Sophia Rosa, Patrick McKay, Francesco Stompanato, Antonio Beleza, Hans Hagen

Author Affiliations +

Proceedings Volume 12734, Earth Resources and Environmental Remote Sensing/GIS Applications XIV; 127340G (2023) https://doi.org/10.1117/12.2683882
Event: SPIE Remote Sensing, 2023, Amsterdam, Netherlands

Abstract

Natural disasters have devastating effects on communities, necessitating swift and accurate damage assessment. Manual assessment methods are time-consuming and costly, emphasizing the significance of semiautomatic approaches employing remote sensing and drone data. However, current datasets primarily focus on Western countries’ infrastructure, lacking information on damaged buildings in other regions specifically Africa. To bridge this gap, we present the EDDA dataset, comprising orthorectified mosaic images of rural and urban areas in Mozambique affected by Cyclone Idai. In this study, we utilize the EDDA dataset to evaluate the applicability of the lightweight object detection model YOLOv7 for efficient and timely disaster response. Testing the dataset with YOLOv7, assessed the datasets suitability for the task of building damage object detection under different class compositions and training data preprocessing configurations. Results showed promising results when utilizing Yolov7 as a building detector regardless of damage class, as a region proposal network, while building damage recognition requires additional research.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Damjan Hatic, Markus Rauhut, Vladyslav Polushko, Marco Codastefano, Sophia Rosa, Patrick McKay, Francesco Stompanato, Antonio Beleza, and Hans Hagen "Disaster impact analysis in Africa: EDDA - UAV building damage dataset of rural and urban Mozambique", Proc. SPIE 12734, Earth Resources and Environmental Remote Sensing/GIS Applications XIV, 127340G (19 October 2023); https://doi.org/10.1117/12.2683882

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available