UAVs in disaster management: application of integrated aerial Imagery and convolutional neural network for flood detection

Munawar, Hafiz Suliman and Ullah, Fahim ORCID: https://orcid.org/0000-0002-6221-1175 and Qayyum, Siddra and Khan, Sara Imran and Mojtahedi, Mohammad (2021) UAVs in disaster management: application of integrated aerial Imagery and convolutional neural network for flood detection. Sustainability, 13 (14):7547. pp. 1-22.

[img]
Preview
Text (Published Version)
sustainability-13-07547-v2.pdf
Available under License Creative Commons Attribution 4.0.

Download (6MB) | Preview

Abstract

Floods have been a major cause of destruction, instigating fatalities and massive damageto the infrastructure and overall economy of the affected country. Flood-related devastation resultsin the loss of homes, buildings, and critical infrastructure, leaving no means of communicationor travel for the people stuck in such disasters. Thus, it is essential to develop systems that candetect floods in a region to provide timely aid and relief to stranded people, save their livelihoods,homes, and buildings, and protect key city infrastructure. Flood prediction and warning systemshave been implemented in developed countries, but the manufacturing cost of such systems istoo high for developing countries. Remote sensing, satellite imagery, global positioning system,and geographical information systems are currently used for flood detection to assess the flood-related damages. These techniques use neural networks, machine learning, or deep learning methods.However, unmanned aerial vehicles (UAVs) coupled with convolution neural networks have not beenexplored in these contexts to instigate a swift disaster management response to minimize damage toinfrastructure. Accordingly, this paper uses UAV-based aerial imagery as a flood detection methodbased on Convolutional Neural Network (CNN) to extract flood-related features from the imagesof the disaster zone. This method is effective in assessing the damage to local infrastructures in thedisaster zones. The study area is based on a flood-prone region of the Indus River in Pakistan, whereboth pre-and post-disaster images are collected through UAVs. For the training phase,2150 imagepatches are created by resizing and cropping the source images. These patches in the training datasettrain the CNN model to detect and extract the regions where a flood-related change has occurred.The model is tested against both pre-and post-disaster images to validate it, which has positive flooddetection results with an accuracy of 91%. Disaster management organizations can use this modelto assess the damages to critical city infrastructure and other assets worldwide to instigate properdisaster responses and minimize the damages. This can help with the smart governance of the citieswhere all emergent disasters are addressed promptly


Statistics for USQ ePrint 42926
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 Jul 2013 -)
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 Jul 2013 -)
Date Deposited: 30 Jul 2021 00:32
Last Modified: 14 Sep 2021 01:44
Uncontrolled Keywords: convolutional neural networks; disaster management; aerial imagery; flood detection; unmanned aerial vehicles
Fields of Research (2008): 12 Built Environment and Design > 1299 Other Built Environment and Design > 129999 Built Environment and Design not elsewhere classified
10 Technology > 1099 Other Technology > 109999 Technology not elsewhere classified
Fields of Research (2020): 33 BUILT ENVIRONMENT AND DESIGN > 3302 Building > 330201 Automation and technology in building and construction
Identification Number or DOI: https://doi.org/10.3390/su13147547
URI: http://eprints.usq.edu.au/id/eprint/42926

Actions (login required)

View Item Archive Repository Staff Only