Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System
Estimating the damaged area after a forest fire is important for responding to this natural catastrophe. With the support of aerial remote sensing, typically with unmanned aerial vehicles (UAVs), the aerial imagery of forest-fire areas can be easily obtained; however, retrieving the burnt area from...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/24/4169 |
_version_ | 1797544042138959872 |
---|---|
author | Dai Quoc Tran Minsoo Park Daekyo Jung Seunghee Park |
author_facet | Dai Quoc Tran Minsoo Park Daekyo Jung Seunghee Park |
author_sort | Dai Quoc Tran |
collection | DOAJ |
description | Estimating the damaged area after a forest fire is important for responding to this natural catastrophe. With the support of aerial remote sensing, typically with unmanned aerial vehicles (UAVs), the aerial imagery of forest-fire areas can be easily obtained; however, retrieving the burnt area from the image is still a challenge. We implemented a new approach for segmenting burnt areas from UAV images using deep learning algorithms. First, the data were collected from a forest fire in Andong, the Republic of Korea, in April 2020. Then, the proposed two-patch-level deep-learning models were implemented. A patch-level 1 network was trained using the UNet++ architecture. The output prediction of this network was used as a position input for the second network, which used UNet. It took the reference position from the first network as its input and refined the results. Finally, the final performance of our proposed method was compared with a state-of-the-art image-segmentation algorithm to prove its robustness. Comparative research on the loss functions was also performed. Our proposed approach demonstrated its effectiveness in extracting burnt areas from UAV images and can contribute to estimating maps showing the areas damaged by forest fires. |
first_indexed | 2024-03-10T13:54:51Z |
format | Article |
id | doaj.art-0505471ddcfb4fb7a36fbe5ff0120e09 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T13:54:51Z |
publishDate | 2020-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-0505471ddcfb4fb7a36fbe5ff0120e092023-11-21T01:42:19ZengMDPI AGRemote Sensing2072-42922020-12-011224416910.3390/rs12244169Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management SystemDai Quoc Tran0Minsoo Park1Daekyo Jung2Seunghee Park3Department of Civil, Architecture and Environmental System Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Civil, Architecture and Environmental System Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Convergence Engineering for Future City, Sungkyunkwan University, Suwon 16419, KoreaSchool of Civil, Architectural Engineering and Landscape Architecture, Sungkyunkwan University, Suwon 16419, KoreaEstimating the damaged area after a forest fire is important for responding to this natural catastrophe. With the support of aerial remote sensing, typically with unmanned aerial vehicles (UAVs), the aerial imagery of forest-fire areas can be easily obtained; however, retrieving the burnt area from the image is still a challenge. We implemented a new approach for segmenting burnt areas from UAV images using deep learning algorithms. First, the data were collected from a forest fire in Andong, the Republic of Korea, in April 2020. Then, the proposed two-patch-level deep-learning models were implemented. A patch-level 1 network was trained using the UNet++ architecture. The output prediction of this network was used as a position input for the second network, which used UNet. It took the reference position from the first network as its input and refined the results. Finally, the final performance of our proposed method was compared with a state-of-the-art image-segmentation algorithm to prove its robustness. Comparative research on the loss functions was also performed. Our proposed approach demonstrated its effectiveness in extracting burnt areas from UAV images and can contribute to estimating maps showing the areas damaged by forest fires.https://www.mdpi.com/2072-4292/12/24/4169forestryfiresimage processingobject segmentation |
spellingShingle | Dai Quoc Tran Minsoo Park Daekyo Jung Seunghee Park Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System Remote Sensing forestry fires image processing object segmentation |
title | Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System |
title_full | Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System |
title_fullStr | Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System |
title_full_unstemmed | Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System |
title_short | Damage-Map Estimation Using UAV Images and Deep Learning Algorithms for Disaster Management System |
title_sort | damage map estimation using uav images and deep learning algorithms for disaster management system |
topic | forestry fires image processing object segmentation |
url | https://www.mdpi.com/2072-4292/12/24/4169 |
work_keys_str_mv | AT daiquoctran damagemapestimationusinguavimagesanddeeplearningalgorithmsfordisastermanagementsystem AT minsoopark damagemapestimationusinguavimagesanddeeplearningalgorithmsfordisastermanagementsystem AT daekyojung damagemapestimationusinguavimagesanddeeplearningalgorithmsfordisastermanagementsystem AT seungheepark damagemapestimationusinguavimagesanddeeplearningalgorithmsfordisastermanagementsystem |