Repository logo
 
Publication

Assessing the impact of the loss function and encoder architecture for fire aerial images segmentation using deeplabv3+

2022-04-22Journal article Open access
Simple item page
dc.contributor.authorHarkat, Houda
dc.contributor.authorNascimento, Jose
dc.contributor.authorBernardino, Alexandre
dc.contributor.authorAhmed, Hasmath Farhana Thariq
dc.date.accessioned2022-05-31T09:38:50Z
dc.date.available2022-05-31T09:38:50Z
dc.date.issued2022-04-22
dc.description.abstractWildfire early detection and prevention had become a priority. Detection using Internet of Things (IoT) sensors, however, is expensive in practical situations. The majority of present wildfire detection research focuses on segmentation and detection. The developed machine learning models deploy appropriate image processing techniques to enhance the detection outputs. As a result, the time necessary for data processing is drastically reduced, as the time required rises exponentially with the size of the captured pictures. In a real-time fire emergency, it is critical to notice the fire pixels and warn the firemen as soon as possible to handle the problem more quickly. The present study addresses the challenge mentioned above by implementing an on-site detection system that detects fire pixels in real-time in the given scenario. The proposed approach is accomplished using Deeplabv3+, a deep learning architecture that is an enhanced version of an existing model. However, present work fine-tuned the Deeplabv3 model through various experimental trials that have resulted in improved performance. Two public aerial datasets, the Corsican dataset and FLAME, and one private dataset, Firefront Gestosa, were used for experimental trials in this work with different backbones. To conclude, the selected model trained with ResNet-50 and Dice loss attains a global accuracy of 98.70%, a mean accuracy of 89.54%, a mean IoU 86.38%, a weighted IoU of 97.51%, and a mean BF score of 93.86%.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationHARKAT, Houda; [et al] – Assessing the impact of the loss function and encoder architecture for fire aerial images segmentation using deeplabv3+. Remote Sensing. eISSN 2072-4292. Vol. 14, N.º 9 (2022), pp. 1-22.pt_PT
dc.identifier.doi10.3390/rs14092023pt_PT
dc.identifier.eissn2072-4292
dc.identifier.urihttp://hdl.handle.net/10400.21/14678
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherMDPIpt_PT
dc.relationInstituto de Telecomunicações
dc.relation.publisherversionhttps://www.mdpi.com/2072-4292/14/9/2023pt_PT
dc.subjectFirept_PT
dc.subjectFirefront_gestosapt_PT
dc.subjectDeep learningpt_PT
dc.subjectDeeplabv3+pt_PT
dc.subjectBackbonept_PT
dc.subjectDice losspt_PT
dc.subjectImage processingpt_PT
dc.titleAssessing the impact of the loss function and encoder architecture for fire aerial images segmentation using deeplabv3+pt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstituto de Telecomunicações
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FSSI%2F0096%2F2017/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50008%2F2020/PT
oaire.citation.endPage22pt_PT
oaire.citation.issue9pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleRemote Sensingpt_PT
oaire.citation.volume14pt_PT
oaire.fundingStream3599-PPCDT
oaire.fundingStream6817 - DCRRNI ID
person.familyNameHarkat
person.familyNameNascimento
person.familyNameBernardino
person.givenNameHouda
person.givenNameJose
person.givenNameAlexandre
person.identifierA-9436-2019
person.identifierG-1316-2010
person.identifier.ciencia-id991F-2F5C-2433
person.identifier.ciencia-id6912-6F61-1964
person.identifier.ciencia-id1118-49F0-B28C
person.identifier.orcid0000-0002-7827-1527
person.identifier.orcid0000-0002-5291-6147
person.identifier.orcid0000-0003-3991-1269
person.identifier.ridE-6212-2015
person.identifier.scopus-author-id56736693300
person.identifier.scopus-author-id55920018000
person.identifier.scopus-author-id7003407125
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicatione57b2206-2eff-4c6e-8a7f-680de110bffc
relation.isAuthorOfPublicationc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isAuthorOfPublication801a33d7-b93d-4502-9d11-c3eff61cc310
relation.isAuthorOfPublication.latestForDiscoveryc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isProjectOfPublicationbac32016-be68-4b35-9d42-fabc0409716f
relation.isProjectOfPublication75f6c6d9-5365-4d88-a66f-00492a6ffb5a
relation.isProjectOfPublication.latestForDiscovery75f6c6d9-5365-4d88-a66f-00492a6ffb5a

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Assessing_JMPNascimento.pdf
Size:
8.39 MB
Format:
Adobe Portable Document Format
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Artigos