Repository logo
 
Publication

Fire segmentation using a Deeplabv3+ architecture

2020-09-20Conference object Restricted access
Simple item page
dc.contributor.authorHarkat, Houda
dc.contributor.authorNascimento, Jose
dc.contributor.authorBernardino, Alexandre
dc.date.accessioned2020-11-23T15:56:35Z
dc.date.available2020-11-23T15:56:35Z
dc.date.issued2020-09-20
dc.description.abstractIn the last decade, the number of forest _res events is growing due to the fast change of earth's climate. Hence, more automatized _re _ghting actions had become necessary. Deep learning had drawn interesting results for pixel level classi_cation for smoke detection, but few systems are proposed for _re ame detection. In this paper, a semantic segmentation approach using Deeplabv3+ architecture for wild_re detection is proposed. The network uses Deeplabv3 architecture as encoder and Atrous Spatial Pyramid Pooling (ASPP) which allows to encode multi-scale information and boost the network performance. In fact, the ASPP block concatenates a stack of parallel Atrous convolutions with graduating rates, which produces a multi-scale feature map that is further resized. The tests were performed on a public dataset, Corsican _re dataset, which contains 1135 RGB images and 640 infrared pictures. The experiments were conducted on two customized datasets, one using the whole dataset within a single channel information (red and infra-red), and another using only the RGB image set that contains information coded in 3 channels. The used dataset is unbalanced, which could induce high precision with very low sensitivity. Therefore, to measure the performance, Dice similarity and Tversky loss functions with cross-entropy are adopted. The capability of Deeplabv3+ was tested with two di_erent backbones, ResNet-18 and ResNet-50, and compared to a very simple Convolutional Neural Network (CNN) architecture with dilated convolution. Four di_erent metrics were used to evaluate the segmentation capability: Accuracy, mean Intersection over Union (IoU), Mean Boundary F1 (BF) Score, and Mean Dice coe_cient. The experimental results demonstrate that the Deeplabv3+ with ResNet-50 backbone and a loss function type Dice or Tversky can accurately detect the _re ame. The given results are very encouraging for further study using deep learning approaches.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationHARKAT, H.; NASCIMENTO, José; BERNARDINO, A. – Fire segmentation using a Deeplabv3+ architecture. In Proc. SPIE 11533, Image and Signal Processing for Remote Sensing XXVI. United Kingdom: SPIE, 2020. ISBN 978-151-063-879-2. Pp. 115330M-1-115330M-12pt_PT
dc.identifier.doi10.1117/12.2573902pt_PT
dc.identifier.isbn978-151-063-879-2
dc.identifier.urihttp://hdl.handle.net/10400.21/12391
dc.language.isoengpt_PT
dc.publisherSPIEpt_PT
dc.relationUIDB/50008/2020 - IT/FCTpt_PT
dc.subjectWildfirept_PT
dc.subjectRGB imagespt_PT
dc.subjectSegmentationpt_PT
dc.subjectDilated convolutionpt_PT
dc.subjectAtrous Spatial Pyramid Pooling (ASPP)pt_PT
dc.titleFire segmentation using a Deeplabv3+ architecturept_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.conferencePlace21-25 September 2020 - United Kingdompt_PT
oaire.citation.endPage115330M-12pt_PT
oaire.citation.startPage115330M-1pt_PT
oaire.citation.titleImage and Signal Processing for Remote Sensing XXVIpt_PT
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
rcaap.rightsclosedAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicatione57b2206-2eff-4c6e-8a7f-680de110bffc
relation.isAuthorOfPublicationc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isAuthorOfPublication801a33d7-b93d-4502-9d11-c3eff61cc310
relation.isAuthorOfPublication.latestForDiscoverye57b2206-2eff-4c6e-8a7f-680de110bffc

Files

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

Collections

ISEL - Eng. Elect. Tel. Comp. - Comunicações