Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitemtc-m16c.sid.inpe.br
Identifier8JMKD3MGPDW34P/45U7H3L
Repositorysid.inpe.br/mtc-m16c/2021/12.09.11.36
Last Update2021:12.09.11.36.57 (UTC) simone
Metadata Repositorysid.inpe.br/mtc-m16c/2021/12.09.11.36.57
Metadata Last Update2023:01.30.13.07.56 (UTC) administrator
ISSN2179-4847
Citation KeyMirandaMaxSanKörFon:2021:ClWaVo
TitleClassification of the water volume of dams using heterogeneous remote sensing images through a deep convolutional neural network
FormatOn-line.
Year2021
Access Date2024, May 09
Secondary TypePRE CN
Number of Files1
Size1767 KiB
2. Context
Author1 Miranda, Mateus de Souza
2 Maximiano, Renato de Sousa
3 Santiago Júnior, Valdivino Alexandre de
4 Körting, Thales Sehn
5 Fonseca, Leila Maria Garcia
Group1
2
3 COPDT-CGIP-INPE-MCTI-GOV-BR
4 DIOTG-CGCT-INPE-MCTI-GOV-BR
5 DIOTG-CGCT-INPE-MCTI-GOV-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Instituto Nacional de Pesquisas Espaciais (INPE)
3 Instituto Nacional de Pesquisas Espaciais (INPE)
4 Instituto Nacional de Pesquisas Espaciais (INPE)
5 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 mateus.miranda@inpe.br
2 renato.maximiano@inpe.br
3 valdivino.santiago@inpe.br
4 thales.korting@inpe.br
5 leila.fonseca@inpe.br
EditorVinhas, Lubia (INPE)
Graça, Alan J. Salomão (UERJ)
Conference NameSimpósio Brasileiro de Geoinformática, 22 (GEOINFO)
Conference LocationOn-line
Date29 nov. a 02 dez. 2021
PublisherInstituto Nacional de Pesquisas Espaciais (INPE)
Publisher CitySão José dos Campos
Book TitleAnais
Tertiary TypeFull paper
History (UTC)2021-12-09 11:37:48 :: simone -> administrator :: 2021
2021-12-16 15:23:31 :: administrator -> simone :: 2021
2021-12-16 18:04:38 :: simone -> administrator :: 2021
2023-01-30 13:07:56 :: administrator -> simone :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
AbstractDeep Convolutional Neural Networks (DCNN) have played an important role in several application domains and also in remote sensing image classification and object detection. In this article, we extend a previously proposed model, used to classify forest areas as preserved or non-preserved, in order to classify the water volume of dams in the state of Sao Paulo, Brazil, using remote sensing images. Our revised DCNN addresses a multi-class classification problem while our previous one was devised for binary classification. Moreover, our model relies on heterogeneous images, considering different sensors and also different spatial resolutions regarding the data sets. Results show that the overall accuracy of our model was 85.56% considering images from the Atibainha and Jaguari dams of the Cantareira water supply system to compose the testing set, demonstrating the feasibility of our approach to these types of applications. This is an indication of the good generalization capabilities of our model.
AreaSRE
Arrangement 1urlib.net > BDMCI > Fonds > Produção a partir de 2021 > CGCT > Classification of the...
Arrangement 2urlib.net > BDMCI > Fonds > Produção a partir de 2021 > CGIP > Classification of the...
Arrangement 3urlib.net > BDMCI > Fonds > GEOINFO > XXII GEOINFO > Classification of the...
Arrangement 4urlib.net > BDMCI > Fonds > Produção a partir de 2021 > CGCT > XXII GEOINFO > Classification of the...
Arrangement 5urlib.net > BDMCI > Fonds > GEOINFO > Coleção GEOINFO > Classification of the...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPDW34P/45U7H3L
zipped data URLhttp://urlib.net/zip/8JMKD3MGPDW34P/45U7H3L
Languageen
Target FileMiranda_classificaction.pdf
User Groupsimone
Visibilityshown
Copyright Licenseurlib.net/www/2012/11.12.15.19
Rightsholderoriginalauthor yes
5. Allied materials
Next Higher Units8JMKD3MGPCW/46KUATE
8JMKD3MGPCW/46KUES5
8JMKD3MGPDW34P/462CM9S
8JMKD3MGPDW34P/48F29JE
Citing Item Listsid.inpe.br/mtc-m16c/2023/01.30.13.05 6
sid.inpe.br/bibdigital/2022/04.03.22.23 1
sid.inpe.br/mtc-m16c/2021/12.16.19.25 1
Host Collectionsid.inpe.br/mtc-m18@80/2008/03.17.15.17
6. Notes
Empty Fieldsarchivingpolicy archivist callnumber contenttype copyholder creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition holdercode isbn keywords label lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid schedulinginformation secondarydate secondarykey secondarymark serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
7. Description control
e-Mail (login)simone
update 


Close