Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitemarte.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Repositorydpi.inpe.br/sbsr@80/2007/01.17.12.22
Last Update2007:03.01.11.25.36 (UTC) administrator
Metadata Repositorydpi.inpe.br/sbsr@80/2007/01.17.12.22.33
Metadata Last Update2018:06.06.02.38.02 (UTC) administrator
ISBN978-85-17-00031-7
Citation KeyBentzEbecPoli:2007:IdAuEv
TitleIdentificação automática de eventos ambientais costeiros e oceânicos detectáveis em imagens de radares orbitais
FormatCD-ROM, On-line.
Year2007
Access Date2025, May 09
Secondary TypePRE CN
Number of Files1
Size235 KiB
2. Context
Author1 Bentz, Cristina Maria
2 Ebecken, Nelson F. F.
3 Politano, Alexandre Tadeu
Affiliation1 PETROBRAS/CENPES - Centro de Pesquisas
2 Universidade Federal do Rio de janeiro – UFRJ/COPPE
3 PETROBRAS/CENPES - Centro de Pesquisas
Author e-Mail Address1 cris@petrobras.com.br
2 nelson@ntt.ufrj.br
3 politano.gorceix@petrobras.com.br
EditorEpiphanio, José Carlos Neves
Galvão, Lênio Soares
Fonseca, Leila Maria Garcia
e-Mail Addresslise@dpi.inpe.br
Conference NameSimpósio Brasileiro de Sensoriamento Remoto, 13 (SBSR).
Conference LocationFlorianópolis
Date21-26 abr. 2007
PublisherInstituto Nacional de Pesquisas Espaciais (INPE)
Publisher CitySão José dos Campos
Pages1967-1974
Book TitleAnais
Tertiary TypeArtigo
OrganizationInstituto Nacional de Pesquisas Espaciais (INPE)
History (UTC)2007-01-17 12:22:33 :: lise@dpi.inpe.br -> sbsr ::
2007-01-17 15:32:19 :: sbsr -> lise@dpi.inpe.br ::
2007-01-17 23:41:45 :: lise@dpi.inpe.br -> administrator ::
2009-06-30 14:32:50 :: administrator -> erich@sid.inpe.br ::
2009-08-04 18:30:40 :: erich@sid.inpe.br -> administrator ::
2009-08-05 01:47:02 :: administrator -> erich@sid.inpe.br ::
2010-05-14 02:44:12 :: erich@sid.inpe.br -> marciana ::
2011-02-16 14:07:05 :: marciana -> administrator :: 2007
2018-06-06 02:38:02 :: administrator -> :: 2007
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordssynthetic aperture radar
oil spill and ocean features detection
classification
machine learning
radares de abertura sintética
detecção de óleo e feições oceânicas
classificação
aprendizagem de máquina
AbstractA classification procedure using machine learning algorithms was developed to identify different types of pollution and meteo-oceanographic events, detected in SAR (Synthetic Aperture Radar) images. The classification is done in two steps: first the features area classified in one of two classes - oil pollution or meteooceanographic event. In the second step, the identification of tree classes of oil pollution and four classes or meteo-oceanographic events is done. Spectral, geometric, and contextual features are evaluated. The classification training and test was done using examples extracted from 402 RADARSAT-1 images acquired in Campos Basin, southeastern Brazilian coast. Different configurations of decision trees, neural networks and support vector machines are tested.
AreaSRE
TypeGeologia
doc Directory Contentaccess
source Directory Content
sbsr_tese_cristina bentz.pdf 17/01/2007 10:22 127.4 KiB 
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/dpi.inpe.br/sbsr@80/2007/01.17.12.22
zipped data URLhttp://urlib.net/zip/dpi.inpe.br/sbsr@80/2007/01.17.12.22
Languagept
Target File1967-1974.pdf
User Grouplise@dpi.inpe.br
erich@sid.inpe.br
administrator
Reader Groupadministrator
lise@dpi.inpe.br
Visibilityshown
5. Allied materials
Mirror Repositorydpi.inpe.br/netuno@1905/2006/07.17.20.18.49
Host Collectiondpi.inpe.br/banon/2003/12.10.19.30
6. Notes
Mark1
Empty Fieldsarchivingpolicy archivist callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition group identifier issn label lineage nextedition nexthigherunit notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor shorttitle sponsor tertiarymark url versiontype volume


Close