Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitemarte.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier3ERPFQRTBW/348RTMS
Repositorydpi.inpe.br/sbsr@80/2008/11.18.13.07
Last Update2009:04.17.19.17.49 (UTC) administrator
Metadata Repositorydpi.inpe.br/sbsr@80/2008/11.18.13.07.04
Metadata Last Update2022:07.07.03.53.35 (UTC) administrator
Secondary KeyINPE-15872-PRE/10482
ISBN978-85-17-00044-7
Citation KeyFeitosaCosFreCamAlm:2009:AvMéGe
TitleUma Avaliação de Métodos Genéticos para Ajuste de Parâmetros de Segmentação
FormatDVD, On-line.
Year2009
Access Date2024, May 18
Secondary TypePRE CN
Number of Files1
Size1812 KiB
2. Context
Author1 Feitosa, Raul Queiroz
2 Costa, Gilson Alexandre Ostwald Pedro da
3 Fredrich, Cecília Maria Buarque
4 Camargo, Flávio Fortes
5 Almeida, Cláudia Maria de
Resume Identifier1
2
3
4
5 8JMKD3MGP5W/3C9JGS3
Group1
2
3
4 DSR-OBT-INPE-MCT-BR
5 DSR-OBT-INPE-MCT-BR
Affiliation1 Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)
2 Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)
3 Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)
4 Instituto Nacional de Pesquisas Espaciais (INPE)
5 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 raul@ele.puc-rio.br
2 gilson@ele.puc-rio.br
3 buarque@ele.puc-rio.br
4 fortes@dsr.inpe.br
5 almeida@dsr.inpe.br
EditorEpiphanio, José Carlos Neves
Galvão, Lênio Soares
e-Mail Addresserich@sid.inpe.br
Conference NameSimpósio Brasileiro de Sensoriamento Remoto, 14 (SBSR)
Conference LocationNatal
Date25-30 abr. 2009
PublisherInstituto Nacional de Pesquisas Espaciais (INPE)
Publisher CitySão José dos Campos
Pages6875-6882
Book TitleAnais
Tertiary TypeArtigo
Organization{Instituto Nacional de Pesquisas Espaciais (INPE)}
History (UTC)2008-11-18 20:34:07 :: gilson@ele.puc-rio.br -> lise@dpi.inpe.br ::
2008-12-04 12:24:39 :: lise@dpi.inpe.br -> sbsr ::
2009-02-19 15:40:07 :: sbsr -> administrator ::
2009-04-06 15:45:36 :: administrator -> lise@dpi.inpe.br ::
2009-04-17 19:17:49 :: lise@dpi.inpe.br -> administrator ::
2009-05-28 13:08:15 :: administrator -> lise@dpi.inpe.br ::
2009-06-09 19:31:48 :: lise@dpi.inpe.br -> marciana ::
2009-06-22 13:55:32 :: marciana -> erich@sid.inpe.br ::
2009-06-23 18:12:06 :: erich@sid.inpe.br -> administrator ::
2009-08-05 02:06:12 :: administrator -> erich@sid.inpe.br ::
2010-05-14 02:40:51 :: erich@sid.inpe.br -> marciana ::
2011-02-16 14:17:26 :: marciana -> administrator :: 2009
2022-07-07 03:53:35 :: administrator -> :: 2009
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsremote sensing
image processing
genetic algorithms
optimization methods
sensoriamento remoto
processamento de imagens
algoritmos genéticos
métodos de otimização
AbstractMost segmentation algorithms have explicit parameters that must be properly set in order to produce the desired outcome, and the definition of suitable parameter values is usually a complex, time consuming task. In Costa et al. (2008), a supervised, semi-automatic parameter adaptation method based on a Genetic Algorithm (GA) was proposed. Given an initial set of reference object samples, the method searches the parameter space for (near) for values that will produce segments as similar as possible to the reference. The specific formulation of the objective function, which provides the similarity measure used in the method, privileged applications in which the objects to be segmented were homogeneous. This work addresses this issue, extending the previous work by proposing a novel objective function which considers the objects of interest to be inhomogeneous, though formed by an assembly of homogeneous parts. The software prototype that implemented the previous approach was extended with the new objective function, and an experimental evaluation of the two objective functions were performed taking into account three different segmentation algorithms and five different object classes. The analysis of the results obtained with both objective functions provides guidelines for the selection of the function to be used in different applications.
AreaSRE
TypeProcessamento de Imagens
Arrangementurlib.net > DIDSR > Uma Avaliação de...
doc Directory Contentaccess
source Directory Content
SBSR_2009_Feitosa_et_al.pdf 18/11/2008 18:34 1.7 MiB
SBSR_Feitosa_et_al.pdf 18/11/2008 11:07 1.9 MiB
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/3ERPFQRTBW/348RTMS
zipped data URLhttp://urlib.net/zip/3ERPFQRTBW/348RTMS
Languagept
Target File6875-6882.pdf
User Groupadministrator
gilson@ele.puc-rio.br
lise@dpi.inpe.br
marciana
erich@sid.inpe.br
administrator
Reader Groupadministrator
gilson@ele.puc-rio.br
Visibilityshown
5. Allied materials
Mirror Repositorydpi.inpe.br/marte1@80/2009/05.26.17.02
Next Higher Units8JMKD3MGPCW/3ER446E
Host Collectiondpi.inpe.br/netuno@1905/2006/07.17.20.18
dpi.inpe.br/banon/2003/12.10.19.30
6. Notes
Mark1
Empty Fieldsarchivingpolicy archivist callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition issn label lineage nextedition notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readpermission rightsholder schedulinginformation secondarydate secondarymark serieseditor shorttitle sponsor tertiarymark url versiontype volume


Close