1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | marte.sid.inpe.br |
Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identifier | 3ERPFQRTBW/348RTMS |
Repository | dpi.inpe.br/sbsr@80/2008/11.18.13.07 |
Last Update | 2009:04.17.19.17.49 (UTC) administrator |
Metadata Repository | dpi.inpe.br/sbsr@80/2008/11.18.13.07.04 |
Metadata Last Update | 2022:07.07.03.53.35 (UTC) administrator |
Secondary Key | INPE-15872-PRE/10482 |
ISBN | 978-85-17-00044-7 |
Citation Key | FeitosaCosFreCamAlm:2009:AvMéGe |
Title | Uma Avaliação de Métodos Genéticos para Ajuste de Parâmetros de Segmentação |
Format | DVD, On-line. |
Year | 2009 |
Access Date | 2024, May 18 |
Secondary Type | PRE CN |
Number of Files | 1 |
Size | 1812 KiB |
|
2. Context | |
Author | 1 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 Identifier | 1 2 3 4 5 8JMKD3MGP5W/3C9JGS3 |
Group | 1 2 3 4 DSR-OBT-INPE-MCT-BR 5 DSR-OBT-INPE-MCT-BR |
Affiliation | 1 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 Address | 1 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 |
Editor | Epiphanio, José Carlos Neves Galvão, Lênio Soares |
e-Mail Address | erich@sid.inpe.br |
Conference Name | Simpósio Brasileiro de Sensoriamento Remoto, 14 (SBSR) |
Conference Location | Natal |
Date | 25-30 abr. 2009 |
Publisher | Instituto Nacional de Pesquisas Espaciais (INPE) |
Publisher City | São José dos Campos |
Pages | 6875-6882 |
Book Title | Anais |
Tertiary Type | Artigo |
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 Stage | completed |
Transferable | 1 |
Keywords | remote sensing image processing genetic algorithms optimization methods sensoriamento remoto processamento de imagens algoritmos genéticos métodos de otimização |
Abstract | Most 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. |
Area | SRE |
Type | Processamento de Imagens |
Arrangement | urlib.net > DIDSR > Uma Avaliação de... |
doc Directory Content | access |
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 Content | there are no files |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/3ERPFQRTBW/348RTMS |
zipped data URL | http://urlib.net/zip/3ERPFQRTBW/348RTMS |
Language | pt |
Target File | 6875-6882.pdf |
User Group | administrator gilson@ele.puc-rio.br lise@dpi.inpe.br marciana erich@sid.inpe.br administrator |
Reader Group | administrator gilson@ele.puc-rio.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | dpi.inpe.br/marte1@80/2009/05.26.17.02 |
Next Higher Units | 8JMKD3MGPCW/3ER446E |
Host Collection | dpi.inpe.br/netuno@1905/2006/07.17.20.18 dpi.inpe.br/banon/2003/12.10.19.30 |
|
6. Notes | |
Mark | 1 |
Empty Fields | archivingpolicy 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 |
|