Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitemarte2.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP6W34M/3JM4K9E
Repositorysid.inpe.br/marte2/2015/06.15.16.59
Last Update2015:06.15.16.59.08 (UTC) banon
Metadata Repositorysid.inpe.br/marte2/2015/06.15.16.59.08
Metadata Last Update2018:06.06.03.28.04 (UTC) administrator
ISBN978-85-17-0076-8
Label1750
Citation KeyAndradeFranAlme:2015:DeClPa
TitleDesempenho de classificadores paramétrico e não paramétrico na classificação da fisionomia vegetal
FormatInternet
Year2015
Access Date2024, May 18
Secondary TypePRE CN
Number of Files1
Size337 KiB
2. Context
Author1 Andrade, Alexandre Curvelo de
2 Francisco, Cristiane Nunes
3 Almeida, Cláudia Maria de
Resume Identifier1
2
3 8JMKD3MGP5W/3C9JGS3
Group1
2
3 DSR-OBT-INPE-MCTI-GOV-BR
Affiliation1
2
3 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 curvelo@amskepler.com
EditorGherardi, Douglas Francisco Marcolino
Aragão, Luiz Eduardo Oliveira e Cruz de
e-Mail Addresswanderf@dsr.inpe.br
Conference NameSimpósio Brasileiro de Sensoriamento Remoto, 17 (SBSR)
Conference LocationJoão Pessoa
Date25-29 abr. 2015
PublisherInstituto Nacional de Pesquisas Espaciais (INPE)
Publisher CitySão José dos Campos
Pages7611-7618
Book TitleAnais
OrganizationInstituto Nacional de Pesquisas Espaciais (INPE)
History (UTC)2015-06-15 16:59:08 :: banon -> administrator ::
2018-06-06 03:28:04 :: administrator -> simone :: 2015
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
AbstractThe present work is committed to conduct a comparative analysis between two supervised classifiers, Maximum Likelihood and Support Vector Machine, respectively parametric and non-parametric, for the classification of vegetal physiognomies using very high spatial resolution imagery, emphasizing the gain in performance with the accordingly increase in the number of attributes. The database consisted of pan-sharpened QuickBird images and transformed images derived from the original bands besides relief data obtained from the TOPODATA Project. The study area extends over a surface of 16 km2 and is located within the municipality of Nova Friburgo, in the mountainous region of Rio de Janeiro state. In total, four experiments were accomplished all of them combining the adopted classifier with a different number of attributes. In the first two experiments, only the four QuickBird spectral bands, previously subject to geometric and radiometric corrections, were used. In the remainder two experiments, eighteen input bands were employed. The Kappa indices obtained with the Maximum Likelihood classifier lied between 0.64 and 0.66, while those obtained for the Support Vector Machine ranged from 0.52 to 0.80. Considering the attained results, we concluded that the number of input bands does not meaningfully increase the accuracy of the Maximum Likelihood classifier, whereas this factor greatly influences the Support Vector Machine performance.
AreaSRE
TypeProcessamento de imagens
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/8JMKD3MGP6W34M/3JM4K9E
zipped data URLhttp://urlib.net/zip/8JMKD3MGP6W34M/3JM4K9E
Languagept
Target Filep1750.pdf
User Groupbanon
Visibilityshown
5. Allied materials
Mirror Repositoryurlib.net/www/2011/03.29.20.55
Next Higher Units8JMKD3MGP6W34M/3JJLLP2
8JMKD3MGPCW/3ER446E
Citing Item Listsid.inpe.br/marte2/2015/05.31.21.54 13
sid.inpe.br/mtc-m21/2012/07.13.14.43.49 3
Host Collectiondpi.inpe.br/marte2/2013/05.17.15.03.06
6. Notes
Empty Fieldsarchivingpolicy archivist callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition issn keywords lineage mark nextedition notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor session shorttitle sponsor subject tertiarymark tertiarytype url versiontype volume
7. Description control
e-Mail (login)simone
update 


Close