Close

1. Identity statement
Reference TypeJournal Article
Sitemtc-m12.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier6qtX3pFwXQZ3r59YD6/G7bkJ
Repositorysid.inpe.br/iris@1912/2005/05.10.14.17   (restricted access)
Last Update2005:05.10.03.00.00 (UTC) administrator
Metadata Repositorysid.inpe.br/iris@1912/2005/05.10.14.17.39
Metadata Last Update2019:02.04.13.03.17 (UTC) administrator
Secondary KeyINPE-12366-PRE/7670
ISSN1516-9375
Citation KeyCarvalhoJrCarGuiMesShi:2003:IDeMe
TitleMistura espectral: (I) Detenção dos membros finais utilizando a geometria do simplex
ProjectComportamento Espectral de Alvos
Year2003
Access Date2024, Apr. 27
Secondary TypePRE PN
Number of Files1
Size1228 KiB
2. Context
Author1 Carvalho Junior, Osmar Abílio de
2 Carvalho, Ana Paula Ferreira de
3 Guimarães, Renato Fontes
4 Meseses, Paulo Roberto
5 Shimabukuro, Yosio Edemir
Resume Identifier1
2
3
4
5 8JMKD3MGP5W/3C9JJCQ
Group1 DSR-INPE-MCT-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais - INPE
2 UNB - Universidade de Brasilia - Depto de Geografia - Geologia
3
JournalEspaço e Geografia
Volume6
Number1
Pages151-176
History (UTC)2006-03-15 14:12:49 :: sergio -> administrator ::
2006-09-03 21:42:10 :: administrator -> sergio ::
2007-04-23 21:09:31 :: sergio -> administrator ::
2019-02-04 13:03:17 :: administrator -> simone :: 2003
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordsmistura espectral
classificação de imagens
simplex
membros finais
spectral mixture
simplex
endmembers
image classification
AbstractO conceito de mistura espectral permitiu uma nova abordagem nos procedimentos de classificação de imagens. Esse procedimento busca identificar e quantificar os constituintes que compõem ospixels. Para tanto é necessário estabelecer três etapas de processamento: (a) detecção dos membros finais, (b) localização dos elementos e (c) quantificação. O presente trabalho possui como objetivo discutir e sintetizar as principais abordagens para a detecção dos membros finais utilizando a geometria do simplex. Para tanto são definidos três tipos de simplex: (a) simplex de mínimo volume, (b) máximo volume e (c) volume intermediário. Cada modelo é discutido enfocando-se sua importância para o estabelecimento dos membros finais. -- ABSTRACT: The spectral mixture concepts allowed a new approach in the image classification procedures. This procedure searches to identify and to quantify the constituents that compose the pixels. Thus it is necessary to establish three processing stages: (a) end members detection, (b) elements location and (c) quantification. The present work has as objective to discuss and to synthesize the main approaches to endmembers detection using simplex geometry. For this, it was defined three simplex types: (a) simplex of minimum volume (b) maximum volume and (c) intermediate volume. Each model is discussed focusing on its importance to the establishment of the endmembers.
AreaSRE
ArrangementMistura espectral: (I)...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
Languagept
Target Filemistura espectral dos membros.pdf
User Groupadministrator
sergio
Visibilityshown
Copy HolderSID/SCD
Archiving Policydenypublisher denyfinaldraft
Read Permissiondeny from all and allow from 150.163
5. Allied materials
Next Higher Units8JMKD3MGPCW/3ER446E
Host Collectionsid.inpe.br/banon/2001/04.06.10.52
6. Notes
Empty Fieldsalternatejournal archivist callnumber copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress electronicmailaddress format isbn label lineage mark mirrorrepository month nextedition notes orcid parameterlist parentrepositories previousedition previouslowerunit progress readergroup rightsholder schedulinginformation secondarydate secondarymark session shorttitle sponsor subject tertiarymark tertiarytype typeofwork url versiontype
7. Description control
e-Mail (login)simone
update 


Close