Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitemarte2.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP6W34M/3JM4BBB
Repositorysid.inpe.br/marte2/2015/06.15.15.22.39
Last Update2015:06.15.15.22.39 (UTC) banon
Metadata Repositorysid.inpe.br/marte2/2015/06.15.15.22.40
Metadata Last Update2018:06.06.03.21.19 (UTC) administrator
ISBN978-85-17-0076-8
Label617
Citation KeyMarujoMore:2015:ApQuMu
TitleApplication of quadtree and multiresolution segmentation on rapideye images with and without histogram equalization for coffee crop classification in Machado municipality (MG) - Brazil
FormatInternet
Year2015
Access Date2024, May 14
Secondary TypePRE CN
Number of Files1
Size800 KiB
2. Context
Author1 Marujo, Rennan de Freitas Bezerra
2 Moreira, Mauricio Alves
Resume Identifier1
2 8JMKD3MGP5W/3C9JHT4
Group1 SER-SRE-SPG-INPE-MCTI-GOV-BR
2 DSR-OBT-INPE-MCTI-GOV-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 rennan@dsr.inpe.br
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
Pages3090-3096
Book TitleAnais
OrganizationInstituto Nacional de Pesquisas Espaciais (INPE)
History (UTC)2015-06-15 15:22:40 :: banon -> administrator ::
2018-06-06 03:21:19 :: administrator -> simone :: 2015
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
AbstractThis paper evaluates the influence of segmentation by multiresolution and quadtree algorithm on automatic supervised classification of high spatial resolution satellite images with and without histogram equalization for crop coffee classification. The study area was the municipality of Machado (MG) and in this work were used rapideye images because of its high spatial and radiometric resolutions. The crop coffee plants because of its intrinsic characteristics is easily can be confused with savanna vegetation in automatic classification process because of their similar spectral response. The use of segmentation techniques allows the use of shape and texture features, yet the spectral ones. The study area had two images with two different angle looks at the same time, which implied in different responses for each sensor because of the non lambertianity of the objects. For each class training samples were collected and the thematic result image was got through the nearest neighbor classifier applied to its segments. The effects of the histogram equalization were measured by comparing the classification results with and without histogram equalization to the reference image classified manually by trained professional, getting the global and kappa indices. Also were done a comparison between the results of multiresolution segmentation and quadtree segmentation. Multiresolution have produced more adequate segments to the contours of the coffee plants objects, with homogeneous contents, while quadtree generated too many segments, not capturing border areas. Histogram equalization showed itself an important pre-processing step on image classification process, influencing in the accuracy.
AreaSRE
TypeClassificação e mineração de dados
Arrangement 1urlib.net > BDMCI > Fonds > SBSR > SBSR 17 > Application of quadtree...
Arrangement 2urlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDSR > SBSR 17 > Application of quadtree...
Arrangement 3Projeto Memória 60... > Livros e livros editados > SBSR 17 > Application of quadtree...
Arrangement 4urlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDSR > Application of quadtree...
Arrangement 5urlib.net > BDMCI > Fonds > Produção pgr ATUAIS > SER > Application of quadtree...
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/3JM4BBB
zipped data URLhttp://urlib.net/zip/8JMKD3MGP6W34M/3JM4BBB
Languageen
Target Filep0617.pdf
User Groupbanon
Visibilityshown
5. Allied materials
Mirror Repositoryurlib.net/www/2011/03.29.20.55
Next Higher Units8JMKD3MGP6W34M/3JJLLP2
8JMKD3MGPCW/3ER446E
8JMKD3MGPCW/3F3NU5S
Citing Item Listsid.inpe.br/marte2/2015/05.31.21.54 6
sid.inpe.br/mtc-m21/2012/07.13.14.56.26 2
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