Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus

Detalhes bibliográficos
Autor(a) principal: Silva, Alessandra F. [UNESP]
Data de Publicação: 2013
Outros Autores: Barbosa, Ana Paula [UNESP], Zimback, Célia Regina Lopes [UNESP], Landim, Paulo M. B. [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1590/S0100-69162013000600017
http://hdl.handle.net/11449/110179
Resumo: This study compares the precision of three image classification methods, two of remote sensing and one of geostatistics applied to areas cultivated with citrus. The 5,296.52ha area of study is located in the city of Araraquara - central region of the state of São Paulo (SP), Brazil. The multispectral image from the CCD/CBERS-2B satellite was acquired in 2009 and processed through the Geographic Information System (GIS) SPRING. Three classification methods were used, one unsupervised (Cluster), and two supervised (Indicator Kriging/IK and Maximum Likelihood/Maxver), in addition to the screen classification taken as field checking.. Reliability of classifications was evaluated by Kappa index. In accordance with the Kappa index, the Indicator kriging method obtained the highest degree of reliability for bands 2 and 4. Moreover the Cluster method applied to band 2 (green) was the best quality classification between all the methods. Indicator Kriging was the classifier that presented the citrus total area closest to the field check estimated by -3.01%, whereas Maxver overestimated the total citrus area by 42.94%.
id UNSP_aa07a2416020c5152f6aca89c12daede
oai_identifier_str oai:repositorio.unesp.br:11449/110179
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrusGeoestatística e sensoriamento remoto na classificação de imagens em áreas cultivadas com citrosKrigagem IndicativaClusterMaxversatélite CBERS-2Bclassificação espacialIndicator KrigingClusterMaxverCBERS-2B satellitespatial classificationThis study compares the precision of three image classification methods, two of remote sensing and one of geostatistics applied to areas cultivated with citrus. The 5,296.52ha area of study is located in the city of Araraquara - central region of the state of São Paulo (SP), Brazil. The multispectral image from the CCD/CBERS-2B satellite was acquired in 2009 and processed through the Geographic Information System (GIS) SPRING. Three classification methods were used, one unsupervised (Cluster), and two supervised (Indicator Kriging/IK and Maximum Likelihood/Maxver), in addition to the screen classification taken as field checking.. Reliability of classifications was evaluated by Kappa index. In accordance with the Kappa index, the Indicator kriging method obtained the highest degree of reliability for bands 2 and 4. Moreover the Cluster method applied to band 2 (green) was the best quality classification between all the methods. Indicator Kriging was the classifier that presented the citrus total area closest to the field check estimated by -3.01%, whereas Maxver overestimated the total citrus area by 42.94%.O objetivo deste trabalho foi comparar a precisão de métodos de classificação de imagens orbitais na determinação de áreas cultivadas com citros, por métodos de sensoriamento remoto e de geoestatística. A área de estudo utilizada nesta pesquisa está localizada na cidade de Araraquara, região central do Estado de São Paulo, com 5.296,52 ha. Foi utilizada a imagem multiespectral do satélite CCD/CBERS 2B, adquirida em 2009 e processada no Sistema de Informações Geográficas (SIG) SPRING. Três métodos de classificação foram utilizados, sendo um não supervisionado (Cluster) e dois supervisionados (Krigagem Indicativa/KI e Máxima verossimilhança/Maxver), além da classificação em tela tida como verdade terrestre. A fidedignidade das classificações foi avaliada pelo índice Kappa. A Krigagem Indicativa foi o método que melhor classificou as áreas de citros na banda 4, com forte grau de concordância, conforme a estatística kappa, para as bandas 2 e 4. Pela validação, o Cluster para a banda 2 (verde) foi o classificador que obteve a melhor qualidade. A Krigagem Indicativa foi o classificador que apresentou área total de citros mais próxima da verdade terrestre em -3,01%, enquanto o Maxver foi o classificador que mais superestimou a área total de citros em 42,94 %.GEPAG - Georeferenced Agricultural Research GroupDepartment of Natural Resources - Soil SciencesGraduate Program in Agronomy - Energia na Agricultura, FCA / UNESP BotucatuCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)UNESP FCAUNESP FCA Depto de Solo e Recursos AmbientaisUNESP Instituto de Geociências e Ciências Exatas Departamento de Geologia AplicadaUNESP FCAUNESP FCA Depto de Solo e Recursos AmbientaisUNESP Instituto de Geociências e Ciências Exatas Departamento de Geologia AplicadaAssociação Brasileira de Engenharia Agrícola (SBEA)Universidade Estadual Paulista (Unesp)Silva, Alessandra F. [UNESP]Barbosa, Ana Paula [UNESP]Zimback, Célia Regina Lopes [UNESP]Landim, Paulo M. B. [UNESP]2014-10-01T13:08:53Z2014-10-01T13:08:53Z2013-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1245-1256application/pdfhttp://dx.doi.org/10.1590/S0100-69162013000600017Engenharia Agrícola. Associação Brasileira de Engenharia Agrícola, v. 33, n. 6, p. 1245-1256, 2013.0100-6916http://hdl.handle.net/11449/11017910.1590/S0100-69162013000600017S0100-69162013000600017WOS:000331653400018S0100-69162013000600017.pdfSciELOreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEngenharia Agrícola0.3870,305info:eu-repo/semantics/openAccess2024-04-30T19:29:57Zoai:repositorio.unesp.br:11449/110179Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:03:38.869213Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
Geoestatística e sensoriamento remoto na classificação de imagens em áreas cultivadas com citros
title Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
spellingShingle Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
Silva, Alessandra F. [UNESP]
Krigagem Indicativa
Cluster
Maxver
satélite CBERS-2B
classificação espacial
Indicator Kriging
Cluster
Maxver
CBERS-2B satellite
spatial classification
title_short Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
title_full Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
title_fullStr Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
title_full_unstemmed Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
title_sort Geostatistics and remote sensing methods in the classification of images of areas cultivated with citrus
author Silva, Alessandra F. [UNESP]
author_facet Silva, Alessandra F. [UNESP]
Barbosa, Ana Paula [UNESP]
Zimback, Célia Regina Lopes [UNESP]
Landim, Paulo M. B. [UNESP]
author_role author
author2 Barbosa, Ana Paula [UNESP]
Zimback, Célia Regina Lopes [UNESP]
Landim, Paulo M. B. [UNESP]
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Silva, Alessandra F. [UNESP]
Barbosa, Ana Paula [UNESP]
Zimback, Célia Regina Lopes [UNESP]
Landim, Paulo M. B. [UNESP]
dc.subject.por.fl_str_mv Krigagem Indicativa
Cluster
Maxver
satélite CBERS-2B
classificação espacial
Indicator Kriging
Cluster
Maxver
CBERS-2B satellite
spatial classification
topic Krigagem Indicativa
Cluster
Maxver
satélite CBERS-2B
classificação espacial
Indicator Kriging
Cluster
Maxver
CBERS-2B satellite
spatial classification
description This study compares the precision of three image classification methods, two of remote sensing and one of geostatistics applied to areas cultivated with citrus. The 5,296.52ha area of study is located in the city of Araraquara - central region of the state of São Paulo (SP), Brazil. The multispectral image from the CCD/CBERS-2B satellite was acquired in 2009 and processed through the Geographic Information System (GIS) SPRING. Three classification methods were used, one unsupervised (Cluster), and two supervised (Indicator Kriging/IK and Maximum Likelihood/Maxver), in addition to the screen classification taken as field checking.. Reliability of classifications was evaluated by Kappa index. In accordance with the Kappa index, the Indicator kriging method obtained the highest degree of reliability for bands 2 and 4. Moreover the Cluster method applied to band 2 (green) was the best quality classification between all the methods. Indicator Kriging was the classifier that presented the citrus total area closest to the field check estimated by -3.01%, whereas Maxver overestimated the total citrus area by 42.94%.
publishDate 2013
dc.date.none.fl_str_mv 2013-12-01
2014-10-01T13:08:53Z
2014-10-01T13:08:53Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1590/S0100-69162013000600017
Engenharia Agrícola. Associação Brasileira de Engenharia Agrícola, v. 33, n. 6, p. 1245-1256, 2013.
0100-6916
http://hdl.handle.net/11449/110179
10.1590/S0100-69162013000600017
S0100-69162013000600017
WOS:000331653400018
S0100-69162013000600017.pdf
url http://dx.doi.org/10.1590/S0100-69162013000600017
http://hdl.handle.net/11449/110179
identifier_str_mv Engenharia Agrícola. Associação Brasileira de Engenharia Agrícola, v. 33, n. 6, p. 1245-1256, 2013.
0100-6916
10.1590/S0100-69162013000600017
S0100-69162013000600017
WOS:000331653400018
S0100-69162013000600017.pdf
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Engenharia Agrícola
0.387
0,305
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 1245-1256
application/pdf
dc.publisher.none.fl_str_mv Associação Brasileira de Engenharia Agrícola (SBEA)
publisher.none.fl_str_mv Associação Brasileira de Engenharia Agrícola (SBEA)
dc.source.none.fl_str_mv SciELO
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129578049208320