Comparing support vector machine contextual approaches for urban area classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1080/2150704X.2016.1154218 http://hdl.handle.net/11449/168524 |
Resumo: | Support vector machine (SVM) has been receiving a great deal of attention for remote sensing data classification. Although the original formulation of this method does not incorporate contextual information, lately different formulations have been proposed to incorporate such information, with the aim of improving the mapping accuracy. In general, these proposals modify the SVM training phase or integrate the SVM classifications in stochastic models. Recently, two new contextual versions of SVM, context adaptive and competitive translative SVM (CaSVM and CtSVM, respectively), were proposed in literature. In this work, two case studies of urban area classification, using IKONOS-II and hyperspectral digital imagery collection experiment (HYDICE) data sets were conducted to compare SVM, SVM integrated with the iterated conditional modes (ICM) stochastic algorithm, SVM smoothed using the mode filter and the recent approaches CaSVM and CtSVM. The results indicated that although it possesses a high computational cost, the CaSVM method was able to produce classification results with similar accuracy (using kappa coefficient) to those obtained using SVM integrated with ICM (SVM + ICM) and the mode filter (SVM + Mode), all of them found statistically superior to the SVM result at 95% confidence level for the IKONOS-II image. For HYDICE image, all results were found statistically insignificant at 95% confidence level. Investigation of what happens at transition regions between classes, however, showed that some methods can present superior performance. To this objective, a new performance measure, called upsilon coefficient, was introduced in this work, which measures the impact that the smoothing effect, typical of contextual methods, can have in distorting the edges between regions. With this new measure was found that CaSVM is the one which has better performance followed with SVM + ICM. |
id |
UNSP_fc407124b2d16d9c98900b07a5cb0a7c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/168524 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Comparing support vector machine contextual approaches for urban area classificationSupport vector machine (SVM) has been receiving a great deal of attention for remote sensing data classification. Although the original formulation of this method does not incorporate contextual information, lately different formulations have been proposed to incorporate such information, with the aim of improving the mapping accuracy. In general, these proposals modify the SVM training phase or integrate the SVM classifications in stochastic models. Recently, two new contextual versions of SVM, context adaptive and competitive translative SVM (CaSVM and CtSVM, respectively), were proposed in literature. In this work, two case studies of urban area classification, using IKONOS-II and hyperspectral digital imagery collection experiment (HYDICE) data sets were conducted to compare SVM, SVM integrated with the iterated conditional modes (ICM) stochastic algorithm, SVM smoothed using the mode filter and the recent approaches CaSVM and CtSVM. The results indicated that although it possesses a high computational cost, the CaSVM method was able to produce classification results with similar accuracy (using kappa coefficient) to those obtained using SVM integrated with ICM (SVM + ICM) and the mode filter (SVM + Mode), all of them found statistically superior to the SVM result at 95% confidence level for the IKONOS-II image. For HYDICE image, all results were found statistically insignificant at 95% confidence level. Investigation of what happens at transition regions between classes, however, showed that some methods can present superior performance. To this objective, a new performance measure, called upsilon coefficient, was introduced in this work, which measures the impact that the smoothing effect, typical of contextual methods, can have in distorting the edges between regions. With this new measure was found that CaSVM is the one which has better performance followed with SVM + ICM.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Instituto de Ciência e Tecnologia UNESP - Univ. Estadual Paulista, Rod. Presidente Dutra, km 137.8Divisão de Processamento de Imagens INPE - Inst. Nacional de Pesquisas EspaciaisInstituto de Ciência e Tecnologia UNESP - Univ. Estadual Paulista, Rod. Presidente Dutra, km 137.8CNPq: 151571/2013-9FAPESP: 2014/14830-8CNPq: 307666/2011-5CNPq: 401528/2012-0Universidade Estadual Paulista (Unesp)INPE - Inst. Nacional de Pesquisas EspaciaisNegri, R. G. [UNESP]Dutra, L. V.SantAnna, S. J.S.2018-12-11T16:41:38Z2018-12-11T16:41:38Z2016-05-03info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article485-494application/pdfhttp://dx.doi.org/10.1080/2150704X.2016.1154218Remote Sensing Letters, v. 7, n. 5, p. 485-494, 2016.2150-70582150-704Xhttp://hdl.handle.net/11449/16852410.1080/2150704X.2016.11542182-s2.0-849622095432-s2.0-84962209543.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensing Letters0,752info:eu-repo/semantics/openAccess2023-12-30T06:23:27Zoai:repositorio.unesp.br:11449/168524Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-12-30T06:23:27Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Comparing support vector machine contextual approaches for urban area classification |
title |
Comparing support vector machine contextual approaches for urban area classification |
spellingShingle |
Comparing support vector machine contextual approaches for urban area classification Negri, R. G. [UNESP] |
title_short |
Comparing support vector machine contextual approaches for urban area classification |
title_full |
Comparing support vector machine contextual approaches for urban area classification |
title_fullStr |
Comparing support vector machine contextual approaches for urban area classification |
title_full_unstemmed |
Comparing support vector machine contextual approaches for urban area classification |
title_sort |
Comparing support vector machine contextual approaches for urban area classification |
author |
Negri, R. G. [UNESP] |
author_facet |
Negri, R. G. [UNESP] Dutra, L. V. SantAnna, S. J.S. |
author_role |
author |
author2 |
Dutra, L. V. SantAnna, S. J.S. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) INPE - Inst. Nacional de Pesquisas Espaciais |
dc.contributor.author.fl_str_mv |
Negri, R. G. [UNESP] Dutra, L. V. SantAnna, S. J.S. |
description |
Support vector machine (SVM) has been receiving a great deal of attention for remote sensing data classification. Although the original formulation of this method does not incorporate contextual information, lately different formulations have been proposed to incorporate such information, with the aim of improving the mapping accuracy. In general, these proposals modify the SVM training phase or integrate the SVM classifications in stochastic models. Recently, two new contextual versions of SVM, context adaptive and competitive translative SVM (CaSVM and CtSVM, respectively), were proposed in literature. In this work, two case studies of urban area classification, using IKONOS-II and hyperspectral digital imagery collection experiment (HYDICE) data sets were conducted to compare SVM, SVM integrated with the iterated conditional modes (ICM) stochastic algorithm, SVM smoothed using the mode filter and the recent approaches CaSVM and CtSVM. The results indicated that although it possesses a high computational cost, the CaSVM method was able to produce classification results with similar accuracy (using kappa coefficient) to those obtained using SVM integrated with ICM (SVM + ICM) and the mode filter (SVM + Mode), all of them found statistically superior to the SVM result at 95% confidence level for the IKONOS-II image. For HYDICE image, all results were found statistically insignificant at 95% confidence level. Investigation of what happens at transition regions between classes, however, showed that some methods can present superior performance. To this objective, a new performance measure, called upsilon coefficient, was introduced in this work, which measures the impact that the smoothing effect, typical of contextual methods, can have in distorting the edges between regions. With this new measure was found that CaSVM is the one which has better performance followed with SVM + ICM. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-05-03 2018-12-11T16:41:38Z 2018-12-11T16:41:38Z |
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/10.1080/2150704X.2016.1154218 Remote Sensing Letters, v. 7, n. 5, p. 485-494, 2016. 2150-7058 2150-704X http://hdl.handle.net/11449/168524 10.1080/2150704X.2016.1154218 2-s2.0-84962209543 2-s2.0-84962209543.pdf |
url |
http://dx.doi.org/10.1080/2150704X.2016.1154218 http://hdl.handle.net/11449/168524 |
identifier_str_mv |
Remote Sensing Letters, v. 7, n. 5, p. 485-494, 2016. 2150-7058 2150-704X 10.1080/2150704X.2016.1154218 2-s2.0-84962209543 2-s2.0-84962209543.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Remote Sensing Letters 0,752 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
485-494 application/pdf |
dc.source.none.fl_str_mv |
Scopus 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_ |
1797790156783091712 |