Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação
Autor(a) principal: | |
---|---|
Data de Publicação: | 2007 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://ojs.c3sl.ufpr.br/ojs/index.php/bcg/article/view/8247 http://hdl.handle.net/11449/69495 |
Resumo: | Image matching is one of the most important processes in Digital Photogrammetry, since it allows the automation of several stages of the photogrammetric pipeline. In most of the commercial software nowadays available, the algorithms of image correlation use the intensity information (gray levels), despising color information, that could be useful, if used in a suitable way, increasing the robustness of the current correspondence techniques in Digital Photogrammetry. The aim of this work is to present a technique that uses the RGB color model in the correlation process, in which a correlation matrix is generated for each color channel. The trace of the covariance matrix related to the translations of the reference window is used to predict which channel can better contribute to the result of the correlation and, with this, to properly weight the correlation coefficients. The weights to be applied to each one of the correlations matrixes are computed adaptively, considering the characteristics of each image. In order to assess this methodology, experiments with real color aerial images were accomplished and correct correlations were achieved with the proposed technique but failed with the current techniques using only grey level images. The results are presented and discussed, showing that the use of color information increases the robustness of the correlation process. |
id |
UNSP_4fd18c508b760649f3cfc458c7bc5913 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/69495 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlaçãoAn investigation on the use of the RGB color model in the matching process by correlationComputer visionDigital photogrammetryImage matchingalgorithmcolorcorrelationcovariance analysisdigital photogrammetryimage processingmatrixvisionImage matching is one of the most important processes in Digital Photogrammetry, since it allows the automation of several stages of the photogrammetric pipeline. In most of the commercial software nowadays available, the algorithms of image correlation use the intensity information (gray levels), despising color information, that could be useful, if used in a suitable way, increasing the robustness of the current correspondence techniques in Digital Photogrammetry. The aim of this work is to present a technique that uses the RGB color model in the correlation process, in which a correlation matrix is generated for each color channel. The trace of the covariance matrix related to the translations of the reference window is used to predict which channel can better contribute to the result of the correlation and, with this, to properly weight the correlation coefficients. The weights to be applied to each one of the correlations matrixes are computed adaptively, considering the characteristics of each image. In order to assess this methodology, experiments with real color aerial images were accomplished and correct correlations were achieved with the proposed technique but failed with the current techniques using only grey level images. The results are presented and discussed, showing that the use of color information increases the robustness of the correlation process.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)UNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Bolsista de IC da FapespUNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Faculdade de Ciências e TecnologiaUNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Gisplan - Tecnologia da GeoinformaçãoUNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Bolsista de IC da FapespUNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Faculdade de Ciências e TecnologiaUNESP - Universidade Estadual Paulista Júlio de Mesquita Filho Gisplan - Tecnologia da GeoinformaçãoUniversidade Estadual Paulista (Unesp)da Silva, Paulo Henrique Amorim [UNESP]Tommaselli, Antonio Maria Garcia [UNESP]Galo, Mauricio [UNESP]Costa, Elaine Reis [UNESP]2014-05-27T11:22:23Z2014-05-27T11:22:23Z2007-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article91-106application/pdfhttp://ojs.c3sl.ufpr.br/ojs/index.php/bcg/article/view/8247Boletim de Ciencias Geodesicas, v. 13, n. 1, p. 91-106, 2007.1413-4853http://hdl.handle.net/11449/694952-s2.0-365490461702-s2.0-36549046170.pdf16473186442995610000-0002-0104-9960Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPporBoletim de Ciências Geodésicas0,188info:eu-repo/semantics/openAccess2024-06-18T15:01:26Zoai:repositorio.unesp.br:11449/69495Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:04:28.217460Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação An investigation on the use of the RGB color model in the matching process by correlation |
title |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
spellingShingle |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação da Silva, Paulo Henrique Amorim [UNESP] Computer vision Digital photogrammetry Image matching algorithm color correlation covariance analysis digital photogrammetry image processing matrix vision |
title_short |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
title_full |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
title_fullStr |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
title_full_unstemmed |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
title_sort |
Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação |
author |
da Silva, Paulo Henrique Amorim [UNESP] |
author_facet |
da Silva, Paulo Henrique Amorim [UNESP] Tommaselli, Antonio Maria Garcia [UNESP] Galo, Mauricio [UNESP] Costa, Elaine Reis [UNESP] |
author_role |
author |
author2 |
Tommaselli, Antonio Maria Garcia [UNESP] Galo, Mauricio [UNESP] Costa, Elaine Reis [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
da Silva, Paulo Henrique Amorim [UNESP] Tommaselli, Antonio Maria Garcia [UNESP] Galo, Mauricio [UNESP] Costa, Elaine Reis [UNESP] |
dc.subject.por.fl_str_mv |
Computer vision Digital photogrammetry Image matching algorithm color correlation covariance analysis digital photogrammetry image processing matrix vision |
topic |
Computer vision Digital photogrammetry Image matching algorithm color correlation covariance analysis digital photogrammetry image processing matrix vision |
description |
Image matching is one of the most important processes in Digital Photogrammetry, since it allows the automation of several stages of the photogrammetric pipeline. In most of the commercial software nowadays available, the algorithms of image correlation use the intensity information (gray levels), despising color information, that could be useful, if used in a suitable way, increasing the robustness of the current correspondence techniques in Digital Photogrammetry. The aim of this work is to present a technique that uses the RGB color model in the correlation process, in which a correlation matrix is generated for each color channel. The trace of the covariance matrix related to the translations of the reference window is used to predict which channel can better contribute to the result of the correlation and, with this, to properly weight the correlation coefficients. The weights to be applied to each one of the correlations matrixes are computed adaptively, considering the characteristics of each image. In order to assess this methodology, experiments with real color aerial images were accomplished and correct correlations were achieved with the proposed technique but failed with the current techniques using only grey level images. The results are presented and discussed, showing that the use of color information increases the robustness of the correlation process. |
publishDate |
2007 |
dc.date.none.fl_str_mv |
2007-01-01 2014-05-27T11:22:23Z 2014-05-27T11:22:23Z |
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://ojs.c3sl.ufpr.br/ojs/index.php/bcg/article/view/8247 Boletim de Ciencias Geodesicas, v. 13, n. 1, p. 91-106, 2007. 1413-4853 http://hdl.handle.net/11449/69495 2-s2.0-36549046170 2-s2.0-36549046170.pdf 1647318644299561 0000-0002-0104-9960 |
url |
http://ojs.c3sl.ufpr.br/ojs/index.php/bcg/article/view/8247 http://hdl.handle.net/11449/69495 |
identifier_str_mv |
Boletim de Ciencias Geodesicas, v. 13, n. 1, p. 91-106, 2007. 1413-4853 2-s2.0-36549046170 2-s2.0-36549046170.pdf 1647318644299561 0000-0002-0104-9960 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
Boletim de Ciências Geodésicas 0,188 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
91-106 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_ |
1808128750466891776 |