Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto
Ano de defesa: | 2008 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | , , , |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Federal de Viçosa
|
Programa de Pós-Graduação: |
Mestrado em Engenharia Civil
|
Departamento: |
Geotecnia; Saneamento ambiental
|
País: |
BR
|
Palavras-chave em Português: | |
Palavras-chave em Inglês: | |
Área do conhecimento CNPq: | |
Link de acesso: | http://locus.ufv.br/handle/123456789/3706 |
Resumo: | The exclusive use of spectral information applied to image classification has shown less efficiency through the complex conditions that technological incoming of earth observation offers. For this reason, the research presented on this dissertation purposes to consider the contextual information to help in the remote sensing digital image classification process. To reveal the purpose viability, the methodology was applied in the study case for determination of vegetation areas at Belo Horizonte Municipal District. Through the partnership with some organisms of the Belo Horizonte Administration, the spatial data providers, informational classes to be discovered by the process was determined. The data were composed by vector information layers and QuickBird 2 artificial satellite multispectral images. After the edition of part of the vector layers data and subsequent conversion to raster format, combined to the atmospheric effects attenuation process and imagery orthorrectification, the application of the method was initiated. At first, the helpful contextual information to map categories identification was established, following by the necessary procedures to get them. Two different approaches to deal with the context modeling were chosen: one direct and other indirect one. The direct modeling was featured by images intersection operations with Boolean data types, and, the indirect modeling offered the analyst option to operate continuous data types. The direct modeling was applied to identify the incidence of vegetation areas on streets and blocks, obtained from the spectral environmental variable NDVI. And then, an intersection operation was performed between vegetation image, the streets and blocks layers. To apply the indirect modeling, the contextual information were defined to better featuring the vegetation types (native forest, crop forest, savannah, savannah field and crop field), in terms of the topographic environmental variables HCDEM (Hydrologically Consistent Digital Elevation Model), SDM (Slope Digital Model), NDM (North face Digital Model also called Northness), and EDM (East face Digital Model also called Eastness); and the spectral environmental variable NDVI. For each informational class, one specific arrangement of contextual information was determined and used on a Binomial Logistic Regression procedure, to find out initial values of higher likelihood for class happening. In this way, images was generated, one for each class, with defined likelihood values defined by regression operation. The Bayesian Paradigm was applied, through the Bayesian probabilistic model, to obtain images founded on updated probability values based on specialist knowledge. Beta-Binomial was the Bayesian probabilistic model adopted. Model index was done by α and β hyperparameters values, expressing the analyst opinion about the distribution position and dispersion, respectively. Values assigned for the hyperparameters has been acquired by simulations and iterations, following by intermediate results analysis, successively made until a proper reality representation was obtained. Imagery founded on probability values, determined by Bayesian model, was used like initial probability values in the maximum likelihood classification method. To verify the efficiency of the contextual information inclusion method, named Contextual Classification process, it was compared against the Traditional Classification method by the Maximum Likelihood Classifier algorithm. Results of both procedures were evaluated by contingency matrixes build by comparison between the thematic imagery produced by the classification methods and the reference image. Reference image was generated from the training sites, refined (or purified) by the Mahalanobis statistical distance algorithm, employing a 50% arbitrary value threshold of similarity criterion. From the contingency matrixes, Kappa coefficient value was estimated, presenting a difference about 6.5% between the Classification methods, indicating superiority of the Contextual (0.9199) one, in relation to Traditional (0.8528) one. To certify that the difference was, although, significant, a two-sided Z test was applied among the methods at 5% significance level. By Z values obtained, was observed that, at 95% confidence level, the nullity hypothesis (equivalency between methods) must been rejected and, thus, the methods were verified different. Consequently, the Contextual Classification method was employed to generate the vegetation thematic image of Belo Horizonte (MG) Municipal District. Results show that, from the available data and through the simplification hypothesis assumed, the Contextual Classification method purposed was really superior to the Traditional Classification method and, thus, its application is recommended. |
id |
UFV_937fbd770e882c32bbb5b0685d00e962 |
---|---|
oai_identifier_str |
oai:locus.ufv.br:123456789/3706 |
network_acronym_str |
UFV |
network_name_str |
LOCUS Repositório Institucional da UFV |
repository_id_str |
|
spelling |
Assis, Leonardo Campos dehttp://lattes.cnpq.br/7358954562509101Rodrigues, Dalto Domingoshttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4780466U6Silva, Antônio Simõeshttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4781844Y2Vieira, Carlos Antonio Oliveirahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728250D0Gleriani, José Marinaldohttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4791933J1Silva, Fabyano Fonseca ehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4766260Z2Oliveira, Leonardo Castro dehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4786641Y8Vasconcellos, José Carlos Pennahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4730828H32015-03-26T13:27:49Z2009-02-122015-03-26T13:27:49Z2008-07-08ASSIS, Leonardo Campos de. Use of contextual information in the remote sensing images classification process. 2008. 139 f. Dissertação (Mestrado em Geotecnia; Saneamento ambiental) - Universidade Federal de Viçosa, Viçosa, 2008.http://locus.ufv.br/handle/123456789/3706The exclusive use of spectral information applied to image classification has shown less efficiency through the complex conditions that technological incoming of earth observation offers. For this reason, the research presented on this dissertation purposes to consider the contextual information to help in the remote sensing digital image classification process. To reveal the purpose viability, the methodology was applied in the study case for determination of vegetation areas at Belo Horizonte Municipal District. Through the partnership with some organisms of the Belo Horizonte Administration, the spatial data providers, informational classes to be discovered by the process was determined. The data were composed by vector information layers and QuickBird 2 artificial satellite multispectral images. After the edition of part of the vector layers data and subsequent conversion to raster format, combined to the atmospheric effects attenuation process and imagery orthorrectification, the application of the method was initiated. At first, the helpful contextual information to map categories identification was established, following by the necessary procedures to get them. Two different approaches to deal with the context modeling were chosen: one direct and other indirect one. The direct modeling was featured by images intersection operations with Boolean data types, and, the indirect modeling offered the analyst option to operate continuous data types. The direct modeling was applied to identify the incidence of vegetation areas on streets and blocks, obtained from the spectral environmental variable NDVI. And then, an intersection operation was performed between vegetation image, the streets and blocks layers. To apply the indirect modeling, the contextual information were defined to better featuring the vegetation types (native forest, crop forest, savannah, savannah field and crop field), in terms of the topographic environmental variables HCDEM (Hydrologically Consistent Digital Elevation Model), SDM (Slope Digital Model), NDM (North face Digital Model also called Northness), and EDM (East face Digital Model also called Eastness); and the spectral environmental variable NDVI. For each informational class, one specific arrangement of contextual information was determined and used on a Binomial Logistic Regression procedure, to find out initial values of higher likelihood for class happening. In this way, images was generated, one for each class, with defined likelihood values defined by regression operation. The Bayesian Paradigm was applied, through the Bayesian probabilistic model, to obtain images founded on updated probability values based on specialist knowledge. Beta-Binomial was the Bayesian probabilistic model adopted. Model index was done by α and β hyperparameters values, expressing the analyst opinion about the distribution position and dispersion, respectively. Values assigned for the hyperparameters has been acquired by simulations and iterations, following by intermediate results analysis, successively made until a proper reality representation was obtained. Imagery founded on probability values, determined by Bayesian model, was used like initial probability values in the maximum likelihood classification method. To verify the efficiency of the contextual information inclusion method, named Contextual Classification process, it was compared against the Traditional Classification method by the Maximum Likelihood Classifier algorithm. Results of both procedures were evaluated by contingency matrixes build by comparison between the thematic imagery produced by the classification methods and the reference image. Reference image was generated from the training sites, refined (or purified) by the Mahalanobis statistical distance algorithm, employing a 50% arbitrary value threshold of similarity criterion. From the contingency matrixes, Kappa coefficient value was estimated, presenting a difference about 6.5% between the Classification methods, indicating superiority of the Contextual (0.9199) one, in relation to Traditional (0.8528) one. To certify that the difference was, although, significant, a two-sided Z test was applied among the methods at 5% significance level. By Z values obtained, was observed that, at 95% confidence level, the nullity hypothesis (equivalency between methods) must been rejected and, thus, the methods were verified different. Consequently, the Contextual Classification method was employed to generate the vegetation thematic image of Belo Horizonte (MG) Municipal District. Results show that, from the available data and through the simplification hypothesis assumed, the Contextual Classification method purposed was really superior to the Traditional Classification method and, thus, its application is recommended.A utilização de informações exclusivamente espectrais para classificação de imagens tem se mostrado pouco eficiente frente aos complexos cenários que o avanço tecnológico de observação terrestre oferece. Por esse motivo, a pesquisa apresentada nesta dissertação propõe a consideração de informações contextuais para auxiliar no processo de classificação de imagens digitais do sensoriamento remoto. Para demonstrar a viabilidade da proposta, aplicou-se a metodologia no estudo de caso para determinação de áreas de vegetação no Município de Belo Horizonte MG. Através de contato com órgãos da Prefeitura de Belo Horizonte, provedores dos dados espaciais, foram estabelecidas as classes informacionais a serem discriminadas pelo processo. Os dados constavam de planos de informação vetoriais e imagens multiespectrais do satélite artificial QuickBird 2. Após edição de parte dos dados vetoriais e posterior conversão para o formato raster, aliada ao processo de atenuação dos efeitos atmosféricos e ortorretificação das imagens, iniciou-se a aplicação do método. Primeiramente foram levantadas quais informações contextuais seriam úteis à identificação das classes informacionais almejadas, em seguida realizaram-se procedimentos para se obtê-las. Optou-se então por tratar a modelagem do contexto por meio de duas abordagens distintas: uma direta e outra indireta. A modelagem direta caracterizou-se por operações de intersecção de imagens com tipo de dados booleanos, enquanto a modelagem indireta forneceu a opção de manipular tipos de dados contínuos. A modelagem direta foi aplicada para obtenção da ocorrência de áreas de vegetação em vias e em quadras, conseguida a partir da variável de ambiente espectral NDVI. Após, foi realizada operação de intersecção com imagens de vegetação, de vias e de quadras. Para aplicação da modelagem indireta, as informações contextuais foram definidas para melhor caracterizar tipos de vegetação (floresta nativa; floresta plantada, cerrado, campo cerrado e campo plantado), em termos das variáveis de ambiente topográficas MDEHC, MDD, MDN, e MDL; e variável da ambiente espectral NDVI. Para cada classe informacional, uma combinação particular de informações contextuais foi estabelecida e utilizada em procedimento de Regressão Logística Binomial, para determinar valores iniciais de maior verossimilhança para sua ocorrência. Desse modo, foram geradas imagens, uma para cada classe informacional, com valores de verossimilhança definidos pela operação de regressão. Aplicou-se então o paradigma Bayesiano, através de modelo probabilístico Bayesiano, para se obter imagens fundamentadas em valores atualizados de probabilidade com base no conhecimento especialista. O modelo probabilístico Bayesiano adotado foi o Beta-Binomial, cuja indexação foi feita pelos valores dos hiperparâmetros α e β, que expressam a opinião do analista acerca da posição e dispersão da distribuição, respectivamente. Os valores adotados para os hiperparâmetros foram obtidos por simulações e iterações, seguidas de análises intermediárias dos resultados, realizadas sucessivamente até que se obtivesse uma representação mais apropriada da realidade. As imagens fundamentadas em valores de probabilidade, determinadas pelo modelo Bayesiano, foram utilizadas como valores iniciais de probabilidade no método de classificação pela máxima verossimilhança. Para verificar a eficácia do método de inclusão de informações contextuais, denominado de Classificação Contextual, comparou-se com o método de Classificação Tradicional pelo algoritmo Classificador da Máxima Verossimilhança. Os resultados dos dois procedimentos foram avaliados por matrizes de contingência, geradas pela comparação entre as imagens temáticas produzidas e uma imagem de referência. A imagem de referência foi obtida a partir das amostras de treinamento refinadas (ou purificadas) pelo algoritmo da distância estatística de Mahalanobis, com um valor arbitrado de 50% como critério de semelhança. A partir das matrizes de contingência foi estimado o valor do coeficiente Kappa, que apresentou diferença de aproximadamente 6,5% entre os métodos de Classificação, com superioridade para o Contextual (0,9199) em relação ao Tradicional (0,8528). Para certificar que essa diferença foi, contudo, significativa, aplicou-se o teste Z bilateral entre os métodos ao nível de significância de 5%. Pelos valores Z observou-se que, ao nível de confiança de 95%, a hipótese de nulidade (de equivalência entre métodos) foi rejeitada e, portanto, os métodos foram constatados diferentes. Empregou-se então, o método de Classificação Contextual para geração da imagem temática de vegetação do Município de Belo Horizonte - MG. Concluí-se daí que, a partir dos dados disponíveis e hipóteses simplificativas assumidas, o método de Classificação Contextual foi realmente superior ao método de Classificação Tradicional, logo, sua aplicação é recomendada.Fundação de Amparo a Pesquisa do Estado de Minas Geraisapplication/pdfporUniversidade Federal de ViçosaMestrado em Engenharia CivilUFVBRGeotecnia; Saneamento ambientalInferência BayesianaRegressão logística binomialImagens fundamentadas em valores de probabilidadeBayesian modelBinomial Logistic RegressionImagery founded on probability valuesCNPQ::ENGENHARIAS::ENGENHARIA CIVILUso de informações contextuais no processo de classificação de imagens do sensoriamento remotoUse of contextual information in the remote sensing images classification processinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:LOCUS Repositório Institucional da UFVinstname:Universidade Federal de Viçosa (UFV)instacron:UFVORIGINALtexto completo.pdfapplication/pdf2860382https://locus.ufv.br//bitstream/123456789/3706/1/texto%20completo.pdf5437d49fdccb3a8717b6db62730f33a5MD51TEXTtexto completo.pdf.txttexto completo.pdf.txtExtracted texttext/plain272238https://locus.ufv.br//bitstream/123456789/3706/2/texto%20completo.pdf.txt8a5da3f5fe67342d0f5397905bc09920MD52THUMBNAILtexto completo.pdf.jpgtexto completo.pdf.jpgIM Thumbnailimage/jpeg3518https://locus.ufv.br//bitstream/123456789/3706/3/texto%20completo.pdf.jpg73d974448ad5a1fbf6a01c25fdc84e19MD53123456789/37062016-04-09 23:13:50.646oai:locus.ufv.br:123456789/3706Repositório InstitucionalPUBhttps://www.locus.ufv.br/oai/requestfabiojreis@ufv.bropendoar:21452016-04-10T02:13:50LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV)false |
dc.title.por.fl_str_mv |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
dc.title.alternative.eng.fl_str_mv |
Use of contextual information in the remote sensing images classification process |
title |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
spellingShingle |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto Assis, Leonardo Campos de Inferência Bayesiana Regressão logística binomial Imagens fundamentadas em valores de probabilidade Bayesian model Binomial Logistic Regression Imagery founded on probability values CNPQ::ENGENHARIAS::ENGENHARIA CIVIL |
title_short |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
title_full |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
title_fullStr |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
title_full_unstemmed |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
title_sort |
Uso de informações contextuais no processo de classificação de imagens do sensoriamento remoto |
author |
Assis, Leonardo Campos de |
author_facet |
Assis, Leonardo Campos de |
author_role |
author |
dc.contributor.authorLattes.por.fl_str_mv |
http://lattes.cnpq.br/7358954562509101 |
dc.contributor.author.fl_str_mv |
Assis, Leonardo Campos de |
dc.contributor.advisor-co1.fl_str_mv |
Rodrigues, Dalto Domingos |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4780466U6 |
dc.contributor.advisor-co2.fl_str_mv |
Silva, Antônio Simões |
dc.contributor.advisor-co2Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4781844Y2 |
dc.contributor.advisor1.fl_str_mv |
Vieira, Carlos Antonio Oliveira |
dc.contributor.advisor1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728250D0 |
dc.contributor.referee1.fl_str_mv |
Gleriani, José Marinaldo |
dc.contributor.referee1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4791933J1 |
dc.contributor.referee2.fl_str_mv |
Silva, Fabyano Fonseca e |
dc.contributor.referee2Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4766260Z2 |
dc.contributor.referee3.fl_str_mv |
Oliveira, Leonardo Castro de |
dc.contributor.referee3Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4786641Y8 |
dc.contributor.referee4.fl_str_mv |
Vasconcellos, José Carlos Penna |
dc.contributor.referee4Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4730828H3 |
contributor_str_mv |
Rodrigues, Dalto Domingos Silva, Antônio Simões Vieira, Carlos Antonio Oliveira Gleriani, José Marinaldo Silva, Fabyano Fonseca e Oliveira, Leonardo Castro de Vasconcellos, José Carlos Penna |
dc.subject.por.fl_str_mv |
Inferência Bayesiana Regressão logística binomial Imagens fundamentadas em valores de probabilidade |
topic |
Inferência Bayesiana Regressão logística binomial Imagens fundamentadas em valores de probabilidade Bayesian model Binomial Logistic Regression Imagery founded on probability values CNPQ::ENGENHARIAS::ENGENHARIA CIVIL |
dc.subject.eng.fl_str_mv |
Bayesian model Binomial Logistic Regression Imagery founded on probability values |
dc.subject.cnpq.fl_str_mv |
CNPQ::ENGENHARIAS::ENGENHARIA CIVIL |
description |
The exclusive use of spectral information applied to image classification has shown less efficiency through the complex conditions that technological incoming of earth observation offers. For this reason, the research presented on this dissertation purposes to consider the contextual information to help in the remote sensing digital image classification process. To reveal the purpose viability, the methodology was applied in the study case for determination of vegetation areas at Belo Horizonte Municipal District. Through the partnership with some organisms of the Belo Horizonte Administration, the spatial data providers, informational classes to be discovered by the process was determined. The data were composed by vector information layers and QuickBird 2 artificial satellite multispectral images. After the edition of part of the vector layers data and subsequent conversion to raster format, combined to the atmospheric effects attenuation process and imagery orthorrectification, the application of the method was initiated. At first, the helpful contextual information to map categories identification was established, following by the necessary procedures to get them. Two different approaches to deal with the context modeling were chosen: one direct and other indirect one. The direct modeling was featured by images intersection operations with Boolean data types, and, the indirect modeling offered the analyst option to operate continuous data types. The direct modeling was applied to identify the incidence of vegetation areas on streets and blocks, obtained from the spectral environmental variable NDVI. And then, an intersection operation was performed between vegetation image, the streets and blocks layers. To apply the indirect modeling, the contextual information were defined to better featuring the vegetation types (native forest, crop forest, savannah, savannah field and crop field), in terms of the topographic environmental variables HCDEM (Hydrologically Consistent Digital Elevation Model), SDM (Slope Digital Model), NDM (North face Digital Model also called Northness), and EDM (East face Digital Model also called Eastness); and the spectral environmental variable NDVI. For each informational class, one specific arrangement of contextual information was determined and used on a Binomial Logistic Regression procedure, to find out initial values of higher likelihood for class happening. In this way, images was generated, one for each class, with defined likelihood values defined by regression operation. The Bayesian Paradigm was applied, through the Bayesian probabilistic model, to obtain images founded on updated probability values based on specialist knowledge. Beta-Binomial was the Bayesian probabilistic model adopted. Model index was done by α and β hyperparameters values, expressing the analyst opinion about the distribution position and dispersion, respectively. Values assigned for the hyperparameters has been acquired by simulations and iterations, following by intermediate results analysis, successively made until a proper reality representation was obtained. Imagery founded on probability values, determined by Bayesian model, was used like initial probability values in the maximum likelihood classification method. To verify the efficiency of the contextual information inclusion method, named Contextual Classification process, it was compared against the Traditional Classification method by the Maximum Likelihood Classifier algorithm. Results of both procedures were evaluated by contingency matrixes build by comparison between the thematic imagery produced by the classification methods and the reference image. Reference image was generated from the training sites, refined (or purified) by the Mahalanobis statistical distance algorithm, employing a 50% arbitrary value threshold of similarity criterion. From the contingency matrixes, Kappa coefficient value was estimated, presenting a difference about 6.5% between the Classification methods, indicating superiority of the Contextual (0.9199) one, in relation to Traditional (0.8528) one. To certify that the difference was, although, significant, a two-sided Z test was applied among the methods at 5% significance level. By Z values obtained, was observed that, at 95% confidence level, the nullity hypothesis (equivalency between methods) must been rejected and, thus, the methods were verified different. Consequently, the Contextual Classification method was employed to generate the vegetation thematic image of Belo Horizonte (MG) Municipal District. Results show that, from the available data and through the simplification hypothesis assumed, the Contextual Classification method purposed was really superior to the Traditional Classification method and, thus, its application is recommended. |
publishDate |
2008 |
dc.date.issued.fl_str_mv |
2008-07-08 |
dc.date.available.fl_str_mv |
2009-02-12 2015-03-26T13:27:49Z |
dc.date.accessioned.fl_str_mv |
2015-03-26T13:27:49Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
ASSIS, Leonardo Campos de. Use of contextual information in the remote sensing images classification process. 2008. 139 f. Dissertação (Mestrado em Geotecnia; Saneamento ambiental) - Universidade Federal de Viçosa, Viçosa, 2008. |
dc.identifier.uri.fl_str_mv |
http://locus.ufv.br/handle/123456789/3706 |
identifier_str_mv |
ASSIS, Leonardo Campos de. Use of contextual information in the remote sensing images classification process. 2008. 139 f. Dissertação (Mestrado em Geotecnia; Saneamento ambiental) - Universidade Federal de Viçosa, Viçosa, 2008. |
url |
http://locus.ufv.br/handle/123456789/3706 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Viçosa |
dc.publisher.program.fl_str_mv |
Mestrado em Engenharia Civil |
dc.publisher.initials.fl_str_mv |
UFV |
dc.publisher.country.fl_str_mv |
BR |
dc.publisher.department.fl_str_mv |
Geotecnia; Saneamento ambiental |
publisher.none.fl_str_mv |
Universidade Federal de Viçosa |
dc.source.none.fl_str_mv |
reponame:LOCUS Repositório Institucional da UFV instname:Universidade Federal de Viçosa (UFV) instacron:UFV |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
UFV |
institution |
UFV |
reponame_str |
LOCUS Repositório Institucional da UFV |
collection |
LOCUS Repositório Institucional da UFV |
bitstream.url.fl_str_mv |
https://locus.ufv.br//bitstream/123456789/3706/1/texto%20completo.pdf https://locus.ufv.br//bitstream/123456789/3706/2/texto%20completo.pdf.txt https://locus.ufv.br//bitstream/123456789/3706/3/texto%20completo.pdf.jpg |
bitstream.checksum.fl_str_mv |
5437d49fdccb3a8717b6db62730f33a5 8a5da3f5fe67342d0f5397905bc09920 73d974448ad5a1fbf6a01c25fdc84e19 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
fabiojreis@ufv.br |
_version_ |
1794528600098078720 |