Geographical mapping of coffee crops by using convolutional networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/43132 |
Resumo: | In the last decades we have observed a constant growth in the use of remote sensing images for the monitoring of activities and phenomena on Earth allowing the development of several applications. Among the existing applications, the creation of thematic maps is one of the most common, since it allows the classi cation and analysis of the various objects that composes an image and can be used for many purposes, such as: monitoring, planning and recognition. Thematic maps are, usually, generated manually or by the use of models trained by supervised learning. In this type of learning, the system is trained to learn di erent patterns by using labeled samples provided by the user. In this sense, in this dissertation, a thematic map generation method was developed for the recognition of co ee crops in order to obtain data from this crop. For, despite its great importance in the country's economy and Minas Gerais, data collection is still performed manually. The method developed in this work is based on the combination of convolutional neural networks in multiple scales and the choice by neural networks for the development of this project is attributed to the fact that its performance is superior to the traditional methods proposed in computer vision and also not yet be widely used in tasks related to the agricultural area. The use of a multi-scale approach is related to the variation of the size of the patterns found in satellite images and aims to make the method more robust by allowing distinct features to be learned at each of the scales and used in a complementary way. |
id |
UFMG_6066052b29e34e557be1e339185f75f0 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/43132 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Jefersson Alex dos Santoshttp://lattes.cnpq.br/2171782600728348David Menotti GomesArnaldo Albuquerque AraújoRubens Augusto Camargo Lamparellihttp://lattes.cnpq.br/8927799884903333Rafael Marlon Peirera Costa Baeta Carreira2022-07-11T12:53:50Z2022-07-11T12:53:50Z2017-09-04http://hdl.handle.net/1843/43132In the last decades we have observed a constant growth in the use of remote sensing images for the monitoring of activities and phenomena on Earth allowing the development of several applications. Among the existing applications, the creation of thematic maps is one of the most common, since it allows the classi cation and analysis of the various objects that composes an image and can be used for many purposes, such as: monitoring, planning and recognition. Thematic maps are, usually, generated manually or by the use of models trained by supervised learning. In this type of learning, the system is trained to learn di erent patterns by using labeled samples provided by the user. In this sense, in this dissertation, a thematic map generation method was developed for the recognition of co ee crops in order to obtain data from this crop. For, despite its great importance in the country's economy and Minas Gerais, data collection is still performed manually. The method developed in this work is based on the combination of convolutional neural networks in multiple scales and the choice by neural networks for the development of this project is attributed to the fact that its performance is superior to the traditional methods proposed in computer vision and also not yet be widely used in tasks related to the agricultural area. The use of a multi-scale approach is related to the variation of the size of the patterns found in satellite images and aims to make the method more robust by allowing distinct features to be learned at each of the scales and used in a complementary way.Nas últimas décadas temos observado um constante crescimento na utilização de imagens de sensoriamento remoto para o monitoramento de atividades e fenômenos na Terra, o que permite o desenvolvimento de diversas aplicações. Dentre as aplicações existentes, a criação de mapas temáticos é uma das mais comuns, pois permite a classi cação e análise dos vários objetos que compõe uma imagem podendo ser utilizado para muitos ns, tais como: monitoramento, planejamento e reconhecimento. Mapas temáticos podem ser construídos de forma manual ou por modelos treinados através de aprendizagem supervisionada. Neste tipo de aprendizagem, o sistema é treinado para aprender diferentes padrões através da utilização de amostras rotuladas fornecidas pelo usuário. Nesse sentido, nesta dissertação, um método de geração de mapas temáticos foi desenvolvido para o reconhecimento de colheitas de café visando auxiliar na obtenção de dados dessa cultura agrícola. Pois, apesar de sua grande importância na economia do país e de Minas Gerais, a obtenção de dados ainda é realizada de forma manual. O método desenvolvido neste trabalho baseia-se na combinação de redes neuronais de convolução em múltiplas escalas sendo a escolha das redes neuronais para o desenvolvimento deste projeto atribuída ao seu desempenho superior aos métodos tradicionais propostos em visão computacional e também por ainda não ser amplamente utilizada em tarefas relacionadas à área agrícola. A utilização de uma abordagem multi-escala está relacionada à variação do tamanho dos padrões encontrados em imagens de satélite e visa tornar o método mais robusto ao permitir que características distintas sejam aprendidas em cada uma das escalas e usadas de forma complementar.engUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOComputação – Teses.Sensoriamento remoto - TesesRedes neurais convolucionais – TesesCafé – Cultivo – Teses.Remote sensingCoffee classificationConvolutional neural networksGeographical mapping of coffee crops by using convolutional networksinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALrafael_baeta_dissertacao.pdfrafael_baeta_dissertacao.pdfapplication/pdf13106494https://repositorio.ufmg.br/bitstream/1843/43132/5/rafael_baeta_dissertacao.pdf6c8b90b2d5f03ea7e22eb87edcaa58d6MD55LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/43132/6/license.txtcda590c95a0b51b4d15f60c9642ca272MD561843/431322022-07-11 09:53:51.431oai:repositorio.ufmg.br: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ório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2022-07-11T12:53:51Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
Geographical mapping of coffee crops by using convolutional networks |
title |
Geographical mapping of coffee crops by using convolutional networks |
spellingShingle |
Geographical mapping of coffee crops by using convolutional networks Rafael Marlon Peirera Costa Baeta Carreira Remote sensing Coffee classification Convolutional neural networks Computação – Teses. Sensoriamento remoto - Teses Redes neurais convolucionais – Teses Café – Cultivo – Teses. |
title_short |
Geographical mapping of coffee crops by using convolutional networks |
title_full |
Geographical mapping of coffee crops by using convolutional networks |
title_fullStr |
Geographical mapping of coffee crops by using convolutional networks |
title_full_unstemmed |
Geographical mapping of coffee crops by using convolutional networks |
title_sort |
Geographical mapping of coffee crops by using convolutional networks |
author |
Rafael Marlon Peirera Costa Baeta Carreira |
author_facet |
Rafael Marlon Peirera Costa Baeta Carreira |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Jefersson Alex dos Santos |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/2171782600728348 |
dc.contributor.advisor-co1.fl_str_mv |
David Menotti Gomes |
dc.contributor.referee1.fl_str_mv |
Arnaldo Albuquerque Araújo |
dc.contributor.referee2.fl_str_mv |
Rubens Augusto Camargo Lamparelli |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/8927799884903333 |
dc.contributor.author.fl_str_mv |
Rafael Marlon Peirera Costa Baeta Carreira |
contributor_str_mv |
Jefersson Alex dos Santos David Menotti Gomes Arnaldo Albuquerque Araújo Rubens Augusto Camargo Lamparelli |
dc.subject.por.fl_str_mv |
Remote sensing Coffee classification Convolutional neural networks |
topic |
Remote sensing Coffee classification Convolutional neural networks Computação – Teses. Sensoriamento remoto - Teses Redes neurais convolucionais – Teses Café – Cultivo – Teses. |
dc.subject.other.pt_BR.fl_str_mv |
Computação – Teses. Sensoriamento remoto - Teses Redes neurais convolucionais – Teses Café – Cultivo – Teses. |
description |
In the last decades we have observed a constant growth in the use of remote sensing images for the monitoring of activities and phenomena on Earth allowing the development of several applications. Among the existing applications, the creation of thematic maps is one of the most common, since it allows the classi cation and analysis of the various objects that composes an image and can be used for many purposes, such as: monitoring, planning and recognition. Thematic maps are, usually, generated manually or by the use of models trained by supervised learning. In this type of learning, the system is trained to learn di erent patterns by using labeled samples provided by the user. In this sense, in this dissertation, a thematic map generation method was developed for the recognition of co ee crops in order to obtain data from this crop. For, despite its great importance in the country's economy and Minas Gerais, data collection is still performed manually. The method developed in this work is based on the combination of convolutional neural networks in multiple scales and the choice by neural networks for the development of this project is attributed to the fact that its performance is superior to the traditional methods proposed in computer vision and also not yet be widely used in tasks related to the agricultural area. The use of a multi-scale approach is related to the variation of the size of the patterns found in satellite images and aims to make the method more robust by allowing distinct features to be learned at each of the scales and used in a complementary way. |
publishDate |
2017 |
dc.date.issued.fl_str_mv |
2017-09-04 |
dc.date.accessioned.fl_str_mv |
2022-07-11T12:53:50Z |
dc.date.available.fl_str_mv |
2022-07-11T12:53:50Z |
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.uri.fl_str_mv |
http://hdl.handle.net/1843/43132 |
url |
http://hdl.handle.net/1843/43132 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/43132/5/rafael_baeta_dissertacao.pdf https://repositorio.ufmg.br/bitstream/1843/43132/6/license.txt |
bitstream.checksum.fl_str_mv |
6c8b90b2d5f03ea7e22eb87edcaa58d6 cda590c95a0b51b4d15f60c9642ca272 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589225442967552 |