Exportação concluída — 

Remote sensing and Deep Learning applied to vegetation mapping

Detalhes bibliográficos
Ano de defesa: 2023
Autor(a) principal: Martins, José Augusto Correa
Orientador(a): Marcato Junior, Jose
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Federal de Mato Grosso do Sul
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Brasil
Palavras-chave em Português:
Link de acesso: https://repositorio.ufms.br/handle/123456789/5584
Resumo: The fast development of human civilization imposed a recent and big environmental impact on the planet earth and the collective of life on Earth to support. The dawn of civilization is a very recent impact on the geologic time scale of the planet. Human needs to have a dimension of the effect of their actions inside the areas where it lives and in other natural environments to know their environmental impacts and consequences. The will to give an objective answer for this topic guided this research work. This doctoral dissertation presents the results of three years of research as a Doctoral student in the Environmental Technologies program at UFMS (Federal University of Mato Grosso do Sul). During my research, remote sensing and deep learning were the leading scientific fields I studied. The applications of the conjunction of these sciences to analyze the vegetation composition of urban and natural environments in the form of wetlands. We achieved exciting results in applying these techniques, i.e., an F1-score of 91% and an IoU of 73% for urban vegetation segmentation. Moreover, achieving a maximum 97% of F1-score for a specific plant species and 88% average for the whole dataset of 11 wetland plant species. The advances of the experiments conducted during the Doctorate program comprehend a broad range of sensors, from Unmanned aerial vehicles (UAV) that produce centimeter-level data to sensors capable of producing large earth mosaics. We also worked with a broad range of Deep Learning techniques to develop vegetation models. This research work and development can technologically assist the community in improving the understanding of the natural environment that we live in, leading to more resilient, sustainable, and healthy earth environmental systems
id UFMS_eb0e4e67729a9c9b908ae56ca3e20991
oai_identifier_str oai:repositorio.ufms.br:123456789/5584
network_acronym_str UFMS
network_name_str Repositório Institucional da UFMS
repository_id_str
spelling 2023-02-02T12:55:22Z2023-02-02T12:55:22Z2023https://repositorio.ufms.br/handle/123456789/5584The fast development of human civilization imposed a recent and big environmental impact on the planet earth and the collective of life on Earth to support. The dawn of civilization is a very recent impact on the geologic time scale of the planet. Human needs to have a dimension of the effect of their actions inside the areas where it lives and in other natural environments to know their environmental impacts and consequences. The will to give an objective answer for this topic guided this research work. This doctoral dissertation presents the results of three years of research as a Doctoral student in the Environmental Technologies program at UFMS (Federal University of Mato Grosso do Sul). During my research, remote sensing and deep learning were the leading scientific fields I studied. The applications of the conjunction of these sciences to analyze the vegetation composition of urban and natural environments in the form of wetlands. We achieved exciting results in applying these techniques, i.e., an F1-score of 91% and an IoU of 73% for urban vegetation segmentation. Moreover, achieving a maximum 97% of F1-score for a specific plant species and 88% average for the whole dataset of 11 wetland plant species. The advances of the experiments conducted during the Doctorate program comprehend a broad range of sensors, from Unmanned aerial vehicles (UAV) that produce centimeter-level data to sensors capable of producing large earth mosaics. We also worked with a broad range of Deep Learning techniques to develop vegetation models. This research work and development can technologically assist the community in improving the understanding of the natural environment that we live in, leading to more resilient, sustainable, and healthy earth environmental systemsO rápido desenvolvimento da civilização humana impôs um recente e grande impacto ambiental ao planeta Terra e ao coletivo da vida terrestre. O alvorecer da civilização é um impacto muito recente na escala de tempo geológico do planeta. O ser humano precisa ter uma dimensão do efeito de suas ações dentro das áreas onde vive e em outros ambientes naturais para conhecer seus impactos e consequências ambientais. A vontade de dar uma resposta objetiva a este tema orientou este trabalho de pesquisa. Esta tese de doutorado apresenta os resultados de três anos de pesquisa como aluno de doutorado no programa de Tecnologias Ambientais da UFMS (Universidade Federal de Mato Grosso do Sul). Durante minha pesquisa, sensoriamento remoto e aprendizado profundo foram os principais campos científicos que estudei. As aplicações da conjunção dessas ciências para analisar a composição da vegetação de ambientes urbanos e naturais na forma de zonas úmidas. Obtivemos resultados empolgantes na aplicação dessas técnicas, ou seja, um F1-score de 91% e um IoU de 73% para a segmentação da vegetação urbana. Além disso, alcançando um máximo de 97% de pontuação F1 para uma espécie de planta específica e 88% de média para todo o conjunto de dados de 11 espécies de plantas de zonas úmidas. Os avanços dos experimentos realizados durante o doutorado abrangem uma ampla gama de sensores, desde veículos aéreos não tripulados (VANT) que produzem dados centimétricos até sensores capazes de produzir grandes mosaicos da terra. Também trabalhamos com uma ampla gama de técnicas de Deep Learning para desenvolver modelos computacionais de de vegetação. Este trabalho de pesquisa e desenvolvimento pode ajudar tecnologicamente a comunidade a melhorar a compreensão do ambiente natural em que vivemos, levando a sistemas ambientais terrestres mais resilientes, sustentáveis e saudáveis.Universidade Federal de Mato Grosso do SulUFMSBrasilVisão ComputacionalSensoriamento RemotoAprendizado ProfundoRemote sensing and Deep Learning applied to vegetation mappinginfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisMarcato Junior, JoseMartins, José Augusto Correainfo:eu-repo/semantics/openAccessporreponame:Repositório Institucional da UFMSinstname:Universidade Federal de Mato Grosso do Sul (UFMS)instacron:UFMSORIGINALTese_jose_augusto_martins_defesa_.pdfTese_jose_augusto_martins_defesa_.pdfapplication/pdf16832963https://repositorio.ufms.br/bitstream/123456789/5584/1/Tese_jose_augusto_martins_defesa_.pdfb275fc7889e05e97bdddb343505ffd93MD51123456789/55842025-07-31 11:52:23.044oai:repositorio.ufms.br:123456789/5584Repositório InstitucionalPUBhttps://repositorio.ufms.br/oai/requestri.prograd@ufms.bropendoar:21242025-07-31T15:52:23Repositório Institucional da UFMS - Universidade Federal de Mato Grosso do Sul (UFMS)false
dc.title.pt_BR.fl_str_mv Remote sensing and Deep Learning applied to vegetation mapping
title Remote sensing and Deep Learning applied to vegetation mapping
spellingShingle Remote sensing and Deep Learning applied to vegetation mapping
Martins, José Augusto Correa
Visão Computacional
Sensoriamento Remoto
Aprendizado Profundo
title_short Remote sensing and Deep Learning applied to vegetation mapping
title_full Remote sensing and Deep Learning applied to vegetation mapping
title_fullStr Remote sensing and Deep Learning applied to vegetation mapping
title_full_unstemmed Remote sensing and Deep Learning applied to vegetation mapping
title_sort Remote sensing and Deep Learning applied to vegetation mapping
author Martins, José Augusto Correa
author_facet Martins, José Augusto Correa
author_role author
dc.contributor.advisor1.fl_str_mv Marcato Junior, Jose
dc.contributor.author.fl_str_mv Martins, José Augusto Correa
contributor_str_mv Marcato Junior, Jose
dc.subject.por.fl_str_mv Visão Computacional
Sensoriamento Remoto
Aprendizado Profundo
topic Visão Computacional
Sensoriamento Remoto
Aprendizado Profundo
description The fast development of human civilization imposed a recent and big environmental impact on the planet earth and the collective of life on Earth to support. The dawn of civilization is a very recent impact on the geologic time scale of the planet. Human needs to have a dimension of the effect of their actions inside the areas where it lives and in other natural environments to know their environmental impacts and consequences. The will to give an objective answer for this topic guided this research work. This doctoral dissertation presents the results of three years of research as a Doctoral student in the Environmental Technologies program at UFMS (Federal University of Mato Grosso do Sul). During my research, remote sensing and deep learning were the leading scientific fields I studied. The applications of the conjunction of these sciences to analyze the vegetation composition of urban and natural environments in the form of wetlands. We achieved exciting results in applying these techniques, i.e., an F1-score of 91% and an IoU of 73% for urban vegetation segmentation. Moreover, achieving a maximum 97% of F1-score for a specific plant species and 88% average for the whole dataset of 11 wetland plant species. The advances of the experiments conducted during the Doctorate program comprehend a broad range of sensors, from Unmanned aerial vehicles (UAV) that produce centimeter-level data to sensors capable of producing large earth mosaics. We also worked with a broad range of Deep Learning techniques to develop vegetation models. This research work and development can technologically assist the community in improving the understanding of the natural environment that we live in, leading to more resilient, sustainable, and healthy earth environmental systems
publishDate 2023
dc.date.accessioned.fl_str_mv 2023-02-02T12:55:22Z
dc.date.available.fl_str_mv 2023-02-02T12:55:22Z
dc.date.issued.fl_str_mv 2023
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://repositorio.ufms.br/handle/123456789/5584
url https://repositorio.ufms.br/handle/123456789/5584
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.publisher.none.fl_str_mv Universidade Federal de Mato Grosso do Sul
dc.publisher.initials.fl_str_mv UFMS
dc.publisher.country.fl_str_mv Brasil
publisher.none.fl_str_mv Universidade Federal de Mato Grosso do Sul
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFMS
instname:Universidade Federal de Mato Grosso do Sul (UFMS)
instacron:UFMS
instname_str Universidade Federal de Mato Grosso do Sul (UFMS)
instacron_str UFMS
institution UFMS
reponame_str Repositório Institucional da UFMS
collection Repositório Institucional da UFMS
bitstream.url.fl_str_mv https://repositorio.ufms.br/bitstream/123456789/5584/1/Tese_jose_augusto_martins_defesa_.pdf
bitstream.checksum.fl_str_mv b275fc7889e05e97bdddb343505ffd93
bitstream.checksumAlgorithm.fl_str_mv MD5
repository.name.fl_str_mv Repositório Institucional da UFMS - Universidade Federal de Mato Grosso do Sul (UFMS)
repository.mail.fl_str_mv ri.prograd@ufms.br
_version_ 1845882011638562816