Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFG |
Texto Completo: | http://repositorio.bc.ufg.br/tede/handle/tede/11838 |
Resumo: | Precision agriculture grows along with new technologies. The use of images for agricultural analysis has been growing and has low cost and processing agility. The presence of trees, with green foliage, inside or on the edges of crops can influence the results of the observation of plantations. The color of the tree tops can be confused with the color of the cultivar's leaves. In this work, we intend to assist in the detection of trees in aerial agricultural images using computational saliency as support. A literature review was conducted, that confirmed the applicability of the saliency methods in different sectors of agriculture. Then, experiments were carried out to evaluate the salient condition of trees in the studied context. It was noticed that some saliency methods highlight trees near to crops, however other regions are also highlighted. Neural networks were used to classify objects obtained from salient regions as being a tree or not. The classifiers achieved about 96\% accuracy. The Tree Detection Method created during this research has the potential to identify regions of trees present in a crop area, through aerial images. The proposed method, using the ResNet classifier, was be able to find about 69\% of the trees in the sample test images. |
id |
UFG-2_2a389875283b02709d0d7868093a3db8 |
---|---|
oai_identifier_str |
oai:repositorio.bc.ufg.br:tede/11838 |
network_acronym_str |
UFG-2 |
network_name_str |
Repositório Institucional da UFG |
repository_id_str |
|
spelling |
Soares, Fabrízzio Alphonsus Alves de Melo Nuneshttp://lattes.cnpq.br/7206645857721831Cabacinha, Christian DiasPedrini, HélioSoares, Fabrízzio Alphonsus Alves de Melo Nuneshttp://lattes.cnpq.br/0615396188934135Sousa, Naiane Maria de2022-01-07T11:24:13Z2022-01-07T11:24:13Z2021-12-09SOUSA, N. M. Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas. 2021. 73 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021.http://repositorio.bc.ufg.br/tede/handle/tede/11838ark:/38995/0013000001xmkPrecision agriculture grows along with new technologies. The use of images for agricultural analysis has been growing and has low cost and processing agility. The presence of trees, with green foliage, inside or on the edges of crops can influence the results of the observation of plantations. The color of the tree tops can be confused with the color of the cultivar's leaves. In this work, we intend to assist in the detection of trees in aerial agricultural images using computational saliency as support. A literature review was conducted, that confirmed the applicability of the saliency methods in different sectors of agriculture. Then, experiments were carried out to evaluate the salient condition of trees in the studied context. It was noticed that some saliency methods highlight trees near to crops, however other regions are also highlighted. Neural networks were used to classify objects obtained from salient regions as being a tree or not. The classifiers achieved about 96\% accuracy. The Tree Detection Method created during this research has the potential to identify regions of trees present in a crop area, through aerial images. The proposed method, using the ResNet classifier, was be able to find about 69\% of the trees in the sample test images.A agricultura de precisão cresce juntamente às novas tecnologias. O uso de imagens para análises agrícolas vem crescendo e apresenta baixo custo e agilidade de processamento. A presença de árvores, com folhagem verde, dentro ou às margens de lavouras pode influenciar nos resultados da observação de plantações. A cor da copa das árvores pode se confundir com a cor das folhas do cultivar. Neste trabalho, pretende-se auxiliar na detecção de árvores em imagens agrícolas aéreas utilizando como apoio a saliência computacional. Foi conduzida uma revisão da literatura que confirmou a aplicabilidade das técnicas de saliência em diversos setores da agricultura e agropecuária. Então, foram realizados experimentos para avaliar a condição saliente de árvores no contexto estudado. Percebeu-se que alguns métodos de saliência destacam árvores próximas às lavouras, contudo outras regiões também são destacadas. Foram utilizadas redes neurais para classificar objetos obtidos de regiões salientes como sendo árvore ou não. Os classificadores alcançaram cerca de 96\% de acurácia. O método de Detecção de Árvores criado durante esta pesquisa apresenta potencial para identificar regiões de árvores presentes em área de lavoura, através de imagens aéreas. O método proposto, utilizando o classificador ResNet mostrou-se capaz de encontrar em torno de 69\% das árvores nas amostras de teste.Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2022-01-06T13:40:49Z No. of bitstreams: 2 Dissertação - Naiane Maria de Sousa - 2021.pdf: 25190858 bytes, checksum: 9000bb1a40d732fd3ec6a6b97da32b93 (MD5) license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2022-01-07T11:24:13Z (GMT) No. of bitstreams: 2 Dissertação - Naiane Maria de Sousa - 2021.pdf: 25190858 bytes, checksum: 9000bb1a40d732fd3ec6a6b97da32b93 (MD5) license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)Made available in DSpace on 2022-01-07T11:24:13Z (GMT). No. of bitstreams: 2 Dissertação - Naiane Maria de Sousa - 2021.pdf: 25190858 bytes, checksum: 9000bb1a40d732fd3ec6a6b97da32b93 (MD5) license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5) Previous issue date: 2021-12-09Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESporUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RG)Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAgriculturaVisão computacionalClassificação de objetosAprendizado profundoAgricultureComputer visionObject classificationDeep learningCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAODetecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundasTree detection in aerial images with saliency methods and deep neural networksinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis20500500500500261841reponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGLICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://repositorio.bc.ufg.br/tede/bitstreams/ba7c89cb-6008-495b-bf76-4d5cc2249710/download8a4605be74aa9ea9d79846c1fba20a33MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805http://repositorio.bc.ufg.br/tede/bitstreams/f50150f2-0ec8-4b32-85b2-591a04db9f96/download4460e5956bc1d1639be9ae6146a50347MD52ORIGINALDissertação - Naiane Maria de Sousa - 2021.pdfDissertação - Naiane Maria de Sousa - 2021.pdfapplication/pdf25190858http://repositorio.bc.ufg.br/tede/bitstreams/66f22cfe-9636-459e-af3e-363a4bdc40e4/download9000bb1a40d732fd3ec6a6b97da32b93MD53tede/118382022-01-07 08:24:14.035http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accessoai:repositorio.bc.ufg.br:tede/11838http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttp://repositorio.bc.ufg.br/oai/requesttasesdissertacoes.bc@ufg.bropendoar:2022-01-07T11:24:14Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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 |
dc.title.pt_BR.fl_str_mv |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
dc.title.alternative.eng.fl_str_mv |
Tree detection in aerial images with saliency methods and deep neural networks |
title |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
spellingShingle |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas Sousa, Naiane Maria de Agricultura Visão computacional Classificação de objetos Aprendizado profundo Agriculture Computer vision Object classification Deep learning CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
title_full |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
title_fullStr |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
title_full_unstemmed |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
title_sort |
Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas |
author |
Sousa, Naiane Maria de |
author_facet |
Sousa, Naiane Maria de |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Soares, Fabrízzio Alphonsus Alves de Melo Nunes |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/7206645857721831 |
dc.contributor.referee1.fl_str_mv |
Cabacinha, Christian Dias |
dc.contributor.referee2.fl_str_mv |
Pedrini, Hélio |
dc.contributor.referee3.fl_str_mv |
Soares, Fabrízzio Alphonsus Alves de Melo Nunes |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/0615396188934135 |
dc.contributor.author.fl_str_mv |
Sousa, Naiane Maria de |
contributor_str_mv |
Soares, Fabrízzio Alphonsus Alves de Melo Nunes Cabacinha, Christian Dias Pedrini, Hélio Soares, Fabrízzio Alphonsus Alves de Melo Nunes |
dc.subject.por.fl_str_mv |
Agricultura Visão computacional Classificação de objetos Aprendizado profundo |
topic |
Agricultura Visão computacional Classificação de objetos Aprendizado profundo Agriculture Computer vision Object classification Deep learning CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.eng.fl_str_mv |
Agriculture Computer vision Object classification Deep learning |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
Precision agriculture grows along with new technologies. The use of images for agricultural analysis has been growing and has low cost and processing agility. The presence of trees, with green foliage, inside or on the edges of crops can influence the results of the observation of plantations. The color of the tree tops can be confused with the color of the cultivar's leaves. In this work, we intend to assist in the detection of trees in aerial agricultural images using computational saliency as support. A literature review was conducted, that confirmed the applicability of the saliency methods in different sectors of agriculture. Then, experiments were carried out to evaluate the salient condition of trees in the studied context. It was noticed that some saliency methods highlight trees near to crops, however other regions are also highlighted. Neural networks were used to classify objects obtained from salient regions as being a tree or not. The classifiers achieved about 96\% accuracy. The Tree Detection Method created during this research has the potential to identify regions of trees present in a crop area, through aerial images. The proposed method, using the ResNet classifier, was be able to find about 69\% of the trees in the sample test images. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021-12-09 |
dc.date.accessioned.fl_str_mv |
2022-01-07T11:24:13Z |
dc.date.available.fl_str_mv |
2022-01-07T11:24:13Z |
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 |
SOUSA, N. M. Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas. 2021. 73 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021. |
dc.identifier.uri.fl_str_mv |
http://repositorio.bc.ufg.br/tede/handle/tede/11838 |
dc.identifier.dark.fl_str_mv |
ark:/38995/0013000001xmk |
identifier_str_mv |
SOUSA, N. M. Detecção de árvores em imagens aéreas com métodos de saliência e redes neurais profundas. 2021. 73 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021. ark:/38995/0013000001xmk |
url |
http://repositorio.bc.ufg.br/tede/handle/tede/11838 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
20 |
dc.relation.confidence.fl_str_mv |
500 500 500 500 |
dc.relation.department.fl_str_mv |
26 |
dc.relation.cnpq.fl_str_mv |
184 |
dc.relation.sponsorship.fl_str_mv |
1 |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.publisher.program.fl_str_mv |
Programa de Pós-graduação em Ciência da Computação (INF) |
dc.publisher.initials.fl_str_mv |
UFG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Instituto de Informática - INF (RG) |
publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFG instname:Universidade Federal de Goiás (UFG) instacron:UFG |
instname_str |
Universidade Federal de Goiás (UFG) |
instacron_str |
UFG |
institution |
UFG |
reponame_str |
Repositório Institucional da UFG |
collection |
Repositório Institucional da UFG |
bitstream.url.fl_str_mv |
http://repositorio.bc.ufg.br/tede/bitstreams/ba7c89cb-6008-495b-bf76-4d5cc2249710/download http://repositorio.bc.ufg.br/tede/bitstreams/f50150f2-0ec8-4b32-85b2-591a04db9f96/download http://repositorio.bc.ufg.br/tede/bitstreams/66f22cfe-9636-459e-af3e-363a4bdc40e4/download |
bitstream.checksum.fl_str_mv |
8a4605be74aa9ea9d79846c1fba20a33 4460e5956bc1d1639be9ae6146a50347 9000bb1a40d732fd3ec6a6b97da32b93 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFG - Universidade Federal de Goiás (UFG) |
repository.mail.fl_str_mv |
tasesdissertacoes.bc@ufg.br |
_version_ |
1811721343648923648 |