Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images.
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
Texto Completo: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1151204 https://doi.org/10.3390/s22114116 |
Resumo: | We assessed the performance of Convolutional Neural Network (CNN)-based approaches using mobile phone images to estimate regrowth density in tropical forages. We generated a dataset composed of 1124 labeled images with 2 mobile phones 7 days after the harvest of the forage plants. Six architectures were evaluated, including AlexNet, ResNet (18, 34, and 50 layers), ResNeXt101, and DarkNet. The best regression model showed a mean absolute error of 7.70 and a correlation of 0.89. Our findings suggest that our proposal using deep learning on mobile phone images can successfully be used to estimate regrowth density in forages. |
id |
EMBR_30e2596001694e36271d35ba7dc1a218 |
---|---|
oai_identifier_str |
oai:www.alice.cnptia.embrapa.br:doc/1151204 |
network_acronym_str |
EMBR |
network_name_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository_id_str |
2154 |
spelling |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images.Banco de GermoplasmaForragemPanicum MaximumTecnologiaForageMechanical harvestingRegression analysisTilleringWe assessed the performance of Convolutional Neural Network (CNN)-based approaches using mobile phone images to estimate regrowth density in tropical forages. We generated a dataset composed of 1124 labeled images with 2 mobile phones 7 days after the harvest of the forage plants. Six architectures were evaluated, including AlexNet, ResNet (18, 34, and 50 layers), ResNeXt101, and DarkNet. The best regression model showed a mean absolute error of 7.70 and a correlation of 0.89. Our findings suggest that our proposal using deep learning on mobile phone images can successfully be used to estimate regrowth density in forages.Na publicação: Mateus Figueiredo Santos.LUIZ SANTOS, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; JOSÉ MARCATO JUNIOR, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; PEDRO ZAMBONI, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; MATEUS FIGUEIREDO SANTOS, CNPGC; LIANA JANK, CNPGC; EDILENE CAMPOS, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; EDSON TAKASHI MATSUBARA, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL.SANTOSMARCATO JUNIOR, J.ZAMBONI, P.SANTOS, M. F.JANK, L.CAMPOS, E.MATSUBARA, E. T.2023-01-25T13:01:26Z2023-01-25T13:01:26Z2023-01-252022info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleSensors, v. 22, article 4116, 2022.1424-8220http://www.alice.cnptia.embrapa.br/alice/handle/doc/1151204https://doi.org/10.3390/s22114116enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPA2023-01-25T13:01:26Zoai:www.alice.cnptia.embrapa.br:doc/1151204Repositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestopendoar:21542023-01-25T13:01:26falseRepositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestcg-riaa@embrapa.bropendoar:21542023-01-25T13:01:26Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
title |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
spellingShingle |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. SANTOS Banco de Germoplasma Forragem Panicum Maximum Tecnologia Forage Mechanical harvesting Regression analysis Tillering |
title_short |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
title_full |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
title_fullStr |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
title_full_unstemmed |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
title_sort |
Deep learning regression approaches applied to estimate tillering in tropical forages using mobile phone images. |
author |
SANTOS |
author_facet |
SANTOS MARCATO JUNIOR, J. ZAMBONI, P. SANTOS, M. F. JANK, L. CAMPOS, E. MATSUBARA, E. T. |
author_role |
author |
author2 |
MARCATO JUNIOR, J. ZAMBONI, P. SANTOS, M. F. JANK, L. CAMPOS, E. MATSUBARA, E. T. |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
LUIZ SANTOS, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; JOSÉ MARCATO JUNIOR, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; PEDRO ZAMBONI, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; MATEUS FIGUEIREDO SANTOS, CNPGC; LIANA JANK, CNPGC; EDILENE CAMPOS, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; EDSON TAKASHI MATSUBARA, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL. |
dc.contributor.author.fl_str_mv |
SANTOS MARCATO JUNIOR, J. ZAMBONI, P. SANTOS, M. F. JANK, L. CAMPOS, E. MATSUBARA, E. T. |
dc.subject.por.fl_str_mv |
Banco de Germoplasma Forragem Panicum Maximum Tecnologia Forage Mechanical harvesting Regression analysis Tillering |
topic |
Banco de Germoplasma Forragem Panicum Maximum Tecnologia Forage Mechanical harvesting Regression analysis Tillering |
description |
We assessed the performance of Convolutional Neural Network (CNN)-based approaches using mobile phone images to estimate regrowth density in tropical forages. We generated a dataset composed of 1124 labeled images with 2 mobile phones 7 days after the harvest of the forage plants. Six architectures were evaluated, including AlexNet, ResNet (18, 34, and 50 layers), ResNeXt101, and DarkNet. The best regression model showed a mean absolute error of 7.70 and a correlation of 0.89. Our findings suggest that our proposal using deep learning on mobile phone images can successfully be used to estimate regrowth density in forages. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022 2023-01-25T13:01:26Z 2023-01-25T13:01:26Z 2023-01-25 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Sensors, v. 22, article 4116, 2022. 1424-8220 http://www.alice.cnptia.embrapa.br/alice/handle/doc/1151204 https://doi.org/10.3390/s22114116 |
identifier_str_mv |
Sensors, v. 22, article 4116, 2022. 1424-8220 |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1151204 https://doi.org/10.3390/s22114116 |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
collection |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository.name.fl_str_mv |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
cg-riaa@embrapa.br |
_version_ |
1794503538866388992 |