Grapevine yield estimation using image analysis for the variety Arinto

Detalhes bibliográficos
Autor(a) principal: Bonaria, Ruben
Data de Publicação: 2019
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.5/25409
Resumo: Mestrado em Engenharia de Viticultura e Enologia (Double Degree) / Instituto Superior de Agronomia. Universidade de Lisboa / Faculdade de Ciências. Universidade do Porto
id RCAP_991c1a9dbbf8d070b46c20f869d7b9f2
oai_identifier_str oai:www.repository.utl.pt:10400.5/25409
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Grapevine yield estimation using image analysis for the variety ArintoArintoimage analysisprecision viticultureroboticsyield estimationVinbotMestrado em Engenharia de Viticultura e Enologia (Double Degree) / Instituto Superior de Agronomia. Universidade de Lisboa / Faculdade de Ciências. Universidade do PortoYield estimation can lead to difficulties in the vineyard and winery, if it is done inaccurately following wrong procedures, doing a non-representative sampling or for the human error. Moreover, the traditional yield estimation methods are time consuming and destructive because they need someone that goes into the vineyard to count the yield components and that take out from the vineyard inflorescence or bunches to count and weight the flowers and the berries. To avoid these problems and the errors that can occur on this way, the development and application of new and innovative techniques to estimate the yield through the analysis of RGB images taken under field conditions are under study from different groups of research. In our research work we’ve studied the application of counting the yield components in the images throughout all the growing season. Furthermore, we’ve studied two different algorithms that starting from the survey of canopy porosity and/or visible bunches area, can help to do an estimation of the yield. The most promising yield estimation, based on the counting of the yield components done through image analysis, was found to be at the phenological stage of four leaves out, which shown a mean absolute percent error (MA%E) of 32 ± 2% and an correlaion coefficient (r Obs,Est) between observed and estimated shoots of 0.62. The two algorithms used different models: for estimating the area of the bunches covered by leaves and to estimate the weight of the bunches per linear canopy meter. When the area of the bunches without leaf occlusion was estimated, an average percentage of occlusion generated by the bunches on the other bunches of 8%, 6% and 12% respectively at pea size, veraison and maturation, was used to estimate the total area of the bunches. When the total area of the bunches per linear canopy meter was estimated the two models to estimate the grape weight were used. Finally, to estimate the weight at harvest, the growth factors of 6.6 and 1.7 respectively, at pea size and veraison were used. The first algorithm shown a MA%E, between the estimated and observed values of yield, of - 33.59%, -9.24% and -11.25%, instead the second algorithm shown a MA%E of -6.81%, -1.35% and 0.01% respectively at pea-size, veraison and maturations.n.Lopes, CarlosRepositório da Universidade de LisboaBonaria, Ruben2022-09-07T10:50:22Z20192019-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.5/25409TID:203083776engBonaria, R. - Grapevine yield estimation using image analysis for the variety Arinto. Lisboa: ISA, 2019, 73 p.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-06T14:54:58Zoai:www.repository.utl.pt:10400.5/25409Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:09:17.422628Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Grapevine yield estimation using image analysis for the variety Arinto
title Grapevine yield estimation using image analysis for the variety Arinto
spellingShingle Grapevine yield estimation using image analysis for the variety Arinto
Bonaria, Ruben
Arinto
image analysis
precision viticulture
robotics
yield estimation
Vinbot
title_short Grapevine yield estimation using image analysis for the variety Arinto
title_full Grapevine yield estimation using image analysis for the variety Arinto
title_fullStr Grapevine yield estimation using image analysis for the variety Arinto
title_full_unstemmed Grapevine yield estimation using image analysis for the variety Arinto
title_sort Grapevine yield estimation using image analysis for the variety Arinto
author Bonaria, Ruben
author_facet Bonaria, Ruben
author_role author
dc.contributor.none.fl_str_mv Lopes, Carlos
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Bonaria, Ruben
dc.subject.por.fl_str_mv Arinto
image analysis
precision viticulture
robotics
yield estimation
Vinbot
topic Arinto
image analysis
precision viticulture
robotics
yield estimation
Vinbot
description Mestrado em Engenharia de Viticultura e Enologia (Double Degree) / Instituto Superior de Agronomia. Universidade de Lisboa / Faculdade de Ciências. Universidade do Porto
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-01-01T00:00:00Z
2022-09-07T10:50:22Z
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/10400.5/25409
TID:203083776
url http://hdl.handle.net/10400.5/25409
identifier_str_mv TID:203083776
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Bonaria, R. - Grapevine yield estimation using image analysis for the variety Arinto. Lisboa: ISA, 2019, 73 p.
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 s.n.
publisher.none.fl_str_mv s.n.
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799131187665436672

Registros relacionados