Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”

Detalhes bibliográficos
Autor(a) principal: Pizzitola, Giuseppe
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.5/25463
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_b3646d32b77fda24ca00d764ebba2141
oai_identifier_str oai:www.repository.utl.pt:10400.5/25463
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”algorithmimage analysisprecision viticultureroboticsyield estimationMestrado em Engenharia de Viticultura e Enologia (Double degree) / Instituto Superior de Agronomia. Universidade de Lisboa / Faculdade de Ciências. Universidade do PortoNowadays, yield estimation represents one of the most important topics in viticulture. It can lead to a better vineyard management and to a better organization of harvesting operations in the vineyard and in the cellar. In recent years, image analysis has become an important tool to improve yield forecast, with the advantages of saving time and being non-invasive. This research aims to estimate the yield of the white cultivar ‘Encruzado’ using visible berry number counted in the images aquired at veraison and near harvest, using a manual RGB camera and the robot VINBOT. Images were collected in laboratory and in the field at the experimental vineyard of the Instituto Superior de Agronomia (ISA) in Lisbon. In the field images the number of visible berries per canopy meter was higher at maturation than at veraison, respectively 72.6 and 66.3. Regarding the percentage of visible berries, 30.2% where visible at veraison and 24.1% at maturation. Concerning percentage of berries occluded by other berries it was observed 28.7% at veraison and 24.3% at maturation. Regression analysis showed that the number of berries in the image explained a very high proportion of bunch weight variability, R2=0.64 at veraison and 0.91 at maturation. Regression analysis also showed that the canopy porosity explained a very high proportion of visible berries variability, R2=0.81 at veraison and 0.88 at maturation. The obtained regression models underestimated the yield with an higher error at veraison than at maturation. This underestimation indicates that the use of visible berry number on the images to estimate yield still needs further research to improve the algorithms accuracys.n.Lopes, CarlosPisciotta, AntoninoRepositório da Universidade de LisboaPizzitola, Giuseppe2022-09-09T12:00:03Z20212021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.5/25463TID:203082109engPizzitola, G. - Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”. Lisboa: ISA, 2021, 65 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:RCAAP2023-03-06T14:55:01Zoai:www.repository.utl.pt:10400.5/25463Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:09:19.849521Repositório 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 Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
title Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
spellingShingle Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
Pizzitola, Giuseppe
algorithm
image analysis
precision viticulture
robotics
yield estimation
title_short Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
title_full Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
title_fullStr Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
title_full_unstemmed Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
title_sort Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”
author Pizzitola, Giuseppe
author_facet Pizzitola, Giuseppe
author_role author
dc.contributor.none.fl_str_mv Lopes, Carlos
Pisciotta, Antonino
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Pizzitola, Giuseppe
dc.subject.por.fl_str_mv algorithm
image analysis
precision viticulture
robotics
yield estimation
topic algorithm
image analysis
precision viticulture
robotics
yield estimation
description Mestrado em Engenharia de Viticultura e Enologia (Double degree) / Instituto Superior de Agronomia. Universidade de Lisboa / Faculdade de Ciências. Universidade do Porto
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-01-01T00:00:00Z
2022-09-09T12:00:03Z
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/10400.5/25463
TID:203082109
url http://hdl.handle.net/10400.5/25463
identifier_str_mv TID:203082109
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Pizzitola, G. - Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Encruzado”. Lisboa: ISA, 2021, 65 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_ 1799131187753517056

Registros relacionados