Detecting grape bunches in vineyard images: a comparison of YOLO versions

Autores
Martínez, Paula Cecilia; Dalmasso, Julieta; Montoya, Marcos; Millán, Emmanuel N.
Año de publicación
2025
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
This work evaluates the performance of different YOLO (You Only Look Once) versions for grape bunch detection, focusing on the inference stage on heterogeneous hardware infrastructures. Devices ranging from a Raspberry Pi 3 and a mini-PC to mid- and high-end GPUs, as well as a conventional desktop CPU, were used. The analysis focuses on measuring the inference times, accuracy, and relative cost of each conf iguration, with the goal of identifying viable solutions under different budget constraints. The results highlight the limitations of low-resource systems and the remarkable performance of modern GPUs, facilitating the selection of the most suitable environment for precision agriculture applications. This study contributes to the development of accessible tools for automated crop estimation using the YOLO image object detection model.
Red de Universidades con Carreras en Informática
Materia
Ciencias Informáticas
Object detection
Machine learning
Precision agriculture
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/191528
Acceder
id SEDICI_2293ba0382c68bf964dacf138931e757
oai_identifier_str oai:sedici.unlp.edu.ar:10915/191528
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Detecting grape bunches in vineyard images: a comparison of YOLO versionsMartínez, Paula CeciliaDalmasso, JulietaMontoya, MarcosMillán, Emmanuel N.Ciencias InformáticasObject detectionMachine learningPrecision agricultureThis work evaluates the performance of different YOLO (You Only Look Once) versions for grape bunch detection, focusing on the inference stage on heterogeneous hardware infrastructures. Devices ranging from a Raspberry Pi 3 and a mini-PC to mid- and high-end GPUs, as well as a conventional desktop CPU, were used. The analysis focuses on measuring the inference times, accuracy, and relative cost of each conf iguration, with the goal of identifying viable solutions under different budget constraints. The results highlight the limitations of low-resource systems and the remarkable performance of modern GPUs, facilitating the selection of the most suitable environment for precision agriculture applications. This study contributes to the development of accessible tools for automated crop estimation using the YOLO image object detection model.Red de Universidades con Carreras en Informática2025-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf64-73http://sedici.unlp.edu.ar/handle/10915/191528enginfo:eu-repo/semantics/altIdentifier/isbn/978-987-8258-99-7info:eu-repo/semantics/reference/hdl/10915/189846info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2026-05-27T11:46:59Zoai:sedici.unlp.edu.ar:10915/191528Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292026-05-27 11:46:59.482SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Detecting grape bunches in vineyard images: a comparison of YOLO versions
title Detecting grape bunches in vineyard images: a comparison of YOLO versions
spellingShingle Detecting grape bunches in vineyard images: a comparison of YOLO versions
Martínez, Paula Cecilia
Ciencias Informáticas
Object detection
Machine learning
Precision agriculture
title_short Detecting grape bunches in vineyard images: a comparison of YOLO versions
title_full Detecting grape bunches in vineyard images: a comparison of YOLO versions
title_fullStr Detecting grape bunches in vineyard images: a comparison of YOLO versions
title_full_unstemmed Detecting grape bunches in vineyard images: a comparison of YOLO versions
title_sort Detecting grape bunches in vineyard images: a comparison of YOLO versions
dc.creator.none.fl_str_mv Martínez, Paula Cecilia
Dalmasso, Julieta
Montoya, Marcos
Millán, Emmanuel N.
author Martínez, Paula Cecilia
author_facet Martínez, Paula Cecilia
Dalmasso, Julieta
Montoya, Marcos
Millán, Emmanuel N.
author_role author
author2 Dalmasso, Julieta
Montoya, Marcos
Millán, Emmanuel N.
author2_role author
author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Object detection
Machine learning
Precision agriculture
topic Ciencias Informáticas
Object detection
Machine learning
Precision agriculture
dc.description.none.fl_txt_mv This work evaluates the performance of different YOLO (You Only Look Once) versions for grape bunch detection, focusing on the inference stage on heterogeneous hardware infrastructures. Devices ranging from a Raspberry Pi 3 and a mini-PC to mid- and high-end GPUs, as well as a conventional desktop CPU, were used. The analysis focuses on measuring the inference times, accuracy, and relative cost of each conf iguration, with the goal of identifying viable solutions under different budget constraints. The results highlight the limitations of low-resource systems and the remarkable performance of modern GPUs, facilitating the selection of the most suitable environment for precision agriculture applications. This study contributes to the development of accessible tools for automated crop estimation using the YOLO image object detection model.
Red de Universidades con Carreras en Informática
description This work evaluates the performance of different YOLO (You Only Look Once) versions for grape bunch detection, focusing on the inference stage on heterogeneous hardware infrastructures. Devices ranging from a Raspberry Pi 3 and a mini-PC to mid- and high-end GPUs, as well as a conventional desktop CPU, were used. The analysis focuses on measuring the inference times, accuracy, and relative cost of each conf iguration, with the goal of identifying viable solutions under different budget constraints. The results highlight the limitations of low-resource systems and the remarkable performance of modern GPUs, facilitating the selection of the most suitable environment for precision agriculture applications. This study contributes to the development of accessible tools for automated crop estimation using the YOLO image object detection model.
publishDate 2025
dc.date.none.fl_str_mv 2025-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/191528
url http://sedici.unlp.edu.ar/handle/10915/191528
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/isbn/978-987-8258-99-7
info:eu-repo/semantics/reference/hdl/10915/189846
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
64-73
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1866372196788600832
score 13.143419

Publicaciones similares