A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning

[EN] A site-specific weed detection and classification system was implemented with a stereoscopic video camera to reduce the adverse effects of chemical herbicides in rice field. A computer vision and meta-heuristic hybrid NN-ICA classifier were used to accurately discriminate between two weed varie...

Descripción completa

Detalles Bibliográficos
Autores: Dadashzadeh, Mojtaba, Abbaspour Gilandeh, Yousef, Mesri Gundoshmian, Tarahom, Sabzi, Sajad, Arribas, Juan Ignacio
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universidad de Salamanca (USAL)
Repositorio:GREDOS. Repositorio Institucional de la Universidad de Salamanca
OAI Identifier:oai:gredos.usal.es:10366/167630
Acceso en línea:http://hdl.handle.net/10366/167630
Access Level:acceso abierto
Palabra clave:Meta-heuristic algorithms
Neural network (NN)
Optimization
Stereo vision
3304.05 Sistemas de Reconocimiento de Caracteres
3102.01 Mecanización Agrícola
3311.02 Ingeniería de Control
id ES_77eaa161b2e370f2a69e4e4396015d9f
oai_identifier_str oai:gredos.usal.es:10366/167630
network_acronym_str ES
network_name_str España
repository_id_str
spelling A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learningDadashzadeh, MojtabaAbbaspour Gilandeh, YousefMesri Gundoshmian, TarahomSabzi, SajadArribas, Juan IgnacioMeta-heuristic algorithmsNeural network (NN)OptimizationStereo vision3304.05 Sistemas de Reconocimiento de Caracteres3102.01 Mecanización Agrícola3311.02 Ingeniería de Control[EN] A site-specific weed detection and classification system was implemented with a stereoscopic video camera to reduce the adverse effects of chemical herbicides in rice field. A computer vision and meta-heuristic hybrid NN-ICA classifier were used to accurately discriminate between two weed varieties and rice plants, under either natural light (NLC) or controlled light conditions (CLC). Preprocessing, segmentation, and matching procedures were performed on images coming from either right or left camera channels. Most discriminant features were selected from average, either arithmetic or geometric, images using a NN-PSO algorithm. Accuracy classification results with the stereo computer vision system under NLC were 85.71 % for the arithmetic mean (AM) and 85.63 % for the geometric mean (GM), test set. At the same time, accuracy classification results of the computer vision system under CLC reached 96.95 % for the AM case and 94.74 % for the GM case, being consistently higher than those under NLC.J. I. Arribas wants to thank the Spanish Ministry for Science, Innovation and Universities (MICINN), Agencia Estatal de Investigacion (AEI), as well as to the Fondo Europeo de Desarrollo Regional funds (FEDER, EU), under grant number PID2021-122210OB-I00, by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, European Union, for partially funding this work.J. I. Arribas wants to thank the Spanish Ministry for Science, Innovation and Universities (MICINN), Agencia Estatal de Investigacion (AEI), as well as to the Fondo Europeo de Desarrollo Regional funds (FEDER, EU), under grant number PID2021-122210OB-I00, by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, European Union, for partially funding this work.Elsevier202520252024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10366/167630reponame:GREDOS. Repositorio Institucional de la Universidad de Salamancainstname:Universidad de Salamanca (USAL)InglésPID2021-122210OB-I00MCIN/AEI/10.13039/501100011033Attribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:gredos.usal.es:10366/1676302026-06-07T06:28:51Z
dc.title.none.fl_str_mv A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
title A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
spellingShingle A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
Dadashzadeh, Mojtaba
Meta-heuristic algorithms
Neural network (NN)
Optimization
Stereo vision
3304.05 Sistemas de Reconocimiento de Caracteres
3102.01 Mecanización Agrícola
3311.02 Ingeniería de Control
title_short A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
title_full A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
title_fullStr A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
title_full_unstemmed A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
title_sort A stereoscopic video computer vision system for weed discrimination in rice field under both natural and controlled light conditions by machine learning
dc.creator.none.fl_str_mv Dadashzadeh, Mojtaba
Abbaspour Gilandeh, Yousef
Mesri Gundoshmian, Tarahom
Sabzi, Sajad
Arribas, Juan Ignacio
author Dadashzadeh, Mojtaba
author_facet Dadashzadeh, Mojtaba
Abbaspour Gilandeh, Yousef
Mesri Gundoshmian, Tarahom
Sabzi, Sajad
Arribas, Juan Ignacio
author_role author
author2 Abbaspour Gilandeh, Yousef
Mesri Gundoshmian, Tarahom
Sabzi, Sajad
Arribas, Juan Ignacio
author2_role author
author
author
author
dc.subject.none.fl_str_mv Meta-heuristic algorithms
Neural network (NN)
Optimization
Stereo vision
3304.05 Sistemas de Reconocimiento de Caracteres
3102.01 Mecanización Agrícola
3311.02 Ingeniería de Control
topic Meta-heuristic algorithms
Neural network (NN)
Optimization
Stereo vision
3304.05 Sistemas de Reconocimiento de Caracteres
3102.01 Mecanización Agrícola
3311.02 Ingeniería de Control
description [EN] A site-specific weed detection and classification system was implemented with a stereoscopic video camera to reduce the adverse effects of chemical herbicides in rice field. A computer vision and meta-heuristic hybrid NN-ICA classifier were used to accurately discriminate between two weed varieties and rice plants, under either natural light (NLC) or controlled light conditions (CLC). Preprocessing, segmentation, and matching procedures were performed on images coming from either right or left camera channels. Most discriminant features were selected from average, either arithmetic or geometric, images using a NN-PSO algorithm. Accuracy classification results with the stereo computer vision system under NLC were 85.71 % for the arithmetic mean (AM) and 85.63 % for the geometric mean (GM), test set. At the same time, accuracy classification results of the computer vision system under CLC reached 96.95 % for the AM case and 94.74 % for the GM case, being consistently higher than those under NLC.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10366/167630
url http://hdl.handle.net/10366/167630
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv PID2021-122210OB-I00
MCIN/AEI/10.13039/501100011033
dc.rights.none.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:GREDOS. Repositorio Institucional de la Universidad de Salamanca
instname:Universidad de Salamanca (USAL)
instname_str Universidad de Salamanca (USAL)
reponame_str GREDOS. Repositorio Institucional de la Universidad de Salamanca
collection GREDOS. Repositorio Institucional de la Universidad de Salamanca
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411157406646272
score 15,811543

Similares en LA Referencia