Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks

The increasing public concern about food security and the stricter rules applied worldwide concerning herbicide use in the agri-food chain, reduce consumer acceptance of chemical plant protection. Site-Specific Weed Management can be achieved by applying a treatment only on the weed patches. Crop pl...

ver descrição completa

Detalhes bibliográficos
Autores: Peteinatos, Gerassimos G., Reichel, Philipp, Karouta, Jeremy, Andújar, Dionisio, Gerhards, Roland
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2020
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositório:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/225750
Acesso em linha:http://hdl.handle.net/10261/225750
Access Level:Acceso aberto
Palavra-chave:Computer vision
Convolutional neural networks
Deep learning
ResNet–50
Weed management
Weed identification
Xception
id ES_71e6e808d77dc928439405e9e8a6a2cd
oai_identifier_str oai:digital.csic.es:10261/225750
network_acronym_str ES
network_name_str España
repository_id_str
spelling Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural NetworksPeteinatos, Gerassimos G.Reichel, PhilippKarouta, JeremyAndújar, DionisioGerhards, RolandComputer visionConvolutional neural networksDeep learningResNet–50Weed managementWeed identificationXceptionThe increasing public concern about food security and the stricter rules applied worldwide concerning herbicide use in the agri-food chain, reduce consumer acceptance of chemical plant protection. Site-Specific Weed Management can be achieved by applying a treatment only on the weed patches. Crop plants and weeds identification is a necessary component for various aspects of precision farming in order to perform on the spot herbicide spraying or robotic weeding and precision mechanical weed control. During the last years, a lot of different methods have been proposed, yet more improvements need to be made on this problem, concerning speed, robustness, and accuracy of the algorithms and the recognition systems. Digital cameras and Artificial Neural Networks (ANNs) have been rapidly developed in the past few years, providing new methods and tools also in agriculture and weed management. In the current work, images gathered by an RGB camera of <i>Zea mays</i>, <i>Helianthus annuus</i>, <i>Solanum tuberosum</i>, <i>Alopecurus myosuroides</i>, <i>Amaranthus retroflexus</i>, <i>Avena fatua</i>, <i>Chenopodium album</i>, <i>Lamium purpureum</i>, <i>Matricaria chamomila</i>, <i>Setaria</i> spp., <i>Solanum nigrum</i> and <i>Stellaria media</i> were provided to train Convolutional Neural Networks (CNNs). Three different CNNs, namely VGG16, ResNet–50, and Xception, were adapted and trained on a pool of 93,000 images. The training images consisted of images with plant material with only one species per image. A Top-1 accuracy between 77% and 98% was obtained in plant detection and weed species discrimination, on the testing of the images.This research was funded by EIT FOOD as project# 20140 DACWEED: Detection and ACtuation system for WEED management. EIT FOOD is the innovation community on Food of the European Institute of Innovation and Technology (EIT), an EU body under Horizon 2020, the EU Framework Programme for Research and InnovationPeer reviewedMultidisciplinary Digital Publishing InstituteEIT FoodEuropean CommissionConsejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]2020202020202020info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10261/225750reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)InglésSíinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/2257502026-05-22T06:33:51Z
dc.title.none.fl_str_mv Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
title Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
spellingShingle Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
Peteinatos, Gerassimos G.
Computer vision
Convolutional neural networks
Deep learning
ResNet–50
Weed management
Weed identification
Xception
title_short Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
title_full Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
title_fullStr Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
title_full_unstemmed Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
title_sort Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks
dc.creator.none.fl_str_mv Peteinatos, Gerassimos G.
Reichel, Philipp
Karouta, Jeremy
Andújar, Dionisio
Gerhards, Roland
author Peteinatos, Gerassimos G.
author_facet Peteinatos, Gerassimos G.
Reichel, Philipp
Karouta, Jeremy
Andújar, Dionisio
Gerhards, Roland
author_role author
author2 Reichel, Philipp
Karouta, Jeremy
Andújar, Dionisio
Gerhards, Roland
author2_role author
author
author
author
dc.contributor.none.fl_str_mv EIT Food
European Commission
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Computer vision
Convolutional neural networks
Deep learning
ResNet–50
Weed management
Weed identification
Xception
topic Computer vision
Convolutional neural networks
Deep learning
ResNet–50
Weed management
Weed identification
Xception
description The increasing public concern about food security and the stricter rules applied worldwide concerning herbicide use in the agri-food chain, reduce consumer acceptance of chemical plant protection. Site-Specific Weed Management can be achieved by applying a treatment only on the weed patches. Crop plants and weeds identification is a necessary component for various aspects of precision farming in order to perform on the spot herbicide spraying or robotic weeding and precision mechanical weed control. During the last years, a lot of different methods have been proposed, yet more improvements need to be made on this problem, concerning speed, robustness, and accuracy of the algorithms and the recognition systems. Digital cameras and Artificial Neural Networks (ANNs) have been rapidly developed in the past few years, providing new methods and tools also in agriculture and weed management. In the current work, images gathered by an RGB camera of <i>Zea mays</i>, <i>Helianthus annuus</i>, <i>Solanum tuberosum</i>, <i>Alopecurus myosuroides</i>, <i>Amaranthus retroflexus</i>, <i>Avena fatua</i>, <i>Chenopodium album</i>, <i>Lamium purpureum</i>, <i>Matricaria chamomila</i>, <i>Setaria</i> spp., <i>Solanum nigrum</i> and <i>Stellaria media</i> were provided to train Convolutional Neural Networks (CNNs). Three different CNNs, namely VGG16, ResNet–50, and Xception, were adapted and trained on a pool of 93,000 images. The training images consisted of images with plant material with only one species per image. A Top-1 accuracy between 77% and 98% was obtained in plant detection and weed species discrimination, on the testing of the images.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/225750
url http://hdl.handle.net/10261/225750
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410685812736000
score 15,812429

Registros relacionados