Cargando…

WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion

Accurate and dependable weed detection technology is a prerequisite for weed control robots to do autonomous weeding. Due to the complexity of the farmland environment and the resemblance between crops and weeds, detecting weeds in the field under natural settings is a difficult task. Existing deep...

Descripción completa

Detalles Bibliográficos
Autores principales: Guo, Zhiqiang, Goh, Hui Hwang, Li, Xiuhua, Zhang, Muqing, Li, Yong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10408303/
https://www.ncbi.nlm.nih.gov/pubmed/37560032
http://dx.doi.org/10.3389/fpls.2023.1226329
_version_ 1785086156830932992
author Guo, Zhiqiang
Goh, Hui Hwang
Li, Xiuhua
Zhang, Muqing
Li, Yong
author_facet Guo, Zhiqiang
Goh, Hui Hwang
Li, Xiuhua
Zhang, Muqing
Li, Yong
author_sort Guo, Zhiqiang
collection PubMed
description Accurate and dependable weed detection technology is a prerequisite for weed control robots to do autonomous weeding. Due to the complexity of the farmland environment and the resemblance between crops and weeds, detecting weeds in the field under natural settings is a difficult task. Existing deep learning-based weed detection approaches often suffer from issues such as monotonous detection scene, lack of picture samples and location information for detected items, low detection accuracy, etc. as compared to conventional weed detection methods. To address these issues, WeedNet-R, a vision-based network for weed identification and localization in sugar beet fields, is proposed. WeedNet-R adds numerous context modules to RetinaNet’s neck in order to combine context information from many feature maps and so expand the effective receptive fields of the entire network. During model training, meantime, a learning rate adjustment method combining an untuned exponential warmup schedule and cosine annealing technique is implemented. As a result, the suggested method for weed detection is more accurate without requiring a considerable increase in model parameters. The WeedNet-R was trained and assessed using the OD-SugarBeets dataset, which is enhanced by manually adding the bounding box labels based on the publicly available agricultural dataset, i.e. SugarBeet2016. Compared to the original RetinaNet, the mAP of the proposed WeedNet-R increased in the weed detection job in sugar beet fields by 4.65% to 92.30%. WeedNet-R’s average precision for weed and sugar beet is 85.70% and 98.89%, respectively. WeedNet-R outperforms other sophisticated object detection algorithms in terms of detection accuracy while matching other single-stage detectors in terms of detection speed.
format Online
Article
Text
id pubmed-10408303
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-104083032023-08-09 WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion Guo, Zhiqiang Goh, Hui Hwang Li, Xiuhua Zhang, Muqing Li, Yong Front Plant Sci Plant Science Accurate and dependable weed detection technology is a prerequisite for weed control robots to do autonomous weeding. Due to the complexity of the farmland environment and the resemblance between crops and weeds, detecting weeds in the field under natural settings is a difficult task. Existing deep learning-based weed detection approaches often suffer from issues such as monotonous detection scene, lack of picture samples and location information for detected items, low detection accuracy, etc. as compared to conventional weed detection methods. To address these issues, WeedNet-R, a vision-based network for weed identification and localization in sugar beet fields, is proposed. WeedNet-R adds numerous context modules to RetinaNet’s neck in order to combine context information from many feature maps and so expand the effective receptive fields of the entire network. During model training, meantime, a learning rate adjustment method combining an untuned exponential warmup schedule and cosine annealing technique is implemented. As a result, the suggested method for weed detection is more accurate without requiring a considerable increase in model parameters. The WeedNet-R was trained and assessed using the OD-SugarBeets dataset, which is enhanced by manually adding the bounding box labels based on the publicly available agricultural dataset, i.e. SugarBeet2016. Compared to the original RetinaNet, the mAP of the proposed WeedNet-R increased in the weed detection job in sugar beet fields by 4.65% to 92.30%. WeedNet-R’s average precision for weed and sugar beet is 85.70% and 98.89%, respectively. WeedNet-R outperforms other sophisticated object detection algorithms in terms of detection accuracy while matching other single-stage detectors in terms of detection speed. Frontiers Media S.A. 2023-07-24 /pmc/articles/PMC10408303/ /pubmed/37560032 http://dx.doi.org/10.3389/fpls.2023.1226329 Text en Copyright © 2023 Guo, Goh, Li, Zhang and Li https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Guo, Zhiqiang
Goh, Hui Hwang
Li, Xiuhua
Zhang, Muqing
Li, Yong
WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title_full WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title_fullStr WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title_full_unstemmed WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title_short WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
title_sort weednet-r: a sugar beet field weed detection algorithm based on enhanced retinanet and context semantic fusion
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10408303/
https://www.ncbi.nlm.nih.gov/pubmed/37560032
http://dx.doi.org/10.3389/fpls.2023.1226329
work_keys_str_mv AT guozhiqiang weednetrasugarbeetfieldweeddetectionalgorithmbasedonenhancedretinanetandcontextsemanticfusion
AT gohhuihwang weednetrasugarbeetfieldweeddetectionalgorithmbasedonenhancedretinanetandcontextsemanticfusion
AT lixiuhua weednetrasugarbeetfieldweeddetectionalgorithmbasedonenhancedretinanetandcontextsemanticfusion
AT zhangmuqing weednetrasugarbeetfieldweeddetectionalgorithmbasedonenhancedretinanetandcontextsemanticfusion
AT liyong weednetrasugarbeetfieldweeddetectionalgorithmbasedonenhancedretinanetandcontextsemanticfusion