Cargando…

Weed25: A deep learning dataset for weed identification

Weed suppression is an important factor affecting crop yields. Precise identification of weed species will contribute to automatic weeding by applying proper herbicides, hoeing position determination, and hoeing depth to specific plants as well as reducing crop injury. However, the lack of datasets...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Pei, Tang, Yin, Luo, Fan, Wang, Lihong, Li, Chengsong, Niu, Qi, Li, Hui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9748680/
https://www.ncbi.nlm.nih.gov/pubmed/36531369
http://dx.doi.org/10.3389/fpls.2022.1053329
_version_ 1784849875615088640
author Wang, Pei
Tang, Yin
Luo, Fan
Wang, Lihong
Li, Chengsong
Niu, Qi
Li, Hui
author_facet Wang, Pei
Tang, Yin
Luo, Fan
Wang, Lihong
Li, Chengsong
Niu, Qi
Li, Hui
author_sort Wang, Pei
collection PubMed
description Weed suppression is an important factor affecting crop yields. Precise identification of weed species will contribute to automatic weeding by applying proper herbicides, hoeing position determination, and hoeing depth to specific plants as well as reducing crop injury. However, the lack of datasets of weeds in the field has limited the application of deep learning techniques in weed management. In this paper, it presented a dataset of weeds in fields, Weed25, which contained 14,035 images of 25 different weed species. Both monocot and dicot weed image resources were included in this dataset. Meanwhile, weed images at different growth stages were also recorded. Several common deep learning detection models—YOLOv3, YOLOv5, and Faster R-CNN—were applied for weed identification model training using this dataset. The results showed that the average accuracy of detection under the same training parameters were 91.8%, 92.4%, and 92.15% respectively. It presented that Weed25 could be a potential effective training resource for further development of in-field real-time weed identification models. The dataset is available at https://pan.baidu.com/s/1rnUoDm7IxxmX1n1LmtXNXw; the password is rn5h.
format Online
Article
Text
id pubmed-9748680
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97486802022-12-15 Weed25: A deep learning dataset for weed identification Wang, Pei Tang, Yin Luo, Fan Wang, Lihong Li, Chengsong Niu, Qi Li, Hui Front Plant Sci Plant Science Weed suppression is an important factor affecting crop yields. Precise identification of weed species will contribute to automatic weeding by applying proper herbicides, hoeing position determination, and hoeing depth to specific plants as well as reducing crop injury. However, the lack of datasets of weeds in the field has limited the application of deep learning techniques in weed management. In this paper, it presented a dataset of weeds in fields, Weed25, which contained 14,035 images of 25 different weed species. Both monocot and dicot weed image resources were included in this dataset. Meanwhile, weed images at different growth stages were also recorded. Several common deep learning detection models—YOLOv3, YOLOv5, and Faster R-CNN—were applied for weed identification model training using this dataset. The results showed that the average accuracy of detection under the same training parameters were 91.8%, 92.4%, and 92.15% respectively. It presented that Weed25 could be a potential effective training resource for further development of in-field real-time weed identification models. The dataset is available at https://pan.baidu.com/s/1rnUoDm7IxxmX1n1LmtXNXw; the password is rn5h. Frontiers Media S.A. 2022-11-30 /pmc/articles/PMC9748680/ /pubmed/36531369 http://dx.doi.org/10.3389/fpls.2022.1053329 Text en Copyright © 2022 Wang, Tang, Luo, Wang, Li, Niu 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
Wang, Pei
Tang, Yin
Luo, Fan
Wang, Lihong
Li, Chengsong
Niu, Qi
Li, Hui
Weed25: A deep learning dataset for weed identification
title Weed25: A deep learning dataset for weed identification
title_full Weed25: A deep learning dataset for weed identification
title_fullStr Weed25: A deep learning dataset for weed identification
title_full_unstemmed Weed25: A deep learning dataset for weed identification
title_short Weed25: A deep learning dataset for weed identification
title_sort weed25: a deep learning dataset for weed identification
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9748680/
https://www.ncbi.nlm.nih.gov/pubmed/36531369
http://dx.doi.org/10.3389/fpls.2022.1053329
work_keys_str_mv AT wangpei weed25adeeplearningdatasetforweedidentification
AT tangyin weed25adeeplearningdatasetforweedidentification
AT luofan weed25adeeplearningdatasetforweedidentification
AT wanglihong weed25adeeplearningdatasetforweedidentification
AT lichengsong weed25adeeplearningdatasetforweedidentification
AT niuqi weed25adeeplearningdatasetforweedidentification
AT lihui weed25adeeplearningdatasetforweedidentification