Cargando…

Rice Grain Detection and Counting Method Based on TCLE–YOLO Model

Thousand-grain weight is the main parameter for accurately estimating rice yields, and it is an important indicator for variety breeding and cultivation management. The accurate detection and counting of rice grains is an important prerequisite for thousand-grain weight measurements. However, becaus...

Descripción completa

Detalles Bibliográficos
Autores principales: Zou, Yu, Tian, Zefeng, Cao, Jiawen, Ren, Yi, Zhang, Yaping, Liu, Lu, Zhang, Peijiang, Ni, Jinlong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10675024/
https://www.ncbi.nlm.nih.gov/pubmed/38005517
http://dx.doi.org/10.3390/s23229129
_version_ 1785140966615678976
author Zou, Yu
Tian, Zefeng
Cao, Jiawen
Ren, Yi
Zhang, Yaping
Liu, Lu
Zhang, Peijiang
Ni, Jinlong
author_facet Zou, Yu
Tian, Zefeng
Cao, Jiawen
Ren, Yi
Zhang, Yaping
Liu, Lu
Zhang, Peijiang
Ni, Jinlong
author_sort Zou, Yu
collection PubMed
description Thousand-grain weight is the main parameter for accurately estimating rice yields, and it is an important indicator for variety breeding and cultivation management. The accurate detection and counting of rice grains is an important prerequisite for thousand-grain weight measurements. However, because rice grains are small targets with high overall similarity and different degrees of adhesion, there are still considerable challenges preventing the accurate detection and counting of rice grains during thousand-grain weight measurements. A deep learning model based on a transformer encoder and coordinate attention module was, therefore, designed for detecting and counting rice grains, and named TCLE-YOLO in which YOLOv5 was used as the backbone network. Specifically, to improve the feature representation of the model for small target regions, a coordinate attention (CA) module was introduced into the backbone module of YOLOv5. In addition, another detection head for small targets was designed based on a low-level, high-resolution feature map, and the transformer encoder was applied to the neck module to expand the receptive field of the network and enhance the extraction of key feature of detected targets. This enabled our additional detection head to be more sensitive to rice grains, especially heavily adhesive grains. Finally, EIoU loss was used to further improve accuracy. The experimental results show that, when applied to the self-built rice grain dataset, the precision, recall, and mAP@0.5 of the TCLE–YOLO model were 99.20%, 99.10%, and 99.20%, respectively. Compared with several state-of-the-art models, the proposed TCLE–YOLO model achieves better detection performance. In summary, the rice grain detection method built in this study is suitable for rice grain recognition and counting, and it can provide guidance for accurate thousand-grain weight measurements and the effective evaluation of rice breeding.
format Online
Article
Text
id pubmed-10675024
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106750242023-11-12 Rice Grain Detection and Counting Method Based on TCLE–YOLO Model Zou, Yu Tian, Zefeng Cao, Jiawen Ren, Yi Zhang, Yaping Liu, Lu Zhang, Peijiang Ni, Jinlong Sensors (Basel) Article Thousand-grain weight is the main parameter for accurately estimating rice yields, and it is an important indicator for variety breeding and cultivation management. The accurate detection and counting of rice grains is an important prerequisite for thousand-grain weight measurements. However, because rice grains are small targets with high overall similarity and different degrees of adhesion, there are still considerable challenges preventing the accurate detection and counting of rice grains during thousand-grain weight measurements. A deep learning model based on a transformer encoder and coordinate attention module was, therefore, designed for detecting and counting rice grains, and named TCLE-YOLO in which YOLOv5 was used as the backbone network. Specifically, to improve the feature representation of the model for small target regions, a coordinate attention (CA) module was introduced into the backbone module of YOLOv5. In addition, another detection head for small targets was designed based on a low-level, high-resolution feature map, and the transformer encoder was applied to the neck module to expand the receptive field of the network and enhance the extraction of key feature of detected targets. This enabled our additional detection head to be more sensitive to rice grains, especially heavily adhesive grains. Finally, EIoU loss was used to further improve accuracy. The experimental results show that, when applied to the self-built rice grain dataset, the precision, recall, and mAP@0.5 of the TCLE–YOLO model were 99.20%, 99.10%, and 99.20%, respectively. Compared with several state-of-the-art models, the proposed TCLE–YOLO model achieves better detection performance. In summary, the rice grain detection method built in this study is suitable for rice grain recognition and counting, and it can provide guidance for accurate thousand-grain weight measurements and the effective evaluation of rice breeding. MDPI 2023-11-12 /pmc/articles/PMC10675024/ /pubmed/38005517 http://dx.doi.org/10.3390/s23229129 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zou, Yu
Tian, Zefeng
Cao, Jiawen
Ren, Yi
Zhang, Yaping
Liu, Lu
Zhang, Peijiang
Ni, Jinlong
Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title_full Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title_fullStr Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title_full_unstemmed Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title_short Rice Grain Detection and Counting Method Based on TCLE–YOLO Model
title_sort rice grain detection and counting method based on tcle–yolo model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10675024/
https://www.ncbi.nlm.nih.gov/pubmed/38005517
http://dx.doi.org/10.3390/s23229129
work_keys_str_mv AT zouyu ricegraindetectionandcountingmethodbasedontcleyolomodel
AT tianzefeng ricegraindetectionandcountingmethodbasedontcleyolomodel
AT caojiawen ricegraindetectionandcountingmethodbasedontcleyolomodel
AT renyi ricegraindetectionandcountingmethodbasedontcleyolomodel
AT zhangyaping ricegraindetectionandcountingmethodbasedontcleyolomodel
AT liulu ricegraindetectionandcountingmethodbasedontcleyolomodel
AT zhangpeijiang ricegraindetectionandcountingmethodbasedontcleyolomodel
AT nijinlong ricegraindetectionandcountingmethodbasedontcleyolomodel