Cargando…

Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism

An improved lightweight network (Improved YOLOv5s) was proposed based on YOLOv5s in this study to realise all-weather detection of dragon fruit in a complex orchard environment. A ghost module was introduced in the original YOLOv5s to realise the lightweight of the model. The coordinate attention me...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Bin, Wang, Rongrong, Zhang, Huiming, Yin, Chenghai, Xia, Yuyang, Fu, Meng, Fu, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9632628/
https://www.ncbi.nlm.nih.gov/pubmed/36340417
http://dx.doi.org/10.3389/fpls.2022.1040923
_version_ 1784824076044337152
author Zhang, Bin
Wang, Rongrong
Zhang, Huiming
Yin, Chenghai
Xia, Yuyang
Fu, Meng
Fu, Wei
author_facet Zhang, Bin
Wang, Rongrong
Zhang, Huiming
Yin, Chenghai
Xia, Yuyang
Fu, Meng
Fu, Wei
author_sort Zhang, Bin
collection PubMed
description An improved lightweight network (Improved YOLOv5s) was proposed based on YOLOv5s in this study to realise all-weather detection of dragon fruit in a complex orchard environment. A ghost module was introduced in the original YOLOv5s to realise the lightweight of the model. The coordinate attention mechanism was joined to make the model accurately locate and identify the dense dragon fruits. A bidirectional feature pyramid network was built to improve the detection effect of dragon fruit at different scales. SIoU loss function was adopted to improve the convergence speed during model training. The improved YOLOv5s model was used to detect a dragon fruit dataset collected in the natural environment. Results showed that the mean average precision (mAP), precision (P) and recall (R) of the model was 97.4%, 96.4% and 95.2%, respectively. The model size, parameters (Params) and floating-point operations (FLOPs) were 11.5 MB, 5.2 M and 11.4 G, respectively. Compared with the original YOLOv5s network, the model size, Params and FLOPs of the improved model was reduced by 20.6%, 18.75% and 27.8%, respectively. Meanwhile, the mAP of the improved model was improved by 1.1%. The results prove that the improved model had a more lightweight structure and better detection performance. Moreover, the average precision (AP) of the improved YOLOv5s for dragon fruit under the front light, back light, side light, cloudy day and night was 99.5%, 97.3%, 98.5%, 95.5% and 96.1%, respectively. The detection performance met the requirements of all-weather detection of dragon fruit and the improved model had good robustness. This study provides a theoretical basis and technical support for fruit monitoring based on unmanned aerial vehicle technology and intelligent picking based on picking robot technology.
format Online
Article
Text
id pubmed-9632628
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-96326282022-11-04 Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism Zhang, Bin Wang, Rongrong Zhang, Huiming Yin, Chenghai Xia, Yuyang Fu, Meng Fu, Wei Front Plant Sci Plant Science An improved lightweight network (Improved YOLOv5s) was proposed based on YOLOv5s in this study to realise all-weather detection of dragon fruit in a complex orchard environment. A ghost module was introduced in the original YOLOv5s to realise the lightweight of the model. The coordinate attention mechanism was joined to make the model accurately locate and identify the dense dragon fruits. A bidirectional feature pyramid network was built to improve the detection effect of dragon fruit at different scales. SIoU loss function was adopted to improve the convergence speed during model training. The improved YOLOv5s model was used to detect a dragon fruit dataset collected in the natural environment. Results showed that the mean average precision (mAP), precision (P) and recall (R) of the model was 97.4%, 96.4% and 95.2%, respectively. The model size, parameters (Params) and floating-point operations (FLOPs) were 11.5 MB, 5.2 M and 11.4 G, respectively. Compared with the original YOLOv5s network, the model size, Params and FLOPs of the improved model was reduced by 20.6%, 18.75% and 27.8%, respectively. Meanwhile, the mAP of the improved model was improved by 1.1%. The results prove that the improved model had a more lightweight structure and better detection performance. Moreover, the average precision (AP) of the improved YOLOv5s for dragon fruit under the front light, back light, side light, cloudy day and night was 99.5%, 97.3%, 98.5%, 95.5% and 96.1%, respectively. The detection performance met the requirements of all-weather detection of dragon fruit and the improved model had good robustness. This study provides a theoretical basis and technical support for fruit monitoring based on unmanned aerial vehicle technology and intelligent picking based on picking robot technology. Frontiers Media S.A. 2022-10-20 /pmc/articles/PMC9632628/ /pubmed/36340417 http://dx.doi.org/10.3389/fpls.2022.1040923 Text en Copyright © 2022 Zhang, Wang, Zhang, Yin, Xia, Fu and Fu 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
Zhang, Bin
Wang, Rongrong
Zhang, Huiming
Yin, Chenghai
Xia, Yuyang
Fu, Meng
Fu, Wei
Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title_full Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title_fullStr Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title_full_unstemmed Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title_short Dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
title_sort dragon fruit detection in natural orchard environment by integrating lightweight network and attention mechanism
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9632628/
https://www.ncbi.nlm.nih.gov/pubmed/36340417
http://dx.doi.org/10.3389/fpls.2022.1040923
work_keys_str_mv AT zhangbin dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT wangrongrong dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT zhanghuiming dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT yinchenghai dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT xiayuyang dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT fumeng dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism
AT fuwei dragonfruitdetectioninnaturalorchardenvironmentbyintegratinglightweightnetworkandattentionmechanism