Deep learning-based target spraying control of weeds in wheat fields at tillering stage

In this study, a target spraying decision and hysteresis algorithm is designed in conjunction with deep learning, which is deployed on a testbed for validation. The overall scheme of the target spraying control system is first proposed. Then YOLOv5s is lightweighted and improved. Based on this, a ta...

Full description

Saved in:
Bibliographic Details
Main Authors: Haiying Wang, Yu Chen, Shuo Zhang, Peijie Guo, Yuxiang Chen, Guangrui Hu, Yuxuan Ma
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1540722/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063161966723072
author Haiying Wang
Yu Chen
Shuo Zhang
Peijie Guo
Yuxiang Chen
Guangrui Hu
Yuxuan Ma
author_facet Haiying Wang
Yu Chen
Shuo Zhang
Peijie Guo
Yuxiang Chen
Guangrui Hu
Yuxuan Ma
author_sort Haiying Wang
collection DOAJ
description In this study, a target spraying decision and hysteresis algorithm is designed in conjunction with deep learning, which is deployed on a testbed for validation. The overall scheme of the target spraying control system is first proposed. Then YOLOv5s is lightweighted and improved. Based on this, a target spraying decision and hysteresis algorithm is designed, so that the target spraying system can precisely control the solenoid valve and differentiate spraying according to the distribution of weeds in different areas, and at the same time, successfully solve the operation hysteresis problem between the hardware. Finally, the algorithm was deployed on a testbed and simulated weeds and simulated tillering wheat were selected for bench experiments. Experiments on a dataset of realistic scenarios show that the improved model reduces the GFLOPs (computational complexity) and size by 52.2% and 42.4%, respectively, with mAP and F1 of 91.4% and 85.3%, which is an improvement of 0.2% and 0.8%, respectively, compared to the original model. The results of bench experiments showed that the spraying rate under the speed intervals of 0.3-0.4m/s, 0.4-0.5m/s and 0.5-0.6m/s reached 99.8%, 98.2% and 95.7%, respectively. Therefore, the algorithm can provide excellent spraying accuracy performance for the target spraying system, thus laying a theoretical foundation for the practical application of target spraying.
format Article
id doaj-art-c9d77bb967d741d9ae68e99a1c35b9e4
institution DOAJ
issn 1664-462X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-c9d77bb967d741d9ae68e99a1c35b9e42025-08-20T02:49:44ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-03-011610.3389/fpls.2025.15407221540722Deep learning-based target spraying control of weeds in wheat fields at tillering stageHaiying Wang0Yu Chen1Shuo Zhang2Peijie Guo3Yuxiang Chen4Guangrui Hu5Yuxuan Ma6College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaSchool of Design, Xi’an Technological University, Xian, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, ChinaIn this study, a target spraying decision and hysteresis algorithm is designed in conjunction with deep learning, which is deployed on a testbed for validation. The overall scheme of the target spraying control system is first proposed. Then YOLOv5s is lightweighted and improved. Based on this, a target spraying decision and hysteresis algorithm is designed, so that the target spraying system can precisely control the solenoid valve and differentiate spraying according to the distribution of weeds in different areas, and at the same time, successfully solve the operation hysteresis problem between the hardware. Finally, the algorithm was deployed on a testbed and simulated weeds and simulated tillering wheat were selected for bench experiments. Experiments on a dataset of realistic scenarios show that the improved model reduces the GFLOPs (computational complexity) and size by 52.2% and 42.4%, respectively, with mAP and F1 of 91.4% and 85.3%, which is an improvement of 0.2% and 0.8%, respectively, compared to the original model. The results of bench experiments showed that the spraying rate under the speed intervals of 0.3-0.4m/s, 0.4-0.5m/s and 0.5-0.6m/s reached 99.8%, 98.2% and 95.7%, respectively. Therefore, the algorithm can provide excellent spraying accuracy performance for the target spraying system, thus laying a theoretical foundation for the practical application of target spraying.https://www.frontiersin.org/articles/10.3389/fpls.2025.1540722/fullweed identificationweed distribution determinationhysteresis propertytarget sprayingdeep learning
spellingShingle Haiying Wang
Yu Chen
Shuo Zhang
Peijie Guo
Yuxiang Chen
Guangrui Hu
Yuxuan Ma
Deep learning-based target spraying control of weeds in wheat fields at tillering stage
Frontiers in Plant Science
weed identification
weed distribution determination
hysteresis property
target spraying
deep learning
title Deep learning-based target spraying control of weeds in wheat fields at tillering stage
title_full Deep learning-based target spraying control of weeds in wheat fields at tillering stage
title_fullStr Deep learning-based target spraying control of weeds in wheat fields at tillering stage
title_full_unstemmed Deep learning-based target spraying control of weeds in wheat fields at tillering stage
title_short Deep learning-based target spraying control of weeds in wheat fields at tillering stage
title_sort deep learning based target spraying control of weeds in wheat fields at tillering stage
topic weed identification
weed distribution determination
hysteresis property
target spraying
deep learning
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1540722/full
work_keys_str_mv AT haiyingwang deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT yuchen deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT shuozhang deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT peijieguo deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT yuxiangchen deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT guangruihu deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage
AT yuxuanma deeplearningbasedtargetsprayingcontrolofweedsinwheatfieldsattilleringstage