EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments

Accurate detection of sugarcane nodes in natural environments is crucial for realizing intelligent sugarcane cutting and precise planting localization. However, current sugarcane node detection models often face challenges such as large parameter sizes, poor adaptability to deployment environments,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenhui Zheng, Lijiao Wei, Kangmin Lin, Weihua Huang, Shuo Wang, Dongjie Du, Tao Wu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1626725/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849703144437579776
author Zhenhui Zheng
Zhenhui Zheng
Zhenhui Zheng
Lijiao Wei
Lijiao Wei
Kangmin Lin
Weihua Huang
Shuo Wang
Dongjie Du
Tao Wu
author_facet Zhenhui Zheng
Zhenhui Zheng
Zhenhui Zheng
Lijiao Wei
Lijiao Wei
Kangmin Lin
Weihua Huang
Shuo Wang
Dongjie Du
Tao Wu
author_sort Zhenhui Zheng
collection DOAJ
description Accurate detection of sugarcane nodes in natural environments is crucial for realizing intelligent sugarcane cutting and precise planting localization. However, current sugarcane node detection models often face challenges such as large parameter sizes, poor adaptability to deployment environments, and limited real-world detection accuracy. To address these challenges, this research proposes a high-precision and lightweight EdgeSugarcane detection model. Firstly, based on YOLOv8, an improved EdgeSugarcane model is proposed. By introducing an interactive attention mechanism across channel and spatial dimensions, the model’s ability to represent node features is enhanced. Then, combined with TensorRT acceleration and optimization, the optimal FP16 quantization deployment scheme is proposed. Finally, end-to-end deployment is implemented on the NVIDIA Orin NX edge device, and its performance and resource consumption in practical applications are analyzed in depth. The experimental results show that EdgeSugarcane achieves a precision of 0.935, a recall of 0.8, and a mAP of 0.87 on the test set, with a model size of 89.9 MB. Compared to YOLOv8, the mAP is improved by 0.6%, and the inference speed is increased by 44%. With lossless precision, the inference time after FP16 quantization is only 1.9ms, a 3.3-fold improvement compared to before optimization, and the model size changes very little. On the NVIDIA Orin NX device, the single-frame inference, pre-processing, and post-processing times are 1.5ms, 60.6ms, and 4.4ms, respectively. The EdgeSugarcane model demonstrates excellent real-time performance and high accuracy under natural field conditions, offering a viable solution for integration into edge-based robotic systems for intelligent sugarcane cutting and precision planting.
format Article
id doaj-art-56b73ccf11a8467b9cc53dd478ad9ac2
institution DOAJ
issn 1664-462X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-56b73ccf11a8467b9cc53dd478ad9ac22025-08-20T03:17:23ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-07-011610.3389/fpls.2025.16267251626725EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environmentsZhenhui Zheng0Zhenhui Zheng1Zhenhui Zheng2Lijiao Wei3Lijiao Wei4Kangmin Lin5Weihua Huang6Shuo Wang7Dongjie Du8Tao Wu9College of Engineering, South China Agricultural University, Guangzhou, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, Guangdong, ChinaKey Laboratory of Agricultural Equipment for Tropical Crops, Ministry of Agriculture and Rural Affairs, Zhanjiang, Guangdong, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, Guangdong, ChinaKey Laboratory of Agricultural Equipment for Tropical Crops, Ministry of Agriculture and Rural Affairs, Zhanjiang, Guangdong, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, Guangdong, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, Guangdong, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, Guangdong, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaAccurate detection of sugarcane nodes in natural environments is crucial for realizing intelligent sugarcane cutting and precise planting localization. However, current sugarcane node detection models often face challenges such as large parameter sizes, poor adaptability to deployment environments, and limited real-world detection accuracy. To address these challenges, this research proposes a high-precision and lightweight EdgeSugarcane detection model. Firstly, based on YOLOv8, an improved EdgeSugarcane model is proposed. By introducing an interactive attention mechanism across channel and spatial dimensions, the model’s ability to represent node features is enhanced. Then, combined with TensorRT acceleration and optimization, the optimal FP16 quantization deployment scheme is proposed. Finally, end-to-end deployment is implemented on the NVIDIA Orin NX edge device, and its performance and resource consumption in practical applications are analyzed in depth. The experimental results show that EdgeSugarcane achieves a precision of 0.935, a recall of 0.8, and a mAP of 0.87 on the test set, with a model size of 89.9 MB. Compared to YOLOv8, the mAP is improved by 0.6%, and the inference speed is increased by 44%. With lossless precision, the inference time after FP16 quantization is only 1.9ms, a 3.3-fold improvement compared to before optimization, and the model size changes very little. On the NVIDIA Orin NX device, the single-frame inference, pre-processing, and post-processing times are 1.5ms, 60.6ms, and 4.4ms, respectively. The EdgeSugarcane model demonstrates excellent real-time performance and high accuracy under natural field conditions, offering a viable solution for integration into edge-based robotic systems for intelligent sugarcane cutting and precision planting.https://www.frontiersin.org/articles/10.3389/fpls.2025.1626725/fullsugarcaneYOLOv8TensorRTedge computinglightweight
spellingShingle Zhenhui Zheng
Zhenhui Zheng
Zhenhui Zheng
Lijiao Wei
Lijiao Wei
Kangmin Lin
Weihua Huang
Shuo Wang
Dongjie Du
Tao Wu
EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
Frontiers in Plant Science
sugarcane
YOLOv8
TensorRT
edge computing
lightweight
title EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
title_full EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
title_fullStr EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
title_full_unstemmed EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
title_short EdgeSugarcane: a lightweight high-precision method for real-time sugarcane node detection in edge computing environments
title_sort edgesugarcane a lightweight high precision method for real time sugarcane node detection in edge computing environments
topic sugarcane
YOLOv8
TensorRT
edge computing
lightweight
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1626725/full
work_keys_str_mv AT zhenhuizheng edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT zhenhuizheng edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT zhenhuizheng edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT lijiaowei edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT lijiaowei edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT kangminlin edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT weihuahuang edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT shuowang edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT dongjiedu edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments
AT taowu edgesugarcanealightweighthighprecisionmethodforrealtimesugarcanenodedetectioninedgecomputingenvironments