Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments
Accurate detection of sugarcane nodes in complex field environments is a critical prerequisite for intelligent seed cutting and automated planting. However, existing detection methods often suffer from large model sizes and suboptimal performance, limiting their applicability on resource-constrained...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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.2025.1643967/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849232982778314752 |
|---|---|
| author | Lijiao Wei Lijiao Wei Shuo Wang Xinwei Liang Dongjie Du Xinyi Huang Ming Li Yuangang Hua Weihua Huang Zhenhui Zheng Zhenhui Zheng |
| author_facet | Lijiao Wei Lijiao Wei Shuo Wang Xinwei Liang Dongjie Du Xinyi Huang Ming Li Yuangang Hua Weihua Huang Zhenhui Zheng Zhenhui Zheng |
| author_sort | Lijiao Wei |
| collection | DOAJ |
| description | Accurate detection of sugarcane nodes in complex field environments is a critical prerequisite for intelligent seed cutting and automated planting. However, existing detection methods often suffer from large model sizes and suboptimal performance, limiting their applicability on resource-constrained edge devices. To address these challenges, we propose Slim-Sugarcane, a lightweight and high-precision node detection framework optimized for real-time deployment in natural agricultural settings. Built upon YOLOv8, our model integrates GSConv, a hybrid convolution module combining group and spatial convolutions, to significantly reduce computational overhead while maintaining detection accuracy. We further introduce a Cross-Stage Local Network module featuring a single-stage aggregation strategy, which effectively minimizes structural redundancy and enhances feature representation. The proposed framework is optimized with TensorRT and deployed using FP16 quantization on the NVIDIA Jetson Orin NX platform to ensure real-time performance under limited hardware conditions. Experimental results demonstrate that Slim-Sugarcane achieves a precision of 0.922, recall of 0.802, and mean average precision of 0.852, with an inference latency of only 60.1 ms and a GPU memory footprint of 1434 MB. The proposed method exhibits superior accuracy and computational efficiency compared to existing approaches, offering a promising solution for precision agriculture and intelligent sugarcane cultivation. |
| format | Article |
| id | doaj-art-8faa2cbed8574966aad788b1a0ae81fa |
| institution | Kabale University |
| 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-8faa2cbed8574966aad788b1a0ae81fa2025-08-20T14:12:09ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-07-011610.3389/fpls.2025.16439671643967Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environmentsLijiao Wei0Lijiao Wei1Shuo Wang2Xinwei Liang3Dongjie Du4Xinyi Huang5Ming Li6Yuangang Hua7Weihua Huang8Zhenhui Zheng9Zhenhui Zheng10Agricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaKey Laboratory of Agricultural Equipment for Tropical Crops, Ministry of Agriculture and Rural Affairs, Zhanjiang, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaSchool of Information Technology & Engineering, Guangzhou College of Commerce, Guangdong, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaAgricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang, ChinaKey Laboratory of Agricultural Equipment for Tropical Crops, Ministry of Agriculture and Rural Affairs, Zhanjiang, ChinaAccurate detection of sugarcane nodes in complex field environments is a critical prerequisite for intelligent seed cutting and automated planting. However, existing detection methods often suffer from large model sizes and suboptimal performance, limiting their applicability on resource-constrained edge devices. To address these challenges, we propose Slim-Sugarcane, a lightweight and high-precision node detection framework optimized for real-time deployment in natural agricultural settings. Built upon YOLOv8, our model integrates GSConv, a hybrid convolution module combining group and spatial convolutions, to significantly reduce computational overhead while maintaining detection accuracy. We further introduce a Cross-Stage Local Network module featuring a single-stage aggregation strategy, which effectively minimizes structural redundancy and enhances feature representation. The proposed framework is optimized with TensorRT and deployed using FP16 quantization on the NVIDIA Jetson Orin NX platform to ensure real-time performance under limited hardware conditions. Experimental results demonstrate that Slim-Sugarcane achieves a precision of 0.922, recall of 0.802, and mean average precision of 0.852, with an inference latency of only 60.1 ms and a GPU memory footprint of 1434 MB. The proposed method exhibits superior accuracy and computational efficiency compared to existing approaches, offering a promising solution for precision agriculture and intelligent sugarcane cultivation.https://www.frontiersin.org/articles/10.3389/fpls.2025.1643967/fullsugarcanedetectionlightweightedge deploymentTensorRT |
| spellingShingle | Lijiao Wei Lijiao Wei Shuo Wang Xinwei Liang Dongjie Du Xinyi Huang Ming Li Yuangang Hua Weihua Huang Zhenhui Zheng Zhenhui Zheng Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments Frontiers in Plant Science sugarcane detection lightweight edge deployment TensorRT |
| title | Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments |
| title_full | Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments |
| title_fullStr | Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments |
| title_full_unstemmed | Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments |
| title_short | Slim-sugarcane: a lightweight and high-precision method for sugarcane node detection and edge deployment in natural environments |
| title_sort | slim sugarcane a lightweight and high precision method for sugarcane node detection and edge deployment in natural environments |
| topic | sugarcane detection lightweight edge deployment TensorRT |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1643967/full |
| work_keys_str_mv | AT lijiaowei slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT lijiaowei slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT shuowang slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT xinweiliang slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT dongjiedu slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT xinyihuang slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT mingli slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT yuanganghua slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT weihuahuang slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT zhenhuizheng slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments AT zhenhuizheng slimsugarcanealightweightandhighprecisionmethodforsugarcanenodedetectionandedgedeploymentinnaturalenvironments |