Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 50 min ago
Peer-reviewedCC BYFrontiers in plant science

A lightweight edge-deployable detection method for sugarcane stem nodes in intelligent seed cane cutting equipment

  • Zhaojun Niu1
  • Huadong Xiao1
  • Zebin Wu1
  • Bohao Lin2
  • Chang Ge1
  • Lijiao Wei1
  • Zexin Chen3
  • Weihua Huang1
  • Shuo Wang1
  • Dongjie Du1
  • Zhenhui Zheng1
  1. 1Agricultural Machinery Research Institute, Chinese Academy of Tropical Agricultural Sciences , ,
  2. 2College of Engineering, South China Agricultural University , ,
  3. 3College of Mathematics and Informatics, South China Agricultural University , ,
Read full textPDFDOICite

Abstract

Introduction: Accurate detection of sugarcane stem nodes is essential for intelligent seed cane cutting, yet existing detectors are often limited by large parameter counts, small target feature loss, and performance degradation under motion blur, making them difficult to deploy on edge devices.

Methods: This study developed SAD-YOLOv11, a lightweight and accurate detector based on YOLOv11, incorporating three modifications. These include an average pooling downsampling module named ADown for reducing computational cost while preserving edge features, a self attention based AIFI module for global contextual modeling, and a SEAMHead detection head with joint channel and spatial attention for adaptive feature calibration. The model was evaluated on a custom sugarcane stem node dataset.

Results: The model achieved a precision of 95.92%, a recall of 95.66%, and an mAP50 of 97.57%, maintaining detection accuracy at a level comparable to the baseline YOLOv11 while reducing parameter count and FLOPs by 18.13% and 17.55%. Under physically captured motion blur conditions, the model maintained more stable detection than the baseline, with the advantage becoming more pronounced as blur severity increased. Deployment on the Jetson Orin NX platform with TensorRT-FP16 quantization achieved a throughput of 37.1 FPS with a zero frame drop rate at a 30 FPS input frame rate, and compressed the engine size by 46.7%.

Discussion: These results suggest that SAD-YOLOv11 achieves a sound balance between detection accuracy and computational efficiency suitable for intelligent seed cane cutting equipment.

Related

  1. Lightweight visual detection approach for apple ripeness perception in intelligent orchard harvesting scenarios
    Mingqing Wu, Jianglei Xiao, Yanjun Chen +4
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMC
  2. LTK-YOLO: Lightweight Keypoint Detection for Robotic Tea Bud Picking
    Xiaomei Yi, Zekai Zheng, Hao Liang +3
    Plants (Basel, Switzerland)Peer-reviewedCC BYFull textPlant biologyEurope PMC
  3. LeafXNet: A Lightweight Explainable Model With Integrated Attention Mechanism for Fruit Leaf Disease Detection
    Shah Murtaza Rashid Al Masud, Farhana Sultana Eshita, Abu Bakar Siddique Mahi +4
    Plant directPeer-reviewedCC BYFull textPlant biologyEurope PMC
  4. Multi-scale lodging in rice and wheat: bridging biomechanical traits, phenotypic detection, and intelligent harvesting systems
    Tiantian Jing, Xianfei Xia, Zhong Tang +2
    Frontiers in plant sciencePeer-reviewedCC BYFull textPlant biologyEurope PMC
  5. Deep learning-based detection of construction waste in complex scenarios with an improved lightweight algorithm
    YiZhong Yang, YeXue Li, ShengWei Li +2
    PLOS OnePeer-reviewedCC BY 4.0Full textNeurosciencePhysiologyPLOS

Cite

BibTeXRIS
BibTeX
@article{niu2026lightweight,
  title = {{A lightweight edge-deployable detection method for sugarcane stem nodes in intelligent seed cane cutting equipment}},
  author = {Zhaojun Niu and Huadong Xiao and Zebin Wu and Bohao Lin and Chang Ge and Lijiao Wei and Zexin Chen and Weihua Huang and Shuo Wang and Dongjie Du and Zhenhui Zheng},
  journal = {Frontiers in plant science},
  year = {2026},
  month = sep,
  doi = {10.3389/fpls.2026.1934317},
  url = {https://europepmc.org/article/PMC/PMC13662428},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - A lightweight edge-deployable detection method for sugarcane stem nodes in intelligent seed cane cutting equipment
AU  - Zhaojun Niu
AU  - Huadong Xiao
AU  - Zebin Wu
AU  - Bohao Lin
AU  - Chang Ge
AU  - Lijiao Wei
AU  - Zexin Chen
AU  - Weihua Huang
AU  - Shuo Wang
AU  - Dongjie Du
AU  - Zhenhui Zheng
PY  - 2026
DA  - 2026/09/30
JO  - Frontiers in plant science
DO  - 10.3389/fpls.2026.1934317
UR  - https://europepmc.org/article/PMC/PMC13662428
AB  - Introduction: Accurate detection of sugarcane stem nodes is essential for intelligent seed cane cutting, yet existing detectors are often limited by large parameter counts, small target feature loss, and performance degradation under motion blur, making them difficult to deploy on edge devices.  Methods: This study developed SAD-YOLOv11, a lightweight and accurate detector based on YOLOv11, incorporating three modifications. These include an average pooling downsampling module named ADown for reducing computational cost while preserving edge features, a self attention based AIFI module for global contextual modeling, and a SEAMHead detection head with joint channel and spatial attention for adaptive feature calibration. The model was evaluated on a custom sugarcane stem node dataset.  Results: The model achieved a precision of 95.92%, a recall of 95.66%, and an mAP50 of 97.57%, maintaining detection accuracy at a level comparable to the baseline YOLOv11 while reducing parameter count and FLOPs by 18.13% and 17.55%. Under physically captured motion blur conditions, the model maintained more stable detection than the baseline, with the advantage becoming more pronounced as blur severity increased. Deployment on the Jetson Orin NX platform with TensorRT-FP16 quantization achieved a throughput of 37.1 FPS with a zero frame drop rate at a 30 FPS input frame rate, and compressed the engine size by 46.7%.  Discussion: These results suggest that SAD-YOLOv11 achieves a sound balance between detection accuracy and computational efficiency suitable for intelligent seed cane cutting equipment.
SN  - 1664-462X
ER  -