Related Experiment Video
Updated: Aug 22, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.6K
Identification and Localisation Algorithm for Sugarcane Stem Nodes by Combining YOLOv3 and Traditional Methods of
Deqiang Zhou1, Wenbo Zhao1, Yanxiang Chen1
1School of Mechanical Engineering, Jiangnan University, Wuxi 214000, China.
Sensors (Basel, Switzerland)
|November 11, 2022
Summary
This study introduces a novel algorithm for sugarcane stem node identification, enhancing automated cutting accuracy. The method combines YOLOv3 with computer vision techniques, achieving a 99.84% harmonic mean for precise stem node recognition.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Machine Learning
Background:
- Sugarcane stem node identification is crucial for industry automation and mechanization.
- Current methods face challenges in achieving rapid and accurate detection of sugarcane stem nodes.
Purpose of the Study:
- To develop an improved algorithm for accurate and efficient sugarcane stem node identification.
- To enhance the performance of automated sugarcane harvesting and processing.
Main Methods:
- A hybrid approach combining YOLOv3 object detection with traditional computer vision techniques.
- Image preprocessing including affine transformation and region of interest extraction.
- Novel gradient operator for edge extraction and local thresholding for image binarization.
Main Results:
- The proposed algorithm achieved a precision rate of 99.68%, recall rate of 100%, and harmonic mean of 99.84%.
- Significant improvements were observed compared to the standalone YOLOv3 network, with precision and harmonic mean increasing by 2.28% and 1.13%, respectively.
- The algorithm demonstrated the highest recognition rate among compared methods.
Conclusions:
- The integrated YOLOv3 and computer vision algorithm offers a highly accurate and efficient solution for sugarcane stem node identification.
- This advancement is vital for the future of intelligent and mechanized sugarcane operations.
- The proposed method sets a new benchmark for stem node recognition in agricultural applications.
