Related Experiment Video
Updated: Jan 7, 2026
08:16
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
Published on: October 24, 2025
410
RsegNet: An Advanced Methodology for Individual Rubber Tree Segmentation and Structural Parameter Extraction from UAV
Hengrui Wang1, Zilin Ye1, Qin Zhang1
1Central South University of Forestry and Technology, Changsha, Hunan, 410004, China.
Plant Phenomics (Washington, D.C.)
|December 19, 2025
Summary
A new method, RsegNet, accurately segments rubber tree point clouds using UAV LiDAR. This improves precision agriculture by enabling detailed assessment of tree architecture and traits for better plantation management.
Area of Science:
- Agricultural Engineering
- Remote Sensing
- Computer Vision
Background:
- Rubber trees are vital tropical crops requiring precise management.
- Traditional point cloud segmentation methods fail to accurately extract rubber tree structural parameters and spatial layout.
- Limitations hinder precision agriculture and refined management in rubber plantations.
Purpose of the Study:
- To develop an optimized dual-channel clustering method for UAV LiDAR-based rubber tree point cloud segmentation.
- To improve the assessment of rubber tree architecture and traits.
- To enhance precision monitoring, plantation management, and health assessment.
Main Methods:
- Proposed RsegNet, a UAV LiDAR-based network for rubber tree point cloud segmentation.
- Designed CosineU-Net for feature extraction, addressing branch-and-leaf overlap using cosine similarity.
- Developed a dual-channel clustering module with dynamic optimization for improved accuracy and reduced background interference.
Main Results:
- RsegNet achieved superior performance compared to five state-of-the-art networks on a self-built dataset and the FOR-instance forest dataset.
- The network reached an F-score of 86.1%, demonstrating high accuracy in segmentation.
- Successfully calculated structural attributes like height, crown diameter, and volume for rubber trees.
Conclusions:
- The proposed RsegNet method significantly improves rubber tree point cloud segmentation accuracy.
- This approach provides robust support for precise monitoring, plantation management, and health assessment of rubber trees.
- The method offers a valuable tool for advancing precision agriculture in rubber plantations.
