Related Experiment Video
Updated: Aug 5, 2025
11:37
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
16.3K
Feasibility Study on the Classification of Persimmon Trees' Components Based on Hyperspectral LiDAR
Hui Shao1,2, Fuyu Wang1,2, Wei Li3
1School of Electronics and Information Engineering, Anhui Jianzhu University, Hefei 230601, China.
Sensors (Basel, Switzerland)
|March 30, 2023
Summary
This study presents a new method for classifying persimmon tree components using hyperspectral LiDAR data. Fusing spatial and spectral information improved classification accuracy, aiding precision orchard management.
Area of Science:
- Agricultural Engineering
- Remote Sensing
- Forestry
Background:
- Intelligent tree management is crucial for precision agriculture.
- Accurate identification of individual tree components is vital for growth analysis.
Purpose of the Study:
- To develop and evaluate a method for classifying persimmon tree components using hyperspectral LiDAR data.
- To improve classification accuracy by addressing the misclassification of edge points.
Main Methods:
- Extraction of nine spectral feature parameters from hyperspectral LiDAR point cloud data.
- Initial classification using random forest, support vector machine, and backpropagation neural network.
- Integration of spatial constraints with spectral information to refine classification.
Main Results:
- Preliminary classification showed limitations with edge points.
- The proposed method, fusing spatial and spectral data, increased overall classification accuracy by 6.55%.
- Successful 3D reconstruction of classified tree components was achieved.
Conclusions:
- The developed method effectively classifies persimmon tree components.
- The fusion of spatial constraints enhances the sensitivity to edge points and improves accuracy.
- This approach offers a valuable tool for precision orchard management and tree growth analysis.
