A Method for Measuring Strawberry Leaf Area Based on Three-Dimensional Point Cloud Instance Segmentation
With effective protective covering and microclimate control, greenhouse crops offer significant advantages, such as high yield and quality, remaining unaffected by seasonal variations and meeting the demand for diverse agricultural products. Efficient production relies on precise automatic control o...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10872974/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With effective protective covering and microclimate control, greenhouse crops offer significant advantages, such as high yield and quality, remaining unaffected by seasonal variations and meeting the demand for diverse agricultural products. Efficient production relies on precise automatic control of the environment and nutrients, and the leaf area index is a crucial growth parameter that affects indoor microclimate and nutrient transport within plants. Therefore, real-time monitoring of leaf area is essential for adjusting control strategies. This study introduces a strawberry three-dimensional point cloud instance segmentation method to address the challenge of stem and leaf instance segmentation in calculating plant leaf area using three-dimensional point cloud data. High-quality point cloud data were obtained using a three-dimensional scanner, and feature enhancement was achieved through the Leaf Vein and Boundary Preserving Sampling method. The network achieved an average precision of 90.41% for instance segmentation, with the precision of leaf segmentation reaching 93.63%. The Mean Absolute Error of the reconstructed leaf area, calculated using the Poisson surface reconstruction method with boundary processing, was 5.51 cm2, with a Root Mean Square Error of 6.91 cm2 and a Coefficient of Determination of 0.867. These findings provide valuable technical support and references for greenhouse cultivation and smart agriculture applications. The source code and dataset can be accessed at <uri>https://github.com/suyangsuluo/SGC</uri>. |
|---|---|
| ISSN: | 2169-3536 |