Tomato Stem and Leaf Segmentation and Phenotype Parameter Extraction Based on Improved Red Billed Blue Magpie Optimization Algorithm DOI Creative Commons
Zhang Lina, Ziyi Huang, Zhiyin Yang

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(2), P. 180 - 180

Published: Jan. 15, 2025

In response to the structural changes of tomato seedlings, traditional image techniques are difficult accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a point cloud stem segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The uses four-layer Convolutional Neural Network (CNN) for by incorporating an improved swarm intelligence algorithm with accuracy 0.965. Four phenotypic parameters plant were extracted. height, thickness, area inclination analyzed comparing values extracted manual measurements 3D technique. results showed that coefficients determination (R2) these 0.932, 0.741, 0.938 0.935, respectively, indicating high correlation. root mean square error (RMSE) was 0.511, 0.135, 0.989 3.628, reflecting level measured values. absolute percentage errors (APE) 1.970, 4.299, 4.365 5.531, which further quantified measurement accuracy. study, efficient adaptive intelligent optimization constructed, is capable optimizing data processing strategies achieve accurate data. This study provides new technical tool phenotyping helps improve management in agricultural production.

Language: Английский

Tomato Stem and Leaf Segmentation and Phenotype Parameter Extraction Based on Improved Red Billed Blue Magpie Optimization Algorithm DOI Creative Commons
Zhang Lina, Ziyi Huang, Zhiyin Yang

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(2), P. 180 - 180

Published: Jan. 15, 2025

In response to the structural changes of tomato seedlings, traditional image techniques are difficult accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a point cloud stem segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The uses four-layer Convolutional Neural Network (CNN) for by incorporating an improved swarm intelligence algorithm with accuracy 0.965. Four phenotypic parameters plant were extracted. height, thickness, area inclination analyzed comparing values extracted manual measurements 3D technique. results showed that coefficients determination (R2) these 0.932, 0.741, 0.938 0.935, respectively, indicating high correlation. root mean square error (RMSE) was 0.511, 0.135, 0.989 3.628, reflecting level measured values. absolute percentage errors (APE) 1.970, 4.299, 4.365 5.531, which further quantified measurement accuracy. study, efficient adaptive intelligent optimization constructed, is capable optimizing data processing strategies achieve accurate data. This study provides new technical tool phenotyping helps improve management in agricultural production.

Language: Английский

Citations

0