Quantitative and Correlation Analysis of Pear Leaf Dynamics Under Wind Field Disturbances

Yunfei Wang, Xiang Dong (), Weidong Jia, Mingxiong Ou, Shiqun Dai, Zhenlei Zhang and Ruohan Shi
Additional contact information
Yunfei Wang: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Xiang Dong: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Weidong Jia: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Mingxiong Ou: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Shiqun Dai: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Zhenlei Zhang: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Ruohan Shi: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China

Agriculture, 2025, vol. 15, issue 15, 1-15

Abstract: In wind-assisted orchard spraying operations, the dynamic response of leaves—manifested through changes in their posture—critically influences droplet deposition on both sides of the leaf surface and the penetration depth into the canopy. These factors are pivotal in determining spray coverage and the spatial distribution of pesticide efficacy. However, current research lacks comprehensive quantification and correlation analysis of the temporal response characteristics of leaves under wind disturbances. To address this gap, a systematic analytical framework was proposed, integrating real-time leaf segmentation and tracking, geometric feature quantification, and statistical correlation modeling. High-frame-rate videos of fluttering leaves were acquired under controlled wind conditions, and background segmentation was performed using principal component analysis (PCA) followed by clustering in the reduced feature space. A fine-tuned Segment Anything Model 2 (SAM2-FT) was employed to extract dynamic leaf masks and enable frame-by-frame tracking. Based on the extracted masks, time series of leaf area and inclination angle were constructed. Subsequently, regression analysis, cross-correlation functions, and Granger causality tests were applied to investigate cooperative responses and potential driving relationships among leaves. Results showed that the SAM2-FT model significantly outperformed the YOLO series in segmentation accuracy, achieving a precision of 98.7% and recall of 97.48%. Leaf area exhibited strong linear coupling and directional causality, while angular responses showed weaker correlations but demonstrated localized synchronization. This study offers a methodological foundation for quantifying temporal dynamics in wind–leaf systems and provides theoretical insights for the adaptive control and optimization of intelligent spraying strategies.

Keywords: precision spraying; dynamic leaf tracking; temporal quantification; synergistic response analysis (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/15/1597/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/15/1597/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:15:p:1597-:d:1709366

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().