Related Experiment Video
Updated: Aug 22, 2025
05:19
A Simple Method for Imaging Arabidopsis Leaves Using Perfluorodecalin as an Infiltrative Imaging Medium
Published on: January 16, 2012
21.8K
Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry
Arth M Patel1, Won Suk Lee2, Natalia A Peres3
1Department of Electrical & Computer Engineering, University of Florida, Gainesville, FL 32611, USA.
Sensors (Basel, Switzerland)
|November 11, 2022
Summary
A new AI-powered imaging system accurately detects leaf wetness duration (LWD) for strawberry disease risk assessment. This technology improves fungicide recommendations, benefiting growers and reducing chemical use.
Area of Science:
- Agricultural Science
- Computer Science
- Plant Pathology
Background:
- Accurate leaf wetness duration (LWD) measurement is crucial for the Strawberry Advisory System (SAS) to predict fungal disease risk.
- Traditional leaf wetness sensors have limitations, necessitating more precise detection methods for effective disease management and reduced fungicide application.
Purpose of the Study:
- To develop and evaluate an advanced leaf wetness detection system utilizing color imaging and artificial intelligence (AI).
- To enhance the accuracy of LWD measurements for improved disease risk modeling in strawberry cultivation.
Main Methods:
- A novel leaf wetness detection system was engineered, employing color imaging of a reference surface.
- A convolutional neural network (CNN) was utilized for AI-based analysis of the captured images.
- The system was field-tested across two locations during the 2021-2022 strawberry growing season, with results compared to manual observations.
Main Results:
- The AI and imaging-based system demonstrated high accuracy in identifying wetness on the reference surface.
- The developed system provides reliable LWD data, outperforming traditional methods.
Conclusions:
- The AI-powered imaging system is a viable and accurate tool for LWD detection in strawberry production.
- This technology can be integrated into the Strawberry Advisory System (SAS) to refine disease risk assessment and fungicide recommendations, with potential for multi-location deployment.
