Citrus Health Monitoring
Research Group:A² LabStatus:Active
This project focuses on implementing an AI-powered smart farming system for monitoring and managing citrus plants within Agri AI Innovation Lab using IP/CCTV cameras, IoT cameras and raspbery pi . Each plant is uniquely identified with a QR code, allowing users to record ground truth data such as plant condition, growth stage, and observed issues through manual entry.
The system integrates computer vision and data analytics techniques to enhance precision agriculture. Key features include leaf color analysis for detecting nutrient deficiencies and diseases, canopy volume estimation to assess plant growth, and time-lapse growth analysis for tracking development over time. Environmental monitoring is also incorporated to understand the impact of surrounding conditions on plant health.
Additionally, each plant maintains an individual health record combining sensor data and user inputs. The collected data is further utilized for yield prediction, enabling informed decision-making for farm management. Overall, the system aims to improve productivity, reduce manual effort, and support data-driven agriculture practices.
Research Aim
The primary aim of this research is to develop and evaluate an intelligent smart farming system that utilizes AI and computer vision techniques to monitor citrus plant health, growth, and productivity.
Specifically, the research aims to:
- Analyze leaf color patterns to identify plant health conditions and potential diseases
- Estimate canopy volume to measure plant growth accurately
- Track growth patterns using time-lapse image analysis
- Integrate environmental and ground truth data for comprehensive plant monitoring
- Maintain individual plant health records using QR-based identification
- Predict crop yield based on collected visual and environmental data
The study ultimately seeks to demonstrate how AI-driven monitoring systems can enhance precision agriculture, improve crop management, and increase overall farm efficiency.