Abstract:

This project presents a smart crop monitoring system utilizing machine learning techniques to identify and manage plant diseases.

The system is built on a Raspberry Pi platform equipped with a Pi Camera for real-time image capture, enabling the detection of diseased crops.

Additionally, a soil moisture sensor and a DHT11 sensor are employed to monitor environmental conditions, specifically soil moisture, temperature, and humidity levels.

An automated response mechanism is integrated using a DC motor controlled by a relay to facilitate the removal of affected plants.

Data from all sensors, along with disease status, are visualized through a customized Android application, providing users with real-time insights and remote control capabilities.

This approach enhances agricultural productivity and supports sustainable farming practices by enabling timely intervention based on monitored conditions.

• Disease Detection: To develop and implement a machine learning model capable of accurately identifying and classifying plant diseases through image analysis captured by the Raspberry Pi Camera.
• Environmental Monitoring: To integrate soil moisture, temperature, and humidity sensors (DHT11) to continuously monitor environmental conditions, providing essential data for effective crop management.
• Automated Response System: To design an automated mechanism using a DC motor and relay that allows for the physical removal of diseased plants based on sensor data and machine learning predictions.
• Data Visualization: To create a user-friendly Android application that visualizes real-time data regarding crop health, environmental conditions, and system status, allowing users to make informed decisions.
• Remote Control and Notifications: To enable remote control of the DC motor and provide timely notifications through the mobile application, ensuring that farmers can respond promptly to changing conditions and disease alerts.

Block Diagram