The cultivation of Areca (betel nut) plays a significant role in the agricultural economy of many tropical regions. One of the persistent challenges in Areca farming is the timely and accurate detection of diseases that affect the trees, which are typically tall and require manual climbing for inspection and treatment. This process is not only labor-intensive but also poses serious risks to the safety of farm workers. Addressing this issue, the present project proposes an innovative solution — a tree-climbing robotic system integrated with image processing capabilities for automated disease detection and targeted pesticide spraying on Areca trees.

The system is built around a tree-climbing robot equipped with a camera module, spraying mechanism, and relay-controlled motors managed by an ESP32 microcontroller. The ESP32 is integrated with the Blynk IoT platform, allowing wireless control of the robot's movement via a smartphone. Two relays are used to control the upward and downward motion of the robot, ensuring stable and precise navigation along the vertical surface of the tree.

At the core of disease detection is a Convolutional Neural Network (CNN) trained using a curated dataset of Areca leaf images, including healthy samples and various disease conditions like Kole Rot, Bette Rot, and Gotu disease. The trained model is deployed within a Python-based Tkinter GUI that allows farmers or operators to upload leaf images or use a live camera feed. The GUI classifies the images in real-time and displays the predicted disease class along with its confidence level. This enables immediate analysis and decision-making for treatment.

Once a disease is detected, the operator can remotely activate the spraying mechanism mounted on the robot, targeting only the affected area. This minimizes pesticide usage, lowers environmental impact, and reduces cost, while ensuring efficient disease control.

This hybrid integration of IoT, robotics, and artificial intelligence offers a smart agricultural solution that reduces labor dependency, improves safety, and increases precision in disease management for Areca farming. The system is scalable and can be adapted for use in other tall-tree crops or vertical plantation monitoring systems.

Components Used: