Empowering Farmers: Real-time Coconut Tree Disease Detection and Management Using Yolov8 and Machine Learning Techniques
Year: 2025
Type: article
Abstract: In the evolving landscape of agricultural technology, enhancing machine learning applications with Explainable AI (XAI) offers significant advancements in managing crop health, especially for coconut farming. This project introduces a YOLOv8-based system enhanced with Explainable AI, designed for the real-time detection and management of coconut tree diseases. Employing advanced image processing techniques, the system analyzes input from various sources such as uploaded images, live webcam feeds, and RTSP streams to detect diseases with high accuracy and efficiency. The integration of Explainable AI, using EigenCAM, highlights regions of the image where the model detects diseases. It provides visual explanations by displaying the disease name and confidence score directly on the image, fostering greater transparency, fostering greater transparency and trust among users. The system’s core, a pre-trained YOLOv8 model, identifies multiple diseases and offers actionable insights and recommendations for each detected issue. Coupled with a user-friendly Streamlit interface, the system ensures accessibility and ease of use for farmers with varying levels of technical skill. Initial deployments have demonstrated impressive results in detection accuracy, processing speed, and user engagement, indicating a substantial impact on improving disease management practices in coconut plantations.
Source: Fuzzy Systems and Soft Computing
Author: Balakrishna Tilakachuri
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W4408835465