An Efficiency CNN Solution for Olive Disease Management Through FPGA

Olives, one of the world's oldest and most significant cultivated crops, face persistent threats from various diseases, devastatingly affecting olive production and quality. In this era of technological advancement, the integration of Convolutional Neural Networks (CNNs) has emerged as a promising tool for the early and accurate identification of diseases in agricultural crops. This work presents a novel solution of CNNs for the automated identification of diseases in olive plants in 3 categories (aculus olearius healthy and olive peacock spot). To further enhance the practicality and real-time applicability of the proposed system, an implementation of Field-Programmable Gate Arrays (FPGAs) is explored. This study delves into the FPGA-based deployment of the CNN solution, optimizing its computational efficiency for on-site disease diagnosis with a 98.82% accuracy rate. The results of this study reveal the potential of CNNs in revolutionizing olive disease management, enabling early intervention and precise treatment. Additionally, the FPGA implementation demonstrates the feasibility of deploying such advanced models where immediate decision-making is crucial for crop protection. This analysis paves the way for sustainable olive cultivation practices, ensuring the longevity and resilience of this invaluable crop in the face of evolving disease challenges.