A Review of Automated Plant Disease Detection Using Camera-Based Systems for Scalable Farm Automation

Computer Engineering

Timely and accurate detection of plant diseases remain a cornerstone challenge in modern agriculture. While numerous studies have explored the use of artificial intelligence (AI) and deep learning techniques for disease identification from leaf images, the practical deployment of these solutions in real-world farm settings remains limited. Most existing research is confined to static datasets and laboratory conditions, lacking integration with automated systems that can actively monitor crops in real-time. This paper proposes a fully automated plant disease detection system that bridges this gap by combining AI-driven image analysis with camera-enabled Raspberry Pi units distributed across designated farm blocks. Each unit continuously captures crop images and uploads them to a centralized cloud server, where trained AI models detect and classify potential diseases. Upon detection, the system automatically notifies farm owners, enabling proactive intervention. The architecture supports scalability, remote monitoring, and modular expansion, offering a practical, end-to-end solution for smart agriculture. By integrating real-time automation with cloud-based intelligence, this approach moves beyond passive disease identification towards an active, responsive farm management system.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.