• Abhishek Salotkar
• Ayush Katre
• Yash kawale
• Rupam Gawali
• Dr. (Mrs) S.P. Washimkar

Agriculture is highly vulnerable to plant diseases, which can cause significant yield losses if not detected and treated early. Traditional diagnostic methods involve manual inspection by experts, which is labor-intensive, time-consuming, and prone to human error. Recent advancements in deep learning, particularly object detection models, offer promising automated solutions. However, deploying these models in remote agricultural fields lacking reliable internet connectivity remains a challenge. This paper presents a novel, edge-computing-based system for real-time plant disease detection. We leverage the state-of-the-art YOLOv8 architecture optimized for deployment on a Raspberry Pi 5 platform. The system acquires live images via a camera module, processes them locally for disease identification, and triggers localized hardware alerts (LEDs and Buzzers). Furthermore, it logs diagnostic data in an SQLite database and dispatches automated email reports asynchronously via SMTP, circumventing the need for cloud-based inference. Experimental results demonstrate that our custom-trained YOLOv8 model achieves a mean Average Precision (mAP) of 94.2% while maintaining real-time inference speeds suitable for practical field application. This integrated software-hardware solution bridges the gap between complex AI research and affordable, decentralized agricultural tools.

Deep Learning, Plant Disease Detection, YOLOv8, Edge Computing, Raspberry Pi, Internet of Things, Smart Agriculture.

"AUTOMATED PLANT DISEASE DETECTION USING DEEP LEARNING AND COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 10, page no.b863-b869, October-2026, Available :http://www.jetir.org/papers/JETIR2610191.pdf

"AUTOMATED PLANT DISEASE DETECTION USING DEEP LEARNING AND COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 10, page no. ppb863-b869, October-2026, Available at : http://www.jetir.org/papers/JETIR2610191.pdf