Enhancing Greenhouse Seedling Transplantation Efficiency Using YOLOv8 and AI-Based Image Processing

The shortage of labor in agriculture, particularly in greenhouse vegetable production, presents a significant challenge to global food security. This study explores the integration of Artificial Intelligence (AI) and image processing to enhance the efficiency and accuracy of seedling transplantation. Utilizing the YOLOv8 model, we developed an AI system capable of distinguishing seedlings such as pepper from empty cells with high precision. High-quality RGB images were collected and annotated using cvat.ai, and the model was trained on Google Colab with 300 epochs. The results demonstrated a significant reduction in bounding box, class, and object losses, alongside improvements in precision, recall, and mean average precision (mAP). Visual validation confirmed the model's effectiveness in real-world conditions. This research highlights the potential of AI-based image processing to address labor shortages, optimize resource use, and improve overall agricultural productivity and sustainability

Enhancing Greenhouse Seedling Transplantation Efficiency Using YOLOv8 and AI-Based Image Processing Keywords:

Artificial Intelligence , Greenhouse Seedling , Image Processing , YOLO model