Home / USS Digital Library / Presentation / Details

Optimizing YOLOv8 for Efficient Tomato Recognition in Greenhouse Environments Using Drone Imagery

ID: 34 View Protection: Public Updated time: 2024-08-05 15:25:24 Views: 980 Favorite Cancel favorite

Time: 01 Jan 1970, 08:00

Session: [RS2] Regular Session 2 » [RS2-4] Others

Source: 2024 Asian Conference on Communication and Networks

Type: Oral Presentation

File: Slide

Abstract:

This study delves into the practical application and fine-tuning of YOLOv8 models for real-time tomato recognition using drone imagery within greenhouse environments. We evaluated YOLO’s speed, robustness, and adaptability, finding that varying batch sizes and epochs had minimal impact on performance. Notably, YOLOv8n performed on par with the extra-large YOLOv8x model, offering a significant advantage: training time was up to 60 times shorter. Further tuning and innovative training strategies revealed that the Final Learning Rate (lrf) and dataset annotation quality were the most influential factors for model performance. Fine-tuning the lrf and re-annotating datasets markedly improved accuracy, underscoring the importance of optimizing learning rates and maintaining high-quality annotations for effective YOLO models. Our results also demonstrated the superiority of YOLOv8 over YOLOv5. The optimized YOLOv8n model is well-prepared for deployment in upcoming tomato recognition tasks, paving the way for more efficient agricultural monitoring. This work also provides valuable insights into the broader field of object recognition and offers practical guidance for researchers tackling similar challenges.

Keywords: AI, Agriculture, CV, Deep Learning, Machine Learning

Speaker:

Shovkovyy Oleg

CMKL

PRESENTATION LIBRARY

Optimizing YOLOv8 for Efficient Tomato Recognition in Greenhouse Environments Using Drone Imagery

Abstract:

Shovkovyy Oleg