障害物認識のための革新的深層学習技術：最新検出アルゴリズムの比較研究
Innovative Deep Learning Techniques for Obstacle Recognition: A Comparative Study of Modern Detection Algorithms
YOLOv5からv8までのモデルを比較し、リアルタイム障害物検出における性能を評価した。YOLOv8が最も高い精度と改善された適合率・再現率を示した。
著者: Santiago Pérez, Camila Gómez, Matías Rodríguez
分類: cs.CV, cs.RO
原文アブストラクト
This study explores a comprehensive approach to obstacle detection using advanced YOLO models, specifically YOLOv8, YOLOv7, YOLOv6, and YOLOv5. Leveraging deep learning techniques, the research focuses on the performance comparison of these models in real-time detection scenarios. The findings demonstrate that YOLOv8 achieves the highest accuracy with improved precision-recall metrics. Detailed training processes, algorithmic principles, and a range of experimental results are presented to validate the model's effectiveness.