对比多个YOLO模型，选出最适合车载瞌睡检测的高效高精度方案。
Vision-Based Driver Drowsiness Monitoring: Comparative Analysis of YOLOv5-v11 Models
- 用7个YOLO变体在真实数据集上实测性能
- YOLOv9c准确率最高（mAP 0.5=0.986），YOLOv11n推理最快
- 适合嵌入式部署，为智能驾驶安全提供实用参考
驾驶员困倦是交通事故的重要成因，每年导致数千人死亡与受伤。本文对基于计算机视觉的实时非侵入式困倦检测方法进行了全面评估，聚焦于YOLO（You Look Only Once）系列算法。实验使用公开数据集UTA-RLDD，涵盖不同性别、佩戴眼镜、光照条件和肤色的样本。对七种YOLO变体（v5s, v9c, v9t, v10n, v10l, v11n, v11l）进行微调，以精确率、召回率、mAP0.5和mAP0.5-0.95作为评价指标。结果表明，YOLOv9c达到最高准确率（mAP0.5=0.986，召回率=0.978）；而YOLOv11n在精确率（0.954）与推理效率间取得最佳平衡，适合嵌入式部署。此外，采用Dlib面部关键点的眨眼比例（EAR）方法虽计算量小，但在姿态变化和遮挡下鲁棒性较差。研究揭示了准确率、延迟与资源消耗间的权衡，为自动驾驶与工业安全应用中的检测方案选择或组合提供实用指导。
原文摘要 · Abstract (English)
Driver drowsiness remains a critical factor in road accidents, accounting for thousands of fatalities and injuries each year. This paper presents a comprehensive evaluation of real-time, non-intrusive drowsiness detection methods, focusing on computer vision based YOLO (You Look Only Once) algorithms. A publicly available dataset namely, UTA-RLDD was used, containing both awake and drowsy conditions, ensuring variability in gender, eyewear, illumination, and skin tone. Seven YOLO variants (v5s, v9c, v9t, v10n, v10l, v11n, v11l) are fine-tuned, with performance measured in terms of Precision, Recall, mAP0.5, and mAP 0.5-0.95. Among these, YOLOv9c achieved the highest accuracy (0.986 mAP 0.5, 0.978 Recall) while YOLOv11n strikes the optimal balance between precision (0.954) and inference efficiency, making it highly suitable for embedded deployment. Additionally, we implement an Eye Aspect Ratio (EAR) approach using Dlib's facial landmarks, which despite its low computational footprint exhibits reduced robustness under pose variation and occlusions. Our findings illustrate clear trade offs between accuracy, latency, and resource requirements, and offer practical guidelines for selecting or combining detection methods in autonomous driving and industrial safety applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。