This research delves into the development of a fatigue detection system based on modern object detection algorithms, particularly YOLO (You Only Look Once) models, including YOLOv5, YOLOv6, YOLOv7, and YOLOv8. By comparing the performance of these models, we evaluate their effectiveness in real-time detection of fatigue-related behavior in drivers. The study addresses challenges like environmental variability and detection accuracy and suggests a roadmap for enhancing real-time detection. Experimental results demonstrate that YOLOv8 offers superior performance, balancing accuracy with speed. Data augmentation techniques and model optimization have been key in enhancing system adaptability to various driving conditions.

翻译：本研究深入探讨了基于现代目标检测算法（特别是YOLO系列模型，包括YOLOv5、YOLOv6、YOLOv7和YOLOv8）的驾驶员疲劳检测系统开发。通过对比这些模型的性能，我们评估了它们在实时检测驾驶员疲劳相关行为方面的有效性。该研究解决了环境多变性和检测准确性等挑战，并提出了增强实时检测能力的路线图。实验结果表明，YOLOv8在准确性与速度之间取得了最佳平衡，展现出卓越的性能。数据增强技术和模型优化对于提升系统在不同驾驶条件下的适应能力起到了关键作用。