基于多特征的疲劳驾驶安全检测
Fatigue Driving Safety Detection Based on Multi-Feature
DOI: 10.12677/CSA.2023.134067, PDF,   
作者: 刘晨熙, 刘 芬：天津职业技术师范大学电子工程学院，天津
关键词: Yolov5；深度学习；疲劳检测；Yolov5； Deep Learning； Fatigue Detection
摘要: 针对目前因疲劳驾驶导致的车祸比例占总车祸比例的极大一部分的情况，故本文设计出一种基于改进的Yolov5算法的疲劳驾驶检测系统。Yolov5算法的疲劳检测是指通过对车辆内部安装摄像头等图像传感器来获取驾驶员的人脸和面部特征，并通过机器视觉中的面部特征提取等方式获取驾驶员眼部以及嘴部状态，从而实现对驾驶员疲劳状态的分析判断。基于Yolov5算法的检测方法成本低，不需接触、检测方便，能够准确地分析出驾驶人的疲劳状况，可以极大地降低因疲劳驾驶而导致的事故发生概率。
Abstract: Aiming at the fact that the proportion of car accidents caused by fatigue driving accounts for a large part of the total number of car accidents, a fatigue driving detection system based on the improved Yolov5 algorithm is designed in this paper. The fatigue detection of the Yolov5 algorithm refers to the acquisition of the driver’s face and facial features by installing image sensors such as cameras in the vehicle, and the driver’s eye and mouth status through facial feature extraction in machine vision, so as to realize the analysis and judgment of the driver’s fatigue state. Based on Yolov5 algorithm, the detection method has low cost, no contact, convenient detection, can accurately analyze the fatigue of the driver, and can greatly reduce the probability of accidents caused by fatigue driving.
文章引用：刘晨熙, 刘芬. 基于多特征的疲劳驾驶安全检测[J]. 计算机科学与应用, 2023, 13(4): 680-688. https://doi.org/10.12677/CSA.2023.134067

参考文献

[1] (2001) Driver Fatigue and Road Accidents: A Literature Review and Position Paper. The Royal Society for the Prevention of Accidents, 1, 1-24.
[2] Tefft, B. (2014) Prevalence of Motor Vehicle Crashes Involving Drowsy Drivers. AAA Foundation for Traffic Safety, 45, 1-8.
[3] 袁泉, 李一兵, 陈康. 引发重大交通事故的显著因素特点分析及安全对策[J]. 中国司法鉴定, 2015(5): 34-40.
[4] Krajewski, J., Sommer, D., Trutschel, U., Edwards, D. and Golz, M. (2009) Steering Wheel Behavior Based Estimation of Fatigue. Proceedings of the Fifth International Driving Symposium on Human Factors in Driver Assessment, Train-ing and Vehicle Design, Big Sky, MT, 23-25 June 2009, 118-124. [Google Scholar] [CrossRef] 
[5] Mott, G.E., Forsman, P., Short, K.R., Mott, C.G. and Van Dongen, H.P.A. (2013) Efficient Driver Drowsiness Detection at Moderate Levels of Drowsiness. Accident Analysis & Prevention, 50, 341-350. [Google Scholar] [CrossRef] [PubMed]
[6] 彭成, 张乔虹, 唐朝晖, 桂卫华. 基于YOLOv5增强模型的口罩佩戴检测方法研究[J]. 计算机工程, 2022, 48(4): 39-49.
[7] Sun, C., Li, J.H., Song, Y. and Jin, L. (2014) Re-al-Time Driver Fatigue Detection Based on Eye State Recognition. Applied Mechanics and Materials, 457-458, 944-952. [Google Scholar] [CrossRef] 
[8] 林向会. 基于视频分析的铁路异物侵限检测系统的设计[D]: [硕士学位论文]. 贵阳: 贵州大学, 2021.
[9] Sun, Q., Liang, L., Dang, X.H. and Chen, Y. (2022) Deep Learning-Based Dimensional Emotion Recognition Combining the Attention Mechanism and Global Second-Order Feature Representations. Computers and Electrical Engineering, 104, Article ID: 108469. [Google Scholar] [CrossRef] 
[10] 李庆盛, 缪楠, 张鑫, 等. 基于注意力机制非对称残差网络和迁移学习的玉米危害图像识别[J]. 科学技术与工程, 2021, 21(15): 6249-6256.
[11] 李顺平, 彭成. 基于高效通道注意力机制和图像分割的轻量级表情识别算法[J]. 现代电子技术, 2022, 45(20): 149-156.
[12] Wang, S.Z., Zhang, Y.F., Hsieh, T.-H., Liu, W., Yin, F. and Liu, B. (2022) Fire Situation Detection Method for Unmanned Fire-Fighting Vessel Based on Coordinate Attention Structure-Based Deep Learning Network. Ocean Engineering, 266, Article ID: 113208. [Google Scholar] [CrossRef] 
[13] 褚文杰. 基于YOLOv5的坦克装甲车辆目标检测关键技术的研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2021.