Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 9, Issue 3, 2025

Application of YOLO-Based Face Recognition in Fatigue Driving Detection

Download as PDF

DOI: 10.23977/acss.2025.090307 | Downloads: 3 | Views: 221

Author(s)

Jianlei Li 1, Runyi Hu 1

Affiliation(s)

1 School of Mathematics and Statistics, North China University of Water Resources and Electric Power, Zhengzhou, Henan, China

Corresponding Author

Jianlei Li

ABSTRACT

Fatigue driving is a major contributing factor to traffic accidents. Accurately and real-time identification of driver fatigue has become a research priority in the field of intelligent driving safety. This paper proposes a face recognition method that integrates YOLOv8 and FaceMesh to achieve high-precision fatigue driving detection. This method first uses the YOLOv8 model to rapidly locate the driver's face. Furthermore, the FaceMesh model is introduced to extract facial key points. Fatigue behavior features such as the eye aspect ratio (EAR) and mouth opening/closing ratio (MAR) are calculated, and state discrimination is performed using time-series statistical logic. Experimental results show that this method achieves 93.4% accuracy, 91.6% recall, and 92.5% F1-score on a public dataset, outperforming the traditional YOLOv5 and keypoint method combination. It also maintains robustness in complex scenarios such as nighttime and occlusion. These results demonstrate the effectiveness and practicality of this method in fatigue driving detection, providing a viable technical path for intelligent vehicle monitoring systems.

KEYWORDS

Fatigue Driving Detection; YOLOv8; FaceMesh; Face Recognition; Eye Aspect Ratio (EAR); Mouth Aspect Ratio (MAR); Deep Learning

CITE THIS PAPER

Jianlei Li, Runyi Hu, Application of YOLO-Based Face Recognition in Fatigue Driving Detection. Advances in Computer, Signals and Systems (2025) Vol. 9: 54-61. DOI: http://dx.doi.org/10.23977/acss.2025.090307.

REFERENCES

[1] C. Li, Y. Zhu, and M. Zheng, "A multi-objective dynamic detection model in autonomous driving based on an improved YOLOv8," Alexandria Engineering Journal, vol. 122, pp. 453–464, May 2025, doi: 10.1016/j.aej.2025.03.020.
[2] A. Rahim, F. Yuan, and J. Barabady, "An ultralytics YOLOv8-based approach for road detection in snowy environments in the arctic region of Norway," Comput. Mater. Continua, vol. 83, no. 3, pp. 4411–4428, May 2025, doi: 10.32604/cmc.2025.061575.
[3] C. Zhang, X. Chen, P. Liu, B. He, W. Li, and T. Song, "Automated detection and segmentation of tunnel defects and objects using YOLOv8-CM," Tunnelling Underground Space Technol., vol. 150, p. 105857, Aug. 2024, doi: 10.1016/j.tust.2024.105857.
[4] M. Venkateswarlu and V. R. R. Chirra, "CNN-ViT: a multi-feature learning based approach for driver drowsiness detection,” Array, vol. 27, p. 100425, Sep. 2025, doi: 10.1016/j.array.2025.100425.
[5] A. Rahman, M. B. H. Hriday, and R. Khan, "Computer vision-based approach to detect fatigue driving and face mask for edge computing device," Heliyon, vol. 8, no. 10, p. e11204, Oct. 2022, doi: 10.1016/j.heliyon.2022.e11204.
[6] A. Kuwahara, K. Nishikawa, R. Hirakawa, H. Kawano, and Y. Nakatoh, "Eye fatigue estimation using blink detection based on eye aspect ratio mapping(EARM),” Cognit. Rob., vol. 2, pp. 50–59, Jan. 2022, doi: 10.1016/j.cogr.2022.01.003.
[7] J. Shi and K. Wang, “Fatigue driving detection method based on time-space-frequency features of multimodal signals," Biomed. Signal Process. Control, vol. 84, p. 104744, Jul. 2023, doi: 10.1016/j.bspc.2023.104744.
[8] K. Kakhi, S. K. Jagatheesaperumal, A. Khosravi, R. Alizadehsani, and U. R. Acharya, "Fatigue monitoring using wearables and AI: trends, challenges, and future opportunities," Comput. Biol. Med., vol. 195, p. 110461, Sep. 2025, doi: 10.1016/j.compbiomed.2025.110461.
[9] Z. Cheng, "Object detection in autonomous driving scenario using YOLOv8-SimAM: a robust test in different datasets," Transportmetrica A: Transport Sci., Jun. 2025, doi: 10.1080/23249935.2025.2511818.
[10] D. Nimma, "Object detection in real-time video surveillance using attention based transformer-YOLOv8 model," Alexandria Eng. J., vol. 118, pp. 482–495, Apr. 2025, doi: 10.1016/j.aej.2025.01.032.
[11] H. Jia, Z. Xiao, and P. Ji, "Real-time fatigue driving detection system based on multi-module fusion," Comput. Graphics, vol. 108, pp. 22–33, Nov. 2022, doi: 10.1016/j.cag.2022.09.001.
[12] X. Fang, X. Yang, X. Xing, J. Wang, W. Umer, and W. Guo, "Real-time monitoring of mental fatigue of construction workers using enhanced sequential learning and timeliness," Autom. Constr., vol. 159, p. 105267, Mar. 2024, doi: 10.1016/j.autcon.2024.105267.
[13] D. Yang, B. Gao, S. Wang, and H. Xiang, "Robustness test for fouling state identification of homogeneous pressure electrodes based on confidence ellipsoids," IEICE Electron. Express, p. 22.20240283, 2025, doi: 10.1587/elex.22.20240283.
[14] X. Wang, M. Wu, C. Xu, X. Yang, and B. Cai, "State space model detection of driving fatigue considering individual differences and time cumulative effect," Int. J. Transp. Sci. Technol., vol. 13, pp. 200–212, Mar. 2024, doi: 10.1016/j.ijtst.2023.12.004.
[15] Y. Zhao, H. Zhao, and J. Shi, "YOLOv8-MAH: multi-attribute recognition model for vehicles," Pattern Recognit., vol. 167, p. 111849, Nov. 2025, doi: 10.1016/j.patcog.2025.111849.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 38553
Visits: 697772

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.