Lightweight and Real-Time Driver Fatigue Detection Based on MG-YOLOv8 with Facial Multi-Feature Fusion
Journal of Imaging · 01.11.2025 · 11 (11) · 385
DOI: 10.3390/jimaging11110385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 01.11.2025. Verfasst von Chengming Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Driver fatigue is a primary factor in traffic accidents and poses a serious threat to road safety. To address this issue, this paper proposes a multi-feature fusion fatigue detection method based on an improved YOLOv8 model. First, the method uses an enhanced YOLOv8 model to achieve high-precision face detection. Then, it crops the detected face regions. Next, the lightweight PFLD (Practical Facial Landmark Detector) model performs keypoint detection on the cropped images, extracting 68 facial feature points and calculating key indicators related to fatigue status. These indicators include the eye aspect ratio (EAR), eyelid closure percentage (PERCLOS), mouth aspect ratio (MAR), and head posture ratio (HPR). To mitigate the impact of individual differences on detection accuracy, the paper introduces a novel sliding window model that combines a dynamic threshold adjustment strategy with an exponential weighted moving average (EWMA) algorithm. Based on this framework, blink frequency (BF), yawn frequency (YF), and nod frequency (NF) are calculated to extract time-series behavioral features related to fatigue. Finally, the driver’s fatigue state is determined using a comprehensive fatigue assessment algorithm. Experimental results on the WIDER FACE and YAWDD datasets demonstrate this method’s significant advantages in improving detection accuracy and computational efficiency. By striking a better balance between real-time performance and accuracy, the proposed method shows promise for real-world driving applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China.
- Department of Illuminating Engineering & Light Sources, School of Information Science and Technology, Fudan University, Shanghai 201203, China.
ORCID-Profile: Xinyue Liu, Yandan Lin
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, C., Liu, X., Zhou, M., Li, Z., Du, Z., & Lin, Y. (2025). Lightweight and Real-Time Driver Fatigue Detection Based on MG-YOLOv8 with Facial Multi-Feature Fusion. Journal of Imaging, 11(11), 385. https://doi.org/10.3390/jimaging11110385
Vancouver
Chen C, Liu X, Zhou M, Li Z, Du Z, Lin Y. Lightweight and Real-Time Driver Fatigue Detection Based on MG-YOLOv8 with Facial Multi-Feature Fusion. Journal of Imaging. 2025;11(11):385. doi:10.3390/jimaging11110385
BibTeX
@article{Chen2025,
author = {Chen, Chengming and Liu, Xinyue and Zhou, Meng and Li, Zhijian and Du, Zhanqi and Lin, Yandan},
title = {Lightweight and Real-Time Driver Fatigue Detection Based on MG-YOLOv8 with Facial Multi-Feature Fusion},
journal = {Journal of Imaging},
year = {2025},
volume = {11},
number = {11},
pages = {385},
doi = {10.3390/jimaging11110385}
}
EUVIMED