EUVIMEDEUVIMED entdecken
Crossref

Multi-Feature fatigue detection method for bus drivers based on YOLOv8n-SimAM with integrated temporal information

Keqi Wu, Shuo Xu, Xin Zhang, Hui Xiao, Xiaoliang Zhang, Pengfei Lin, Xiaodong Wang

Journal of Highway and Transportation Research and Development (English Edition) · 2026-07

DOI: 10.26599/htrd.2026.9480101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Highway and Transportation Research and Development (English Edition), 2026-07. Verfasst von Keqi Wu und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fatigue driving represents a major cause of road traffic accidents, with particularly severe consequences in passenger transport. Developing accurate fatigue detection methods resilient to in-vehicle environmental interference is crucial for enhancing road safety. This study proposes a multi-feature fatigue detection framework integrating temporal information based on YOLOv8n-SimAM for bus drivers. The SimAM attention mechanism enhances feature extraction from ocular and oral regions while suppressing cabin background interference. By incorporating the driver’s eye and mouth states with temporal information, we established a multi-feature fatigue reasoning mechanism. Comparative experiments demonstrate that YOLOv8n-SimAM achieves superior performance in precision, recall, and PmA50-95 (mean average precision across IoU thresholds 0.5–0.95) over alternative models. Our approach achieves enhancements of 2.8% in precision, 5.4% in recall, and 7.5% in F1-score (harmonic mean of precision and recall) over the suboptimal benchmark, without a substantial increase in model parameters. Ablation studies confirm that integrating SimAM reduces false positive rate by 48%, while the temporal fatigue inference module decreases missed detection rate by 72%. The integrated model attains an F1-score of 0.906, an accuracy of 0.9, with corresponding missed detection and false positive rates of 0.111 and 0.087, respectively. This methodology enables reliable facial feature capture and fatigue assessment in challenging in-cabin environments, providing an effective solution for off-site monitoring of bus driver fatigue.

Zitieren

APA

Wu, K., Xu, S., Zhang, X., Xiao, H., Zhang, X., Lin, P., & Wang, X. (2026). Multi-Feature fatigue detection method for bus drivers based on YOLOv8n-SimAM with integrated temporal information. Journal of Highway and Transportation Research and Development (English Edition). https://doi.org/10.26599/htrd.2026.9480101

Vancouver

Wu K, Xu S, Zhang X, Xiao H, Zhang X, Lin P, et al. Multi-Feature fatigue detection method for bus drivers based on YOLOv8n-SimAM with integrated temporal information. Journal of Highway and Transportation Research and Development (English Edition). 2026. doi:10.26599/htrd.2026.9480101

BibTeX
@article{Wu2026,
  author = {Wu, Keqi and Xu, Shuo and Zhang, Xin and Xiao, Hui and Zhang, Xiaoliang and Lin, Pengfei and Wang, Xiaodong},
  title = {Multi-Feature fatigue detection method for bus drivers based on YOLOv8n-SimAM with integrated temporal information},
  journal = {Journal of Highway and Transportation Research and Development (English Edition)},
  year = {2026},
  doi = {10.26599/htrd.2026.9480101}
}
Kostenlos starten →