EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Drowsiness Detection Using YOLOv11 in Driver Monitoring Systems

Santhosh Kumar Kadur Lokeshappa, Pravinth Raja Suthakar

Journal of Computational and Cognitive Engineering · 05.03.2026 · 5 (3) · 533-543

DOI: 10.47852/bonviewjcce62027625 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational and Cognitive Engineering, online erschienen am 05.03.2026. Verfasst von Santhosh Kumar Kadur Lokeshappa und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

One of the main causes of traffic accidents that frequently result in fatalities, serious injuries, and large property losses is driver fatigue. Therefore, enhancing driver safety and preventing such incidents depend heavily on the early, nonintrusive detection of fatigue. A real-time driver monitoring system based on the most recent YOLOv11 framework is presented in this paper. By examining visual indicators like prolonged eye closure and abnormal head movements, the system can identify early indicators of drowsiness. We acquired a purpose-designed dataset that covered a range of driving behaviors and environmental changes in order to improve the framework's flexibility and dependability. The effectiveness of the proposed model was extensively compared with several existing detection methods, and the results indicated that YOLOv11 achieved better accuracy in terms of various evaluation metrics. This improvement is due to its better feature extraction pipeline, attention modules, and computationally efficient architecture, which make it very appealing for real-time applications even inside the vehicle. Overall, the system provides a practical and reliable early warning system for drivers and could greatly reduce the risks associated with fatigue to improve safety in transportation. However, extreme lighting variations and face occlusions may impact the model's performance. To improve robustness, future research will concentrate on expanding the dataset andincorporating multimodal inputs. Received: 9 September 2025 | Revised: 4 December 2025 | Accepted: 6 February 2026 Conflicts of InterestThe authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Roboflow website at https://universe.roboflow.com/santhosh-kumar-k-l/drowsiness-detection-koqqc. Author Contribution Statement Santhosh Kumar Kadur Lokeshappa: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft. Pravinth Raja Suthakar: Resources, Writing – review & editing, Visualization, Supervision.

Zitieren

APA

Lokeshappa, S. K. K., & Suthakar, P. R. (2026). Real-Time Drowsiness Detection Using YOLOv11 in Driver Monitoring Systems. Journal of Computational and Cognitive Engineering, 5(3), 533-543. https://doi.org/10.47852/bonviewjcce62027625

Vancouver

Lokeshappa SKK, Suthakar PR. Real-Time Drowsiness Detection Using YOLOv11 in Driver Monitoring Systems. Journal of Computational and Cognitive Engineering. 2026;5(3):533-543. doi:10.47852/bonviewjcce62027625

BibTeX
@article{Lokeshappa2026,
  author = {Lokeshappa, Santhosh Kumar Kadur and Suthakar, Pravinth Raja},
  title = {Real-Time Drowsiness Detection Using YOLOv11 in Driver Monitoring Systems},
  journal = {Journal of Computational and Cognitive Engineering},
  year = {2026},
  volume = {5},
  number = {3},
  pages = {533--543},
  doi = {10.47852/bonviewjcce62027625}
}
Kostenlos starten →