Hybrid GNN-Based Driver Monitoring System using Facial Landmarks
International Scientific Journal of Engineering and Management · 07.04.2026 · 05 (04) · 1-9
DOI: 10.55041/isjem.acme038 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 07.04.2026. Verfasst von Poojitha M und 4 weiteren Autor:innen.
Abstract (Originalsprache)
-Driver fatigue and stress are major causes of road accidents and unsafe driving conditions. Traditional methods that rely on Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) often fail under real-world conditions such as lighting variations, head movements, and subtle facial changes. This paper presents a hybrid driver monitoring framework based on insights from existing studies for detecting both driver drowsiness and stress using facial landmarks. The system utilizes MediaPipe Face Mesh to extract 468 facial landmarks and computes classical features such as EAR and MAR for fatigue detection. In addition, a Graph Neural Network (GNN) is employed to model the relationships between facial landmarks and capture complex behavioral patterns. The outputs of classical and graph-based methods are fused to determine the driver’s state as SAFE, WARNING, or CRITICAL. The proposed hybrid approach aims to balance computational efficiency and intelligent feature learning, making it suitable for real time applications.
Zitieren
APA
M, P., M, S. R., K, S. R., A, B., & L, L. (2026). Hybrid GNN-Based Driver Monitoring System using Facial Landmarks. International Scientific Journal of Engineering and Management, 05(04), 1-9. https://doi.org/10.55041/isjem.acme038
Vancouver
M P, M SR, K SR, A B, L L. Hybrid GNN-Based Driver Monitoring System using Facial Landmarks. International Scientific Journal of Engineering and Management. 2026;05(04):1-9. doi:10.55041/isjem.acme038
BibTeX
@article{M2026,
author = {M, Poojitha and M, Shobha Rani and K, Saketh Ram and A, Bhagyara and L, Lavanya},
title = {Hybrid GNN-Based Driver Monitoring System using Facial Landmarks},
journal = {International Scientific Journal of Engineering and Management},
year = {2026},
volume = {05},
number = {04},
pages = {1--9},
doi = {10.55041/isjem.acme038}
}
EUVIMED