Blinking Beyond EAR: A Stable Eyelid Angle Metric for Driver Drowsiness Detection and Data Augmentation

TL;DR

This paper introduces the Eyelid Angle (ELA), a new geometric metric for eye openness that improves driver drowsiness detection robustness and enables synthetic data generation for training models.

Contribution

The paper presents the ELA metric, which is more stable than traditional measures, and demonstrates its effectiveness in blink detection and data augmentation for driver monitoring.

Findings

ELA outperforms EAR under viewpoint variations.

ELA enables accurate blink detection correlated with drowsiness.

Synthetic datasets generated using ELA improve drowsiness recognition models.

Abstract

Detecting driver drowsiness reliably is crucial for enhancing road safety and supporting advanced driver assistance systems (ADAS). We introduce the Eyelid Angle (ELA), a novel, reproducible metric of eye openness derived from 3D facial landmarks. Unlike conventional binary eye state estimators or 2D measures, such as the Eye Aspect Ratio (EAR), the ELA provides a stable geometric description of eyelid motion that is robust to variations in camera angle. Using the ELA, we design a blink detection framework that extracts temporal characteristics, including the closing, closed, and reopening durations, which are shown to correlate with drowsiness levels. To address the scarcity and risk of collecting natural drowsiness data, we further leverage ELA signals to animate rigged avatars in Blender 3D, enabling the creation of realistic synthetic datasets with controllable noise, camera viewpoints, and blink dynamics. Experimental results in public driver monitoring datasets demonstrate that the ELA offers lower variance under viewpoint changes compared to EAR and achieves accurate blink detection. At the same time, synthetic augmentation expands the diversity of training data for drowsiness recognition. Our findings highlight the ELA as both a reliable biometric measure and a powerful tool for generating scalable datasets in driver state monitoring.