Blinking Beyond EAR: A Stable Eyelid Angle Metric for Driver Drowsiness Detection and Data Augmentation
This work addresses the need for reliable driver drowsiness detection to enhance road safety, though it is incremental by improving upon existing metrics like EAR.
The paper tackled the problem of detecting driver drowsiness by introducing the Eyelid Angle (ELA), a stable geometric metric for eye openness, which achieved lower variance under viewpoint changes compared to the Eye Aspect Ratio (EAR) and enabled accurate blink detection. It also used ELA to generate realistic synthetic datasets for data augmentation, expanding training diversity for drowsiness recognition.
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.