In-the-wild Drowsiness Detection from Facial Expressions

TL;DR

This paper presents a new approach for detecting driver drowsiness in real-world conditions using facial expression analysis, involving a novel data collection protocol and neural network models, achieving improved accuracy over baseline methods.

Contribution

Introduces a practical data collection protocol and a multi-level drowsiness annotation guideline, along with neural network models for real-time drowsiness detection in natural driving scenarios.

Findings

Best model achieves ROC-AUC of 0.78

Data collection protocol enables realistic drowsiness data

Model outperforms baseline with ROC-AUC of 0.72

Abstract

Driving in a state of drowsiness is a major cause of road accidents, resulting in tremendous damage to life and property. Developing robust, automatic, real-time systems that can infer drowsiness states of drivers has the potential of making life-saving impact. However, developing drowsiness detection systems that work well in real-world scenarios is challenging because of the difficulties associated with collecting high-volume realistic drowsy data and modeling the complex temporal dynamics of evolving drowsy states. In this paper, we propose a data collection protocol that involves outfitting vehicles of overnight shift workers with camera kits that record their faces while driving. We develop a drowsiness annotation guideline to enable humans to label the collected videos into 4 levels of drowsiness: `alert', `slightly drowsy', `moderately drowsy' and `extremely drowsy'. We experiment with different convolutional and temporal neural network architectures to predict drowsiness states from pose, expression and emotion-based representation of the input video of the driver's face. Our best performing model achieves a macro ROC-AUC of 0.78, compared to 0.72 for a baseline model.