Driver Glance Classification In-the-wild: Towards Generalization Across Domains and Subjects

TL;DR

This paper introduces a robust driver glance classification model using an hourglass network with reconstruction loss, personalized tuning, and multi-domain training to improve generalization across subjects and environments.

Contribution

It proposes a novel hourglass-based model with reconstruction loss, personalized adaptation, and weakly supervised multi-domain training for driver glance classification.

Findings

The hourglass network outperforms traditional models in feature learning.

Personalization improves individual driver classification accuracy.

Multi-domain training reduces annotation costs and enhances robustness.

Abstract

Distracted drivers are dangerous drivers. Equipping advanced driver assistance systems (ADAS) with the ability to detect driver distraction can help prevent accidents and improve driver safety. In order to detect driver distraction, an ADAS must be able to monitor their visual attention. We propose a model that takes as input a patch of the driver's face along with a crop of the eye-region and classifies their glance into 6 coarse regions-of-interest (ROIs) in the vehicle. We demonstrate that an hourglass network, trained with an additional reconstruction loss, allows the model to learn stronger contextual feature representations than a traditional encoder-only classification module. To make the system robust to subject-specific variations in appearance and behavior, we design a personalized hourglass model tuned with an auxiliary input representing the driver's baseline glance behavior. Finally, we present a weakly supervised multi-domain training regimen that enables the hourglass to jointly learn representations from different domains (varying in camera type, angle), utilizing unlabeled samples and thereby reducing annotation cost.