# A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection

## TL;DR

This paper introduces a large real-world dataset for early drowsiness detection, benchmarks a low-resource hierarchical LSTM model using blink features, and demonstrates its superior accuracy over human judgment.

## Contribution

It provides a new extensive dataset for early drowsiness detection and proposes a novel low-resource temporal model based on HM-LSTM for this task.

## Key findings

- The dataset contains 30 hours of labeled video from 60 subjects.
- The proposed HM-LSTM model outperforms human judgment in accuracy.
- Blink features are effective indicators for early drowsiness detection.

## Abstract

Drowsiness can put lives of many drivers and workers in danger. It is important to design practical and easy-to-deploy real-world systems to detect the onset of drowsiness.In this paper, we address early drowsiness detection, which can provide early alerts and offer subjects ample time to react. We present a large and public real-life dataset of 60 subjects, with video segments labeled as alert, low vigilant, or drowsy. This dataset consists of around 30 hours of video, with contents ranging from subtle signs of drowsiness to more obvious ones. We also benchmark a temporal model for our dataset, which has low computational and storage demands. The core of our proposed method is a Hierarchical Multiscale Long Short-Term Memory (HM-LSTM) network, that is fed by detected blink features in sequence. Our experiments demonstrate the relationship between the sequential blink features and drowsiness. In the experimental results, our baseline method produces higher accuracy than human judgment.