LiteFat: Lightweight Spatio-Temporal Graph Learning for Real-Time Driver Fatigue Detection

TL;DR

LiteFat is a lightweight, efficient spatio-temporal graph learning model that detects driver fatigue in real-time with high accuracy, suitable for resource-constrained embedded systems in vehicles.

Contribution

The paper introduces LiteFat, a novel low-resource spatio-temporal graph neural network for driver fatigue detection, optimized for embedded devices with minimal latency.

Findings

LiteFat achieves high accuracy comparable to state-of-the-art methods.

It significantly reduces computational complexity and latency.

Experimental results validate its suitability for real-time embedded applications.

Abstract

Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (such as intelligent vehicles/cars) where rapid detection is necessary to prevent accidents. This paper introduces LiteFat, a lightweight spatio-temporal graph learning model designed to detect driver fatigue efficiently while maintaining high accuracy and low computational demands. LiteFat involves converting streaming video data into spatio-temporal graphs (STG) using facial landmark detection, which focuses on key motion patterns and reduces unnecessary data processing. LiteFat uses MobileNet to extract facial features and create a feature matrix for the STG. A lightweight spatio-temporal graph neural network is then employed to identify signs of fatigue with minimal processing and low latency. Experimental results on benchmark datasets show that LiteFat performs competitively while significantly decreasing computational complexity and latency as compared to current state-of-the-art methods. This work enables the development of real-time, resource-efficient human fatigue detection systems that can be implemented upon embedded robotic devices.