Low-Latency Embedded Driver Monitoring System with a Multi-Task Neural Network

2026-05-04

AI Summary

This work addresses traffic accidents caused by driver distraction and fatigue by proposing a lightweight multitask neural network tailored for embedded platforms. The model simultaneously predicts attention, fatigue, and distraction states from facial regions within a single forward pass. By jointly optimizing multiple driving-state indicators, the approach achieves a favorable trade-off between accuracy and efficiency under stringent real-time and computational constraints. Integrated with facial region analysis and an efficient inference pipeline, the system enables low-latency, low-computation real-time monitoring of driver state, making it suitable for deployment on resource-constrained devices.

Abstract

Road traffic accidents remain a significant global concern, with the majority attributed to human factors such as driver distraction and fatigue. This study proposes a camera-based approach to derive useful indicators to assess driver attentiveness and alertness. The proposed pipeline jointly satisfies the stringent real-time requirements imposed by the critical application and minimizes the computational requirements to allow for deployment on a tight computational budget. To this end, we develop a lightweight multi-task neural network that predicts multiple indicators for the face region in a single forward pass. The developed model is integrated into a complete execution workflow to produce a real-time estimate of attentiveness, fatigue, and engagement in distracting activities.

Problem

• driver monitoring
• low-latency
• embedded system
• driver distraction
• driver fatigue

Innovation

• multi-task neural network
• low-latency
• driver monitoring system
• lightweight model
• real-time inference