Real-time Driver Monitoring Systems on Edge AI Device

TL;DR

This paper presents a real-time driver monitoring system that operates on an edge AI device, utilizing hardware acceleration and model optimization to achieve high frame rates for improved road safety.

Contribution

The paper introduces a hardware-accelerator-based edge AI system for driver monitoring, including model surgery techniques to optimize deep learning models for real-time performance.

Findings

Achieves 63 FPS on TI-TDA4VM edge device

Uses InfraRed camera for driver footage recording

Demonstrates effective model optimization for edge deployment

Abstract

As road accident cases are increasing due to the inattention of the driver, automated driver monitoring systems (DMS) have gained an increase in acceptance. In this report, we present a real-time DMS system that runs on a hardware-accelerator-based edge device. The system consists of an InfraRed camera to record the driver footage and an edge device to process the data. To successfully port the deep learning models to run on the edge device taking full advantage of the hardware accelerators, model surgery was performed. The final DMS system achieves 63 frames per second (FPS) on the TI-TDA4VM edge device.