Internship Report: Benchmark of Deep Learning-based Imaging PPG in Automotive Domain

TL;DR

This paper benchmarks a deep learning-based imaging photoplethysmography method using near-infrared cameras for heart rate monitoring in automotive settings, highlighting its potential and current limitations.

Contribution

It provides the first comprehensive benchmark of NIR-based deep learning iPPG methods in automotive scenarios using the MR-NIRP Car dataset.

Findings

Average MAE of 7.5 bpm with still heads

Average MAE of 16.6 bpm with small motion

Method shows promise but needs improvement for real-world use

Abstract

Imaging photoplethysmography (iPPG) can be used for heart rate monitoring during driving, which is expected to reduce traffic accidents by continuously assessing drivers' physical condition. Deep learning-based iPPG methods using near-infrared (NIR) cameras have recently gained attention as a promising approach. To help understand the challenges in applying iPPG in automotive, we provide a benchmark of a NIR-based method using a deep learning model by evaluating its performance on MR-NIRP Car dataset. Experiment results show that the average mean absolute error (MAE) is 7.5 bpm and 16.6 bpm under drivers' heads keeping still or having small motion, respectively. These findings suggest that while the method shows promise, further improvements are needed to make it reliable for real-world driving conditions.