Heart Rate Estimation of Car Driver Using Radar Sensors and Blind Source Separation

Abstract

Monitoring a driver's health condition is essential for advanced driver assistance systems. To detect the driver's health condition, we propose a new system using a contactless biometric radar sensor to monitor the driver's heart rate. The radar sensor measures a microdisplacement of the driver's body surface, and heartbeat signals can be obtained. However, the observed signals are contaminated by noise signals such as body movement and car vibration. The proposed system utilizes blind source separation algorithms and extracts the driver's heartbeat signal from the noisy observation. Furthermore, the estimated heartbeat signal is input to a heart rate estimation algorithm. In experiments, we built a vibration measurement system to simulate a moving car, and an actual noisy heartbeat signal from a subject sitting on a driver's seat was measured. The results show that the proposed system can accurately estimate the subject's heart rate by removing the noise signals.