Non-contact driver cardiac physiological monitoring using video data

Driver physiological monitoring in vehicle is of great importance to provide a comfortable driving environment and prevent road accidents. In recent years, the development of non-contact techniques for such monitoring has been drawing research interests. In this paper, we present a non-contact video-based driver physiological monitoring framework to robustly acquire driver´s heart rate and heart rate variability analysis using a simple consumer-level webcam. More specifically, a real-time facial feature detector as well as a joint blind source separation method is used to capture the driver´s facial blood volume pulse signal. Experimental results from both laboratory and actual road driving conditions demonstrate that the proposed non-contact framework is promising HR and HRV monitoring, even with the existence of unstable light source variation.