2019/05/16 by Javier Hernandez‐Ortega, Shigenori Nagae, Hernandez-Ortega, Javier +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Engineering · Psychology · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Non-Invasive Vital Sign Monitoring #Signal Processing (eess.SP) #Sleep and Work-Related Fatigue #Spectroscopy Techniques in Biomedical and Chemical Research #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1905.06568
openalex publication_date 2019/05/16 · openalex created_date 2022/07/23 · openalex updated_date 2026/07/28
In this paper we develop a robust for heart rate (HR) estimation method using\nface video for challenging scenarios with high variability sources such as head\nmovement, illumination changes, vibration, blur, etc. Our method employs a\nquality measure Q to extract a remote Plethysmography (rPPG) signal as clean as\npossible from a specific face video segment. Our main motivation is developing\nrobust technology for driver monitoring. Therefore, for our experiments we use\na self-collected dataset consisting of Near Infrared (NIR) videos acquired with\na camera mounted in the dashboard of a real moving car. We compare the\nperformance of a classic rPPG algorithm, and the performance of the same\nmethod, but using Q for selecting which video segments present a lower amount\nof variability. Our results show that using the video segments with the highest\nquality in a realistic driving setup improves the HR estimation with a relative\naccuracy improvement larger than 20%.\n