A novel algorithm based on hanning-windowed tri-section independent component analysis for remote heart rate detection
Conference: BIBE 2018 - International Conference on Biological Information and Biomedical Engineering
06/06/2018 - 06/08/2018 at Shanghai, China
Proceedings: BIBE 2018
Pages: 5Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Chen, Haitao; Wei, Qinyuan; Wei, Lai; Duan, Xiaohui (School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China & Engineering Research Center for Mobile Digital Hospital System, Ministry of Education, Beijing 100871, China)
Abstract:
Non-contact heart rate detection can simplify physiological parameters measurement without the invasion of electrodes. In this paper, we provide a novel algorithm based on Hanning Window and Independent Component Analysis (ICA), analysing the frequency spectrum of triple regions of interest (ROI) of human face images obtained from a digital webcam. We use Bland-Altman and correlation analysis to compare the results of our algorithm and reference electro-cardiogram signals obtained from a calibration system. It demonstrates that our algorithm performs well and gets a correlation coefficient of 0.974.