A novel algorithm based on hanning-windowed tri-section independent component analysis for remote heart rate detection

Konferenz: BIBE 2018 - International Conference on Biological Information and Biomedical Engineering
06.06.2018 - 08.06.2018 in Shanghai, China

Tagungsband: BIBE 2018

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

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)

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.