3 December 2015 Non-contact cardiac pulse rate estimation based on web-camera
Author Affiliations +
Proceedings Volume 9794, Sixth International Conference on Electronics and Information Engineering; 979402 (2015) https://doi.org/10.1117/12.2203474
Event: Sixth International Conference on Electronics and Information Engineering, 2015, Dalian, China
Abstract
In this paper, we introduce a new methodology of non-contact cardiac pulse rate estimation based on the imaging Photoplethysmography (iPPG) and blind source separation. This novel’s approach can be applied to color video recordings of the human face and is based on automatic face tracking along with blind source separation of the color channels into RGB three-channel component. First of all, we should do some pre-processings of the data which can be got from color video such as normalization and sphering. We can use spectrum analysis to estimate the cardiac pulse rate by Independent Component Analysis (ICA) and JADE algorithm. With Bland-Altman and correlation analysis, we compared the cardiac pulse rate extracted from videos recorded by a basic webcam to a Commercial pulse oximetry sensors and achieved high accuracy and correlation. Root mean square error for the estimated results is 2.06bpm, which indicates that the algorithm can realize the non-contact measurements of cardiac pulse rate.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yingzhi Wang, Yingzhi Wang, Tailin Han, Tailin Han, } "Non-contact cardiac pulse rate estimation based on web-camera", Proc. SPIE 9794, Sixth International Conference on Electronics and Information Engineering, 979402 (3 December 2015); doi: 10.1117/12.2203474; https://doi.org/10.1117/12.2203474
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT


Back to Top