You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

Non-contact Physiological Parameters Extraction using Facial Video considering Illumination, Motion, Movement and Vibration

Publication Type:

Journal article

Venue:

IEEE Transactions on Biomedical Engineering


Abstract

Abstract—Objective:In this pape r,four phys iological parame te rs i.e . He art Rate (HR), Inte r-Beat-Interval (IBI), Heart Rate Variability (HRV) and Oxyge n Saturation(SpO2)are e xtracte d from facial vide o re cordings. Methods: Facialvide os we rere corde d for 10 minute s e ach in 30 te s t s ubje cts while driving a s imulator. Four Re gions of Inte re s t (ROIs) are automatically s e le cte d in e ach facial image frame bas e d on 66 facial landmarks.Re d-Gre e n-Blue (RGB)color s ignalsare e xtracte d from the ROIsand four phys iological parame te rs are e xtracte dfrom the color s ignals.For the e valuation, phys iological parame te rs are als o re corde d s imultane ous ly us ing a traditional sensor ‘cStress’ which is attached tohands and finge rs of te s t s ubje cts. Results:The Bland Altman plots s how 95% agre e me nt be twe e n the came ras ys te mand ‘cStress’with the highe s t corre lation coe fficie nt R = 0.96 for both HR andSpO2. The Quality Inde x (QI) is e s timate dfor IBIcons ide ring 100 ms R-pe ak e rror;the achie ve d accumulate dpe rce ntage achie ve dis97.5%. HRV fe ature s in both time and fre que ncy domains are compare d and the highe s t corre lation coefficie nt achie ve dis0.93. One-way analys is of variance (ANOVA1) te s t s hows that the re are no s tatis tically s ignificantdiffe re ncesbe twe e n the me as ure me nts bycame ra and re fe re nces e ns ors. Conclusion: The s e re sults pre sent high de grees of accuracy of HR , I B I , H R V and SpO2 e xtraction from facial image s e que nce s . Significance:The propos e d non-contact approach could broade n the dime ns ionality of phys iological parame te rs e xtraction us ing came ras. Thispropos e d me thod could be applie dfor drive rmonitoringapplication unde r re alis tic conditions i.e . illumination, motion, move me nt and vibration.

Bibtex

@article{Rahman5330,
author = {Hamidur Rahman and Mobyen Uddin Ahmed and Shahina Begum},
title = {Non-contact Physiological Parameters Extraction using Facial Video considering Illumination, Motion, Movement and Vibration},
month = {May},
year = {2019},
journal = {IEEE Transactions on Biomedical Engineering},
url = {http://www.es.mdh.se/publications/5330-}
}