Abstract

Camera-based heart rate (HR) estimation is used with different color spaces and regions of interest (ROIs). In this work, seven commonly used ROIs were determined via facial landmarks focusing on forehead, cheeks and glabella, and one ROI was derived by level set segmentation. For each ROI, 25 signals of eight color spaces were derived and HR estimation accuracy was determined. Both color channel and ROI showed significant effects $(p on the accuracy of HR estimation. Glabella or forehead ROI combined with HSV-H or NTSC-Q color channel (accuracy: up to 73.3 %) as well as level set ROI with NTSC-Q color channel (accuracy: 68.7%) performed best.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.