Color Spaces and Regions of Interest in Camera Based Heart Rate Estimation

Research output: Contribution to book/conference proceedings/anthology/report › Conference contribution › Contributed › peer-review

Contributors

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 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.

Details

Original languageEnglish
Title of host publication11th Conference of the European Study Group on Cardiovascular Oscillations (ESGCO)
PublisherWiley-IEEE Press
Pages1-2
Number of pages2
ISBN (print)978-1-7281-5752-8
Publication statusPublished - 15 Jul 2020
Peer-reviewedYes

Conference

Title2020 11th Conference of the European Study Group on Cardiovascular Oscillations (ESGCO)
Abbreviated titleESGCO
Duration15 July 2020
Website
Degree of recognitionInternational event
LocationPisa, Italy
CityPisa
CountryItaly

External IDs

Scopus 85091111213
ORCID /0000-0001-6754-5257/work/142232811
ORCID /0000-0003-4012-0608/work/142235692

Keywords

Sustainable Development Goals

ASJC Scopus subject areas

Keywords

  • Image color analysis, Heart rate, Estimation, Level set, Skin, Forehead, Color