A novel algorithm for remote photoplethysmography: spatial subspace rotation

Research output: Contribution to journalArticleAcademicpeer-review

280 Citations (Scopus)
11 Downloads (Pure)

Abstract

In this paper, we propose a conceptually novel algorithm, namely “Spatial Subspace Rotation” (2SR), that improves the robustness of remote photoplethysmography. Based on the assumption of (1) spatially redundant pixel-sensors of a camera and (2) a well-defined skin mask, our core idea is to estimate a spatial subspace of skin-pixels and measure its temporal rotation for pulse extraction, which does not require skin-tone or pulse-related priors in contrast to existing algorithms. The proposed algorithm is thoroughly assessed on a large benchmark dataset containing 54 videos, which includes challenges of various skin-tones, body-motions in complex illuminance conditions, and pulse-rate recovery after exercise. The experimental results show that given a well-defined skin mask, 2SR outperforms the popular ICA-based approach and two state-of-the-art algorithms (CHROM and PBV). When comparing the pulse frequency spectrum, 2SR improves on average the SNR of ICA by 2.22 dB, CHROM by 1.56 dB, and PBV by 1.95 dB. When comparing the instant pulse-rate, 2SR improves on average the Pearson correlation and precision of ICA by 47% and 65%, CHROM by 22% and 23%, PBV by 21% and 39%. ANOVA confirms the significant improvement of 2SR in peak-to-peak accuracy. The proposed 2SR algorithm is very simple to use and extend, i.e., the implementation only requires a few lines Matlab code.
Original languageEnglish
Pages (from-to)1974-1984
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Volume63
Issue number9
Early online date17 Dec 2015
DOIs
Publication statusPublished - Sept 2016

Fingerprint

Dive into the research topics of 'A novel algorithm for remote photoplethysmography: spatial subspace rotation'. Together they form a unique fingerprint.

Cite this