Key result
Real-time unsupervised rPPG pipeline achieves state-of-the-art accuracy estimating heart rate and HRV against contact sensors.
Why the study?
Measuring heart rate variability from remote photo-plethysmography requires temporally locating heart beats with high precision, which existing methods struggle to achieve in real time.
Answers are grounded in this paper and cite their sources.
An unsupervised real-time webcam rPPG pipeline can accurately estimate heart rate and heart rate variability, which is further validated by a newly released dataset of clean ground truth annotations.
Remote photo-plethysmography (rPPG) uses a camera to estimate a person’s heart rate (HR). Similar to how heart rate can provide useful information about a person’s vital signs, insights about the underlying physio/psychological conditions can be obtained from heart rate variability (HRV). HRV is a measure of the fine fluctuations in the intervals between heart beats. However, this measure requires temporally locating heart beats with a high degree of precision. We introduce a refined and efficient real-time rPPG pipeline with novel filtering and motion suppression that not only estimates heart rates, but also extracts the pulse waveform to time heart beats and measure heart rate variability. This unsupervised method requires no rPPG specific training and is able to operate in real-time. We also introduce a new multi-modal video dataset, VicarPPG 2, specifically designed to evaluate rPPG algorithms on HR and HRV estimation. We validate and study our method under various conditions on a comprehensive range of public and self-recorded datasets, showing state-of-the-art results and providing useful insights into some unique aspects. Lastly, we make available CleanerPPG, a collection of human-verified ground truth peak/heart-beat annotations for existing rPPG datasets. These verified annotations should make future evaluations and benchmarking of rPPG algorithms more accurate, standardized and fair.
No takes yet. Share an insight, caveat, or question.
Gudi et al. (2020) studied Healthy volunteers (n=54). Unsupervised real-time remote photo-plethysmography (rPPG) vs. Contact-based PPG/ECG (ground truth) was evaluated on Heart rate (HR) and heart rate variability (HRV) estimation accuracy. The unsupervised real-time rPPG pipeline successfully estimated heart rate and heart rate variability with state-of-the-art results compared to contact-sensor ground truth.
Synapse has enriched 10 related papers. Consider them for comparative context: