A lock-in technique for extraction of pulse rates and associated confidence levels from video

We investigate the practical applicability of video photoplethysmography (VPPG) to extract heart rates of subjects using non-contact color video recordings of human faces collected under typical indoor laboratory conditions using commercial video cameras. Videos were processed following three previously described simple VPPG algorithms to produce a time-varying plethysmographic signal. These time-signals were then analyzed using a novel, lock-in algorithm that was developed to extract the pulsatile frequency component. A protocol to associate confidence estimates for the extracted heart rates for each video stream is presented. Results indicate that the difference between heart-rates extracted using the lock-in technique and gold-standard measurements, for videos with high-confidence metrics, were less than 4 beats per minute. Constraints on video acquisition and processing including natural subject motion and the total duration of video recorded required for evaluating these confidence metrics are discussed.