Optical heartrate tracking
Heartrate tracking is performed entirely optically without the subject being required to wear any monitoring equipment by processing a combination of signals representing frames of video of the sinusoidal motion of a subject's facial skin color changes captured by both IR and visible light (e.g., RGB—red/green/blue) cameras. The IR and RGB graphs that result from the processing are perfectly phase-shifted so that when the IR signal is going down in amplitude, the RGB signal is going up. Such phase-shifting enables the optical heartrate tracking to utilize diverse input feeds so that a tracked signal is accepted as the user's true heartrate when both IR and RGB signals are well correlated.
1. One or more hardware-based computer-readable memory devices not consisting of propagated signals having computer readable instructions stored thereupon that, when executed by a computer, implement:
a face alignment and preparation pipeline configured to receive respective streams of infrared video frames and visible light video frames which include a facial image of a human subject and simultaneously process the received infrared video frames and visible light video frames to output a decomposed, frame-aligned, facial skin-only signal measurement comprising spatially-corresponding infrared light and visible light graphs that are phase-shifted so that as values in the infrared light graph are increasing, values in the spatially-corresponding visible light graph are decreasing, and vice-versa;
a signal-finding pipeline configured to: i) receive the decomposed, frame-aligned, facial skin-only signal measurement, ii) compare the signal measurement in a current frame to a cached decomposed version of a head image in a previous frame, iii) sum up and average pixels having deltas between head images in the current frame and previous frame that trend in a consistent direction, and are within a set number of standard deviations of brightness, iv) generate a measurement of noisiness per pixel, v) apply at least one filter to the summed and averaged pixels, the filter being weighted by the noisiness measurement, vi) create a time-space representation of low-amplitude deltas in a skin-only facial image;
a signal-extracting pipeline configured to a) apply time-space smoothing or frequency-space smoothing to the time-space representation, b) apply a discrete Fourier transform to transform the time-space representation into a frequency-space representation for each of the infrared and visible streams, c) merge the frequency-space representations weighted by graph noise level; and
a heartrate identification pipeline configured to identify a heartrate of the human subject from the merged frequency-space representations.
2. The one or more hardware-based computer-readable memory devices of claim 1 in which the heartrate identification pipeline is configured to identify a highest peak in the merged frequency-space graphs.
3. The one or more hardware-based computer-readable memory devices of claim 2 in which the pipelines operate sequentially on a given video frame.
4. The one or more hardware-based computer-readable memory devices of claim 2 in which the pipelines operate in parallel.
5. The one or more hardware-based computer-readable memory devices of claim 2 further comprising configuring the heartrate identification pipeline to measure a noise level of the highest peak.
6. The one or more hardware-based computer-readable memory devices of claim 5 further comprising configuring the heartrate identification pipeline to bucket a location of the highest peak, weighted by the noise level into a frequency detector.
7. The one or more hardware-based computer-readable memory devices of claim 1 further comprising configuring the heartrate identification pipeline to apply a smoothing factor to nearby signals and sum the signals together.
8. The one or more hardware-based computer-readable memory devices of claim 7 further comprising configuring the heartrate identification pipeline to output a graph of the summed, smoothed signals.
9. The one or more hardware-based computer-readable memory devices of claim 8 further comprising configuring the heartrate identification pipeline to identify a heartrate signal from the graph if a peak result is above a set amplitude threshold.