DistancePPG: Robust non-contact vital signs monitoring using a camera

Abstract

Vital signs such as pulse rate and breathing rate are currently measured using contact probes. But, non-contact methods for measuring vital signs are desirable both in hospital settings (e.g. in NICU) and for ubiquitous in-situ health tracking (e.g. on mobile phone and computers with webcams). Recently, camera-based non-contact vital sign monitoring have been shown to be feasible. However, camera-based vital sign monitoring is challenging for people with darker skin tone, under low lighting conditions, and/or during movement of an individual in front of the camera. In this paper, we propose distancePPG, a new camera-based vital sign estimation algorithm which addresses these challenges. DistancePPG proposes a new method of combining skin-color change signals from different tracked regions of the face using a weighted average, where the weights depend on the blood perfusion and incident light intensity in the region, to improve the signal-to-noise ratio (SNR) of camera-based estimate. One of our key contributions is a new automatic method for determining the weights based only on the video recording of the subject. The gains in SNR of camera-based PPG estimated using distancePPG translate into reduction of the error in vital sign estimation, and thus expand the scope of camera-based vital sign monitoring to potentially challenging scenarios. Further, a dataset will be released, comprising of synchronized video recordings of face and pulse oximeter based ground truth recordings from the earlobe for people with different skin tones, under different lighting conditions and for various motion scenarios.

Algorithmic Principles of Remote PPG

“…The videos are recorded with a regular RGB camera 7 in an uncompressed bitmap format 8 , 768 × 576 pixels, 8 bit depth, and 20 FPS. The ground-truth is either the contactbased PPG-signal sampled by a finger-based transmissive pulse oximetry 9 or the ECG-signal sampled by a polar chest belt 10 (in the fitness experiment). Both are synchronized with 7 Global shutter RGB CCD camera USB UI-2230SE-C from IDS.…”

Instant Stress: Detection of Perceived Mental Stress Through Smartphone Photoplethysmography and Thermal Imaging (Preprint)

“…Given the cardiac measurement ability of smartphone PPG thoroughly verified in earlier studies (e.g., [6,33]), we only tested the reliability of cardiac pulse signals measured by our approach by using a periodic signal goodness metric based signal quality index (SQI) [9,35]. The SQI is used by setting a frequency range of interest of physiological signals we are interested in [35].…”

“…Extending the existing work, we propose and test the use of entropy patterns rather than average values of all pixels from the R channel detector (among RGB), given that averaging tends to ignore fairly small, but important variations over the color distribution [9]. To estimate heart rate (heartbeat), the frequency analysis method generally performs well without preprocessing the raw BVP [6,7,35]. However, given that our interest is in measuring HRV parameters from raw R-R intervals (also called Normalto-Normal or inter-beat intervals), an additional technique is required.…”

“…The SQI is used by setting a frequency range of interest of physiological signals we are interested in [35]. Figure 5 shows the cardiac pulse rate SQI distributions of the measured signals.…”

Development of a Photoplethysmogram Based Heart Abnormality Detection Technique

“…From the PPG signal acquired, blood pressure estimation, blood oxygen level, pulse rate and breathing rate can be monitored easily [5]. To acquire a PPG signal, a probe which contains a photodiode emitting light with wavelength around 900nm and a photo-detector is used as shown in Figure 1.…”