The hue channel derived from sRGB video recordings provided better heart rate estimation accuracy using extremely low computation power and practically no latency compared to independent component analysis.
Do alternative color spaces derived from sRGB video recordings improve heart rate estimation accuracy and reduce processing latency compared to independent component analysis?
Using the hue channel from sRGB video recordings offers a fast, lightweight, and accurate method for noncontact heart rate measurement.
Existing video plethysmography methods use standard red-green-blue (sRGB) video recordings of the facial region to estimate heart pulse rate without making contact with the person being monitored. Methods achieving high estimation accuracy require considerable signal-processing power and result in significant processing latency. High processing power and latency are limiting factors when real-time pulse rate estimation is required or when the sensing platform has no access to high processing power. We investigate the use of alternative color spaces derived from sRGB video recordings as a fast light-weight alternative to pulse rate estimation. We consider seven color spaces and compare their performance with state-of-the-art algorithms that use independent component analysis. The comparison is performed over a dataset of 41 video recordings from subjects of varying skin tone and age. Results indicate that the hue channel provides better estimation accuracy using extremely low computation power and with practically no latency.
Tsouri et al. (Wed,) conducted a other in Heart rate measurement (n=41). Alternative color spaces (hue channel) vs. State-of-the-art algorithms using independent component analysis was evaluated on Estimation accuracy, computation power, and latency. The hue channel derived from sRGB video recordings provided better heart rate estimation accuracy using extremely low computation power and practically no latency compared to independent component analysis.