Wednesday 19 March 2025
A team of researchers has made a significant breakthrough in remote photoplethysmography (rPPG), a method used to measure heart rate and other vital signs using cameras. The new approach is more robust and accurate than previous methods, and can even work in conditions where the subject is moving or wearing makeup.
The traditional method of rPPG relies on analyzing changes in skin color caused by blood flow. However, this approach is sensitive to external factors such as lighting conditions, facial expressions, and even the type of clothing worn. The new technique, developed by a team of scientists from Joint Stock Research and Production Company Kryptonite, uses a combination of face feature detection, spectrogram calculation, and iterative curve fitting to accurately determine heart rate.
One of the key innovations is the use of the CIELAB color space, which separates luminosity into a separate channel. This allows researchers to operate directly with the hue of the skin, reducing the impact of movement artifacts. The team also developed an algorithm that can track the subject’s face and select specific areas of interest, such as the cheeks or forehead, where the heart rate signal is strongest.
The system was tested on 26 video recordings from 19 volunteers, ranging in age from 20 to 50. The results showed an average mean absolute error (MAE) of just 1.95 beats per minute, compared to previous methods which can have MAEs as high as 5.50 or 7.98 BPM.
The implications of this technology are significant. It could potentially be used in a wide range of applications, from medical research to consumer health monitoring. For example, it could enable the development of wearable cameras that track heart rate and other vital signs, providing real-time feedback on physical activity and overall well-being.
One potential limitation of the system is its reliance on high-quality video footage. The team used a 720p webcam for their tests, but higher-resolution cameras would likely be required for more accurate readings. However, this could also be seen as an opportunity to develop new camera technologies that are specifically designed for rPPG applications.
The researchers have also highlighted the potential for future improvements, such as real-time processing and higher frame rates. These advancements could enable the system to track heart rate in real-time, rather than requiring post-processing of video footage.
Overall, this breakthrough has significant implications for the field of remote photoplethysmography.
Cite this article: “Accurate and Robust Remote Photoplethysmography System Developed”, The Science Archive, 2025.
Remote, Photoplethysmography, Heart Rate, Vital Signs, Cameras, Face Feature Detection, Spectrogram Calculation, Iterative Curve Fitting, Cielab Color Space, Wearable Technology
Reference: Alexey Protopopov, “A Robust Remote Photoplethysmography Method” (2025).
