Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Robust Remote Photoplethysmography Method

Alexey Protopopov

TL;DR

The paper addresses robust remote heart-rate estimation from video under movement and lighting variations by proposing a multi-stage pipeline that leverages the CIELAB color space to isolate chromatic signals, MediaPipe-based face landmark tracking to sample signals from facial regions, and a spectrogram-based processing step with an iterative polyline fit to extract heart-rate harmonics. It demonstrates an average MAE of $1.95$ BPM on 26 videos from 19 volunteers, outperforming prior works and showing improved resistance to distortions from movement and makeup. The approach requires minimal hardware (a standard camera with IR-filter removal) and has moderate computational demands, though it does not operate in real time and relies on relatively long spectrogram windows. This work enables more accessible, non-contact heart-rate monitoring with potential extensions to higher frame rates or multi-camera setups for enhanced temporal resolution.

Abstract

Remote photoplethysmography (rPPG) is a method for measuring a subjects heart rate remotely using a camera. Factors such as subject movement, ambient light level, makeup etc. complicate such measurements by distorting the observed pulse. Recent works on this topic have proposed a variety of approaches for accurately measuring heart rate in humans, however these methods were tested in ideal conditions, where the subject does not make significant movements and all measurements are taken at the same level of illumination. In more realistic conditions these methods suffer from decreased accuracy. The study proposes a more robust method that is less susceptible to distortions and has minimal hardware requirements. The proposed method uses a combination of mathematical transforms to calculate the subjects heart rate. It performs best when used with a camera that has been modified by removing its infrared filter, although using an unmodified camera is also possible. The method was tested on 26 videos taken from 19 volunteers of varying gender and age. The obtained results were compared to reference data and the average mean absolute error was found to be at 1.95 beats per minute, which is noticeably better than the results from previous works. The remote photoplethysmography method proposed in the present article is more resistant to distortions than methods from previous publications and thus allows one to remotely and accurately measure the subjects heart rate without imposing any significant limitations on the subjects behavior.

A Robust Remote Photoplethysmography Method

TL;DR

The paper addresses robust remote heart-rate estimation from video under movement and lighting variations by proposing a multi-stage pipeline that leverages the CIELAB color space to isolate chromatic signals, MediaPipe-based face landmark tracking to sample signals from facial regions, and a spectrogram-based processing step with an iterative polyline fit to extract heart-rate harmonics. It demonstrates an average MAE of BPM on 26 videos from 19 volunteers, outperforming prior works and showing improved resistance to distortions from movement and makeup. The approach requires minimal hardware (a standard camera with IR-filter removal) and has moderate computational demands, though it does not operate in real time and relies on relatively long spectrogram windows. This work enables more accessible, non-contact heart-rate monitoring with potential extensions to higher frame rates or multi-camera setups for enhanced temporal resolution.

Abstract

Remote photoplethysmography (rPPG) is a method for measuring a subjects heart rate remotely using a camera. Factors such as subject movement, ambient light level, makeup etc. complicate such measurements by distorting the observed pulse. Recent works on this topic have proposed a variety of approaches for accurately measuring heart rate in humans, however these methods were tested in ideal conditions, where the subject does not make significant movements and all measurements are taken at the same level of illumination. In more realistic conditions these methods suffer from decreased accuracy. The study proposes a more robust method that is less susceptible to distortions and has minimal hardware requirements. The proposed method uses a combination of mathematical transforms to calculate the subjects heart rate. It performs best when used with a camera that has been modified by removing its infrared filter, although using an unmodified camera is also possible. The method was tested on 26 videos taken from 19 volunteers of varying gender and age. The obtained results were compared to reference data and the average mean absolute error was found to be at 1.95 beats per minute, which is noticeably better than the results from previous works. The remote photoplethysmography method proposed in the present article is more resistant to distortions than methods from previous publications and thus allows one to remotely and accurately measure the subjects heart rate without imposing any significant limitations on the subjects behavior.

Paper Structure

This paper contains 8 sections, 7 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Color space
  4. Face tracking
  5. Signal processing
  6. Results and discussion
  7. Conclusion
  8. Acknowledgements

Figures (5)

  • Figure 1: Comparison between RGB and CIELAB color spaces.
  • Figure 2: A subject’s face with landmarks drawn over it.
  • Figure 3: Spectrogram of the a* channel.
  • Figure 4: The spectrogram together with the map of the window function.
  • Figure 5: Heart rate comparison plots.