Remote Vital Sign Sensing with Joint-Sparse NIR RPPG
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Remote photoplethysmography (RPPG) systems face challenges in providing accurate vital sign measurements in volatile environments due to noise from illumination variations and motion, which degrade the signal-to-noise ratio and introduce false peaks, making it difficult to distinguish photoplethysmographic signals from other intensity variations.
Innovation Solution
The implementation of a narrow-band near-infrared (NIR) system and an algorithm that uses joint sparsity in the frequency domain to reduce noise, specifically by projecting noisy imaging photoplethysmography (iPPG) signals onto an orthogonal complement of the noise subspace and employing active in-car illumination to minimize ambient illumination changes, allowing for robust estimation of vital signs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If remote photoplethysmography (RPPG) is used to measure vital signs, then non-contact measurement is achieved, but measurement precision deteriorates due to noise from illumination variations and motion
Solution Approach 1:
The patent transforms the RPPG signal from the time domain to the frequency domain through Fourier transformation. This parameter change in the representation domain allows separation of the physiological signal components (heart rate, respiration) from noise components based on their distinct frequency characteristics, thereby improving measurement precision while maintaining non-contact operation
Solution Approach 2:
The patent introduces an intermediary processing stage involving frequency domain transformation and component separation algorithms. This intermediary process acts as a mediator between the raw noisy RPPG signal and the final vital sign measurement, filtering out illumination variations and motion artifacts while preserving the physiological signal
2Ease of operation
If conventional RPPG measurement is performed in volatile environments, then unobtrusive monitoring is achieved, but measurement precision deteriorates due to false peaks from motion and illumination changes
Solution Approach 1:
The patent changes the analysis parameter from time-domain waveforms to frequency-domain spectra. By examining the frequency characteristics rather than temporal patterns, the system can distinguish true physiological signals (with characteristic frequency ranges) from false peaks caused by motion and illumination variations, improving accuracy in unobtrusive monitoring
Solution Approach 2:
The patent replaces traditional time-domain signal processing methods with frequency-domain analysis. This substitution of the analysis mechanism enables better discrimination of signal components, allowing the system to maintain unobtrusive monitoring while reducing false peak detection through spectral analysis
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of vital sign estimation by reducing noise sensitivity and maintaining measurement quality even in dynamic environments, such as in-vehicle settings, by using a narrow-band NIR light source and camera filter, effectively filtering out ambient illumination changes and motion noise.
Implementation Method 1
Photoplethysmography (PPG) is an optical measurement technique that evaluates a time-variant change of light reflectance or transmission of an area or volume of interest, which can be used to detect blood volume changes in microvascular bed of tissue
Implementation Method 2
PPG is based on a principle that blood absorbs and reflects light differently than surrounding tissue, so variations in the blood volume with every heartbeat affect light transmission or reflectance correspondingly
Implementation Method 3
The system includes a narrow-band near-infrared (NIR) light source to illuminate the skin of the person at a narrow frequency band including a near-infrared wavelength of 940 nm and an NIR camera with a narrow-band filter overlapping the wavelengths of the narrow-band light source
Data Source
AI summary
A remote photoplethysmography (RPPG) system for estimating vital signs of a person is provided. The RPPG system is configured to receive a set of imaging photoplethysmography (iPPG) signals measured from different regions of a skin of a person. The RPPG system is further configured to determine frequency coefficients at the frequency bins of the quantized frequency spectrum of the measured iPPG signals by minimizing a distance between the measured iPPG signals and corresponding iPPG signals reconstructed from the determined frequency coefficients, while enforcing joint sparsity of the determined frequency coefficients subject to the sparsity level constraint, such that the determined frequency coefficients of different iPPG signals have the non-zero values at the same frequency bins; and output one or a combination of the determined frequency coefficients, the iPPG signals reconstructed from the determined frequency coefficients, and a vital sign signal corresponding to the reconstructed iPPG signals.