Human body heart rate variability and respiration rate measuring method based on variational mode decomposition and constrained independent component analysis

Abstract

The invention discloses a human heart rate variability (HRV) and respiratory rate (RR) measurement method based on variational mode decomposition (VMD) and constrained independent component analysis (cICA), which comprises the following steps: performing pixel coherent average operation on human face video data, converting the human face video data into RGB observation signals, and performing preprocessing operation on the RGB observation signals to realize standardization. Performing four-channel decomposition on the G-channel signal by using a VMD algorithm, and solving a reference signal of a blood flow pulse (BVP) on the basis of the component with the maximum spectrum peak value in the decomposed four-channel components; based on the reference signal, a cICA algorithm is used for separating a BVP source signal from the RGB observation signal, a VMD algorithm is used for conducting four-channel decomposition on the BVP source signal, high-quality pulse wave components are extracted from the separated four-channel components, and HRV parameters and RR are further obtained. According to the method, the inherent source sorting fuzzy problem in a traditional blind source separation/independent component analysis algorithm can be avoided, and the method has good noise interference resistance and has good application prospects in the field.

Description

technical field [0001] The present invention relates to the research field of extraction of facial video physiological parameters based on imaging photoplethysmography (IPPG) technology, including the extraction of heart rate variability (HRV) parameters and respiration rate (RR), in particular to the variational mode decomposition (VMD) algorithm , the constrained independent component analysis (cICA) algorithm. Background technique [0002] Heart rate variability (HRV) and respiration rate (RR) are important clinical physiological parameters of the human body. Exploring the non-contact measurement method of HRV and RR has become one of the research hotspots in the field of biomedical engineering and instrumentation. [0003] Imaging Photoplethysmography (IPPG) is a biomedical signal processing technology that analyzes the video data of sensitive areas on the human body surface through intelligent information processing algorithms, and then realizes the extraction of physi...

AI Technical Summary

Problems solved by technology

[0012] The object of the present invention is to provide a kind of HRV and RR measuring method based on variational mode decomposition (VMD) and constrained independent component analysis (cICA), extract HRV parameter and RR synchronously from human face video, avoid traditional method Inherent BVP source sorting fuzzy problem, and well overcome the difficult problem of BVP source signal noise residual in the extraction of physiological parameters

Images