VIDEO-BASED ESTIMATION OF HEART RATE VARIABILITY
First Claim
1. A method for estimating heart rate variability from a video captured of a subject of interest being monitored in a non-contact remote sensing environment, the method comprising:
- receiving a video captured of a target area of a region of exposed skin of a subject of interest where a photoplethysmographic (PPG) signal of said subject can be registered, said video comprising video images captured by a video camera with at least one imaging channel;
processing said video images to generate a time-series signal containing a PPG signal captured by said imaging channel;
processing said PPG signal to obtain a nearly stationary PPG signal comprising;
Pstat=(I−
(I+λ
2D2TD2)−
1Poriginal where, I is an identity matrix, Poriginal is a normalized zero-removed time-series signal, λ
is a user-defined parameter used to adjust a frequency response of said de-trending algorithm, and D2 is a second order difference matrix;
extracting, over a pre-defined time interval, low frequency and high frequency components of an integrated power spectrum within said time-series signal; and
determining a ratio of said low and high frequency components over said interval, said ratio comprising said subject'"'"'s estimated heart rate variability for said interval.
6 Assignments
0 Petitions
Accused Products
Abstract
What is disclosed is a video-based system and method for estimating heart rate variability from time-series signals generated from video images captured of a subject of interest being monitored for cardiac function. In a manner more fully disclosed herein, low frequency and high frequency components are extracted from a time-series signal obtained by processing a video of the subject being monitored. A ratio of the low and high frequency of the integrated power spectrum within these components is computed. Analysis of the dynamics of this ratio over time is used to estimate heart rate variability. The teachings hereof can be used in a continuous monitoring mode with a relatively high degree of measurement accuracy and find their uses in a variety of diverse applications such as, for instance, emergency rooms, cardiac intensive care units, neonatal intensive care units, and various telemedicine applications.
72 Citations
23 Claims
-
1. A method for estimating heart rate variability from a video captured of a subject of interest being monitored in a non-contact remote sensing environment, the method comprising:
-
receiving a video captured of a target area of a region of exposed skin of a subject of interest where a photoplethysmographic (PPG) signal of said subject can be registered, said video comprising video images captured by a video camera with at least one imaging channel; processing said video images to generate a time-series signal containing a PPG signal captured by said imaging channel; processing said PPG signal to obtain a nearly stationary PPG signal comprising;
Pstat=(I−
(I+λ
2D2TD2)−
1Poriginalwhere, I is an identity matrix, Poriginal is a normalized zero-removed time-series signal, λ
is a user-defined parameter used to adjust a frequency response of said de-trending algorithm, and D2 is a second order difference matrix;extracting, over a pre-defined time interval, low frequency and high frequency components of an integrated power spectrum within said time-series signal; and determining a ratio of said low and high frequency components over said interval, said ratio comprising said subject'"'"'s estimated heart rate variability for said interval. - View Dependent Claims (2, 3, 4, 5, 8)
-
- 6. (canceled)
-
9. A system for estimating heart rate variability from a video captured of a subject of interest being monitored in a non-contact remote sensing environment, the system comprising:
-
a video camera with at least one imaging channel; and a processor in communication with a memory, said processor executing machine readable instructions for performing; receiving a video captured of a target area of a region of exposed skin of a subject of interest where a photoplethysmographic (PPG) signal of said subject can be registered, said video comprising video images captured by said video camera; processing said video images to generate a time-series signal containing a PPG signal captured by said imaging channel; processing said PPG signal to obtain a nearly stationary PPG signal comprising;
Pstat=(I−
(I+λ
2D2TD2)−
Poriginalwhere, I is an identity matrix, Poriginal is a normalized zero-removed time-series signal, λ
is a user-defined parameter used to adjust a frequency response of said de-trending algorithm, and D2 is a second order difference matrix;extracting, over a pre-defined time interval, low frequency and high frequency components of an integrated power spectrum within said time-series signal; and determining a ratio of said low and high frequency components over said interval, said ratio comprising said subject'"'"'s estimated heart rate variability for said interval. - View Dependent Claims (10, 11, 12, 13, 16)
-
- 14. (canceled)
-
17. A computer implemented method for estimating heart rate variability from a video captured of a subject of interest being monitored in a non-contact remote sensing environment, the method comprising:
-
receiving a video captured of a target area of a region of exposed skin of a subject of interest where a photoplethysmographic (PPG) signal of said subject can be registered, said video comprising video images captured by a video camera with at least one imaging channel; processing said video images to generate a time-series signal containing PPG signal captured by said imaging channel; de-trending said PPG signal to remove slow non-stationary trends from said signal to obtain a nearly stationary PPG signal comprising;
Pstat=(I−
(I+λ
2D2TD2)−
1Poriginalwhere, I is an identity matrix, Poriginal is a normalized zero-removed time-series signal, λ
is a user-defined parameter used to adjust a frequency response of said de-trending algorithm, and D2 is a second order difference matrix;extracting, over a pre-defined time interval, low frequency and high frequency components of the integrated power spectrum within said time-series signal; determining a ratio of said low and high frequency components over said interval, said ratio comprising said subject'"'"'s estimated heart rate variability for said interval; and communicating said estimated heart rate variability to a display device. - View Dependent Claims (18, 19, 20, 21)
-
- 22. (canceled)
Specification