System and methods for video-based monitoring of vital signs
The present invention relates to the field of medical monitoring, and in particular non-contact, video-based monitoring of pulse rate, respiration rate, motion, and oxygen saturation. Systems and methods are described for capturing images of a patient, producing intensity signals from the images, filtering those signals to focus on a physiologic component, and measuring a vital sign from the filtered signals.
1. A video-based method of measuring a patient's vital sign, comprising:
receiving a video signal from a video camera, the video signal having a field of view;
extracting from the video signal a time-varying color signal for each of a plurality of regions;
identifying a frequency content of each time-varying color signal;
selecting two or more non-adjacent regions that have a shared frequency content comprising a modulation at a shared frequency;
combining the color signals of the selected regions to thereby provide a combined color signal;
measuring a vital sign from the combined color signal;
outputting the vital sign for further processing or display; and
updating the selected regions by adding or removing regions from the selected regions based on the frequency content of each region.
2. The method of claim 1 , wherein combining the color signals of the selected regions comprises averaging the color signals from the selected regions.
3. The method of claim 1 , wherein the selected regions have different sizes.
4. The method of claim 1 , wherein the vital sign comprises heart rate.
5. The method of claim 4 , wherein measuring the heart rate comprises accumulating frequency peaks from the combined signal, selecting a median frequency, and updating a running average heart rate from the selected frequency.
6. The method of claim 1 , further comprising calculating a statistic of the combined color signal, wherein the statistic comprises an amplitude, a variability, a skew, or a signal to noise ratio.
7. The method of claim 6 , wherein combining the color signals of the selected regions comprises applying a weight to each color signal that is being combined, the weight being based on the statistic.
8. The method of claim 6 , further comprising determining a weight for the vital sign, the weight being based on the statistic, and adding the vital sign to a running average based on the weight.
9. The method of claim 1 , wherein selecting the two or more non-adjacent regions further comprises selecting regions that satisfy a quality criterion, and wherein the quality criterion comprises a signal to noise ratio that satisfies a threshold, or a skew value that satisfies a threshold.
10. The method of claim 9 , further comprising removing a color signal from the combined color signal upon failure of the removed color signal to satisfy the quality criterion.
11. The method of claim 1 , wherein extracting from the video signal the time-varying color signal comprises extracting two time-varying color signals for each of the plurality of regions, and wherein measuring the vital sign from the combined color signal comprises measuring oxygen saturation from the two time-varying color signals.
12. The method of claim 1 , wherein each of the plurality of regions include exposed skin of a patient.
13. The method of claim 1 , wherein the field of view includes exposed skin of a patient.
14. The method of claim 1 , wherein the two or more non-adjacent regions that have a shared frequency content comprising a modulation at a shared frequency are also non-overlapping.
15. A system for video-based measurement of a patient's vital sign, comprising:
a video camera positioned remote from a patient; and
a hardware memory coupled to the video camera by wired or wireless communication, the memory storing instructions for instructing a processor to:
extract from a video signal received from the video camera a time-varying color signal for each of a plurality of regions;
identify a frequency content of each time-varying color signal;
select two or more non-adjacent regions that have a shared frequency content comprising a modulation at a shared frequency;
combine the color signals of the selected regions to thereby provide a combined color signal;
measure a vital sign from the combined color signal;
output the vital sign for further processing or display; and
update the selected regions by adding or removing regions from the selected regions based on the frequency content of each region;
receive a video signal from the video camera, the video signal having a field of view.
16. The system of claim 15 , wherein combining the color signals of the selected regions comprises averaging the color signals from the selected regions.
17. The system of claim 15 , wherein the instructions further instruct the processor to:
calculate a statistic of the combined color signal, wherein the statistic comprises an amplitude, a variability, a skew, or a signal to noise ratio.
18. The system of claim 15 , wherein selecting the two or more non-adjacent regions further comprises selecting regions that satisfy a quality criterion, and wherein the quality criterion comprises a signal to noise ratio that satisfies a threshold, or a skew value that satisfies a threshold.
19. The system of claim 15 , wherein extracting from the video signal the time-varying color signal comprises extracting two time-varying color signals for each of the plurality of regions, and wherein measuring the vital sign from the combined color signal comprises measuring oxygen saturation from the two time-varying color signals.