PROCESSING A VIDEO FOR VASCULAR PATTERN DETECTION AND CARDIAC FUNCTION ANALYSIS

• US 20130322729A1
• Filed: 05/30/2012
• Published: 12/05/2013
• Est. Priority Date: 05/30/2012
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: MESTHA, Lalit Keshav, XU, Beilei, BERNAL, Edgar A.
• Granted Patent: US 8,897,522 B2
• Time in Patent Office: Days
• US Class Current: 382/134
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/02 Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/029 Measuring or recording blood output from the heart, e.g. minute volume A61B8/065 takes precedence
• CPC Class Codes: A61B 5/489 Blood vessels
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30076 Plethysmography
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/0016 involving temporal comparison

Abstract

What is disclosed is a non-contact system and method for determining cardiac function parameters from a vascular pattern identified from RGB and IR video signals captured simultaneously of a region of exposed skin of a subject of interest. In one embodiment, a video of a region of exposed skin is captured using a video camera that captures color values for pixels over visible channels and an IR camera that measures pixel intensity values in wavelength ranges of interest. Pixel intensity values are processed to generate a vascular binary mask that indicates pixel locations corresponding to the vascular pathways. The IR images are registered with corresponding data from the camera'"'"'s visible channels such that pixels that correspond to the vascular pattern can be isolated in each frame of the video of visible color data. Once processed, pixels associated with the isolated vascular patterns are analyzed to determine desired cardiac function parameters.

Claims

1. A method for determining a cardiac function parameter from a video of a subject of interest acquired in a non-contact remote sensing environment, the method comprising:

receiving video of a region of exposed skin of a subject of interest being monitored for cardiac function, said video having been captured using a video system comprising at least one video camera that outputs data comprising color values collected for pixels by at least one visible channel, and at least one infrared (IR) video camera that outputs data comprising intensity values collected for pixels by at least one infrared channel;

processing said infrared pixel intensity values to generate a vascular binary mask that indicates the location of pixels corresponding with the vascular pathway of the subject within said region of exposed skin;

registering said IR pixel data with pixels of said visible channels such that pixels associated with said subject'"'"'s vascular pattern can be isolated in said video; and

analyzing pixels associated with said isolated vascular pattern to determine at least one cardiac function parameter for said subject.

2. The method of claim 1, wherein said video camera that captures color values and said infrared video camera that captures pixel intensity values are integrated into a single video camera.

3. The method of claim 1, wherein said video camera and said infrared video camera simultaneously capture said video in both the visible and infrared wavelength ranges.

4. The method of claim 1, further comprising identifying said region of exposed skin using any of:

object identification, pixel classification, material analysis, texture identification, and pattern recognition.

5. The method of claim 1, wherein, in advance of generating said vascular binary mask, further comprising processing said video to compensate for non-uniform illumination due to a curvature of a surface of said region of exposed skin.

6. The method of claim 1, wherein registering said infrared pixel data with data output by said at least one visible channel comprises matching corresponding features in each of said channels.

7. The method of claim 1, wherein said cardiac function parameter comprises any of:

arterial pulse, pulse frequency, pulse transit time, cardiac output, blood pressure, vessel diameter, blood density, vessel blockage, and peripheral neuropathy.

8. The method of claim 1, further comprising processing said video to remove a texture of skin on a surface of said region of exposed skin via a smoothing technique.

9. The method of claim 1, further comprising pre-processing said video to compensate for any of:

a motion induced blur, an imaging blur, and slow illuminant variation.

10. The method of claim 1, wherein said infrared channel includes the wavelength ranges of any of:

near infrared (NIR), short wave infrared (SWIR), mid-wave infrared (MWIR), and long wave infrared (LWIR).

11. The method of claim 1, wherein processing pixels associated with said isolated vascular pattern comprises:

integrating information being carried by pixels from all of said channels along vessels of said vascular pattern with respect to time and obtaining a resulting signal;

normalizing said resulting signal with respect to a value derived from apriori knowledge of said subject'"'"'s cardiac history;

converting said normalized signal to a time-series signal; and

isolating desired components of interest in said time-series signal via independent component selection.

12. The method of claim 1, further comprising any of:

enhancing a contrast of said video, removing undesirable environmental noise from said video, and filtering said video via independent component selection to emphasize desired content in said video.

13. A system for determining a cardiac function parameter from a video of a subject of interest acquired in a non-contact remote sensing environment, the system comprising:

a video system comprising at least one video camera that outputs data comprising color values collected for pixels by at least one visible channel, and at least one infrared video camera that outputs data comprising intensity values collected for pixels by at least one infrared channel; and

a processor in communication with said video camera system and a memory, said processor executing machine readable instructions for performing;

receiving video of a region of exposed skin of a subject of interest being monitored for cardiac function, said video having been captured using said video system;

processing said infrared pixel intensity values to generate a vascular binary mask that indicates the location of pixels corresponding with the vascular pathway of the subject within said region of exposed skin;

registering said vascular binary mask with pixels of said visible channels such that pixels associated with said subject'"'"'s vascular pattern can be isolated in said video; and

analyzing pixels associated with said isolated vascular pattern to determine at least one cardiac function parameter for said subject.

14. The system of claim 13, wherein said video camera that captures color values and said infrared video camera that captures pixel intensity values are integrated into a single video camera.

15. The system of claim 13, wherein said color video camera and said infrared video camera simultaneously capture said video in both the visible and infrared wavelength ranges.

16. The system of claim 13, further comprising identifying said region of exposed skin using any of:

object identification, pixel classification, material analysis, texture identification, and pattern recognition.

17. The system of claim 13, wherein, in advance of generating said vascular binary mask, further comprising processing said video to compensate for non-uniform illumination due to a curvature of a surface of said region of exposed skin.

18. The system of claim 13, wherein registering said infrared pixel data with data output by said at least one visible channel comprises matching corresponding features in each of said channels.

19. The system of claim 13, further comprising processing said video to remove a texture of skin on a surface of said region of exposed skin via a smoothing technique.

20. The system of claim 13, wherein said cardiac function parameter comprises any of:

arterial pulse, pulse frequency, pulse transit time, cardiac output, blood pressure, vessel diameter, blood density, vessel blockage, and peripheral neuropathy.

21. The system of claim 13, further comprising pre-processing said video to compensate for any of:

a motion induced blur, an imaging blur, and slow illuminant variation.

22. The system of claim 13, wherein said infrared channel includes the wavelength ranges of any of:

near infrared (NIR), short wave infrared (SWIR), mid-wave infrared (MWIR), and long wave infrared (LWIR).

23. The system of claim 13, wherein processing pixels associated with said isolated vascular pattern comprises:

integrating information being carried by pixels from all of said channels along vessels of said vascular pattern with respect to time and obtaining a resulting signal;

normalizing said resulting signal with respect to a value derived from apriori knowledge of said subject'"'"'s cardiac history;

converting said normalized signal to a time-series signal; and

isolating desired components of interest in said time-series signal via independent component selection.

24. The system of claim 13, further comprising any of:

enhancing a contrast of said video, removing undesirable environmental noise from said video, and filtering said video via independent component selection to emphasize desired content in said video.