Granted Patent B2

US 8,790,269 · App. 13/103,406 · Granted Jul 29, 2014

Abstract

Claims (68)

1. A method for monitoring respiration using a thermal imaging system, the method comprising:

capturing thermal images of a subject of interest intended to be monitored for respiration using a thermal image camera set to a temperature of a facial region of said subject, each thermal image comprising a plurality of pixels each corresponding to a surface temperature of said facial region across a thermal wavelength band;

retrieving locational relationship of vectors and angles to determine said location of a facial feature consisting of a nose and a mouth by;

using a location of eyes relative to a location of ears of said subject to locate said nose, and

using a location of said ears and chin to locate said mouth;

analyzing said thermal images to determine said location of said nose and said mouth;

tracking physical motion of said facial feature over time to identify a physical motion pattern of respiration, said tracked physical motion being independent from determining a thermal pattern of respiration using thermal image analysis of said facial feature;

determining a respiration rate from said physical motion pattern of respiration;

performing any of: comparing said determined respiration rate to a pre-defined respiration rate, and comparing said determined physical motion pattern of respiration pattern to a pre-defined physical motion pattern of respiration pattern; and

initiating an alarm in response to either of said comparisons falling outside a level of acceptability.

2. The method of claim 1 , wherein analyzing said thermal images to determine said facial feature associated with respiration comprises:

using pixel temperature values to identify a location of an extremity of the head and face of said subject of interest; and

determining a location of said facial feature associated with respiration relative to said location of said identified head and face extremity.

3. The method of claim 2 , wherein determining a location of said facial feature associated with respiration comprises:

retrieving from a database at least one locational relationship associated with said identified extremity of said subject's head and face; and

using said locational relationship to determine said location of said facial feature associated with respiration.

4. The method of claim 1 , wherein identifying said pattern of respiration comprises tracking over time any of: R, G, and B, values of pixels associated with said facial feature associated with respiration obtained from the R,G,B, channels of said camera.

5. The method of claim 4 , wherein determining said respiration rate comprises counting a number of peaks of said tracked pixel values over an amount of time.

6. The method of claim 1 , wherein comparing said respiration rate to said pre-defined respiration rate comprises calculating a difference between said two respiration rates.

7. The method of claim 1 , wherein comparing said determined physical motion pattern of respiration to said pre-defined physical motion pattern of respiration comprises determining a measure of mismatch between said two physical motion patterns of respiration.

8. The method of claim 1 , further comprising compensating for a movement of said subject of interest in said captured video sequence by removing non-periodic motion of said facial feature.

9. The method of claim 1 , wherein said alarm comprises any of: a visible light, an audible noise, and a signal which activates a device.

10. A system for monitoring respiration using a thermal imaging system, the system comprising:

a thermal image camera set to a temperature of a facial region of a subject of interest intended to be monitored for respiration, said thermal camera capturing thermal images of said subject of interest, each thermal image comprising a plurality of pixels each corresponding to a surface temperature of said facial region across a thermal wavelength band;

a memory and a storage medium; and

a processor in communication with and said thermal image camera, said storage medium and said memory, said processor executing machine readable instructions for performing:

retrieving locational relationship of vectors and angles to determine said location of a facial feature consisting of a nose and a mouth by;

using a location of eyes relative to a location of ears of said subject to locate said nose, and

using a location of said ears and chin to locate said mouth;

analyzing said captured thermal images to determine said location of said nose and said mouth;

tracking physical motion of said facial feature over time to identify a physical motion pattern of respiration, said tracked physical motion being independent from determining a thermal pattern of respiration using thermal image analysis of said facial feature;

determining a respiration rate from said physical motion pattern of respiration;

performing any of: comparing said determined respiration rate to a pre-defined respiration rate, and comparing said determined physical motion pattern of respiration pattern to a pre-defined physical motion pattern of respiration pattern; and

initiating an alarm in response to either of said comparisons falling outside a level of acceptability.

11. The system of claim 10 , wherein analyzing said thermal images to determine said facial feature associated with respiration comprises:

using pixel temperature values to identify a location of an extremity of the head and face of said subject of interest; and

determining a location of said facial feature associated with respiration relative to said location of said identified head and face extremity.

12. The system of claim 11 , wherein determining a location of said facial feature associated with respiration comprises:

retrieving from a database at least one locational relationship associated with said identified extremity of said subject's head and face; and

using said locational relationship to determine said location of said facial feature associated with respiration.

13. The system of claim 10 , wherein identifying said pattern of respiration comprises tracking over time any of: R, G, and B, values of pixels associated with said facial feature associated with respiration obtained from the R,G,B, channels of said camera.

14. The system of claim 13 , wherein determining said respiration rate comprises counting a number of peaks of said plotted pixel values over an amount of time.

15. The system of claim 10 , wherein comparing said respiration rate to said pre-defined respiration rate comprises calculating a difference between said two respiration rates.

16. The system of claim 10 , wherein comparing said determined physical motion pattern of respiration to said pre-defined physical motion pattern of respiration comprises determining a measure of mismatch between said two physical motion patterns of respiration.

17. The system of claim 10 , further comprising compensating for a movement of said subject of interest in said captured video sequence by removing non-periodic motion of said facial feature.

18. The system of claim 10 , wherein said alarm comprises any of: a visible light, an audible noise, and a signal which activates a device.

19. A computer implemented method for monitoring respiration using a thermal imaging system, the method comprising:

capturing thermal images of a subject of interest intended to be monitored for respiration using a thermal image camera set to a temperature of a facial region of said subject, each thermal image comprising a plurality of pixels each corresponding to a surface temperature of said facial region across a thermal wavelength band;

retrieving locational relationship of vectors and angles to determine said location of a facial feature consisting of a nose and a mouth by:

using a location of eyes relative to a location of ears of said subject to locate said nose, and

using a location of said ears and chin to locate said mouth;

analyzing said thermal images to determine said location of said nose and said mouth;

tracking physical motion of said facial feature over time to identify a physical motion pattern of respiration, said tracked physical motion being independent from determining a thermal pattern of respiration using thermal image analysis of said facial feature;

determining a respiration rate from said physical motion pattern of respiration;

performing any of: comparing said determined respiration rate to a pre-defined respiration rate, and comparing said determined physical motion pattern of respiration pattern to a pre-defined physical motion pattern of respiration pattern; and

initiating an alarm in response to either of said comparisons falling outside a level of acceptability.

20. The computer implemented method of claim 19 , wherein analyzing said thermal images to determine said facial feature associated with respiration comprises:

using pixel temperature values to identify a location of an extremity of the head and face of said subject of interest; and

determining a location of said facial feature associated with respiration relative to said location of said identified head and face extremity.

21. The computer implemented method of claim 20 , wherein determining a location of said facial feature associated with respiration comprises:

retrieving from a database at least one locational relationship associated with said identified extremity of said subject's head and face; and

using said locational relationship to determine said location of said facial feature associated with respiration.

22. The computer implemented method of claim 19 , wherein identifying said pattern of respiration comprises:

tracking over time any of: R, G, and B, values of pixels associated with said facial feature associated with respiration obtained from the R,G,B, channels of said camera; and

counting a number of peaks of said plotted pixel values over an amount of time.

23. The computer implemented method of claim 19 , wherein comparing said respiration rate to said pre-defined respiration rate comprises calculating a difference between said two respiration rates.

24. The computer implemented method of claim 19 , wherein comparing said determined physical motion pattern of respiration to said pre-defined physical motion pattern of respiration comprises determining a measure of mismatch between said two physical motion patterns of respiration.

25. The computer implemented method of claim 19 , further comprising compensating for a movement of said subject of interest in said captured video sequence by removing non-periodic motion of said facial feature.

Assignments (9)