Non-invasive biofeedback system

Patent metadata

Field	Value
Publication number	US-10349885-B2
Application number	US-201414785261-A
Country	US
Kind code	B2
Filing date	Jan 16, 2014
Priority date	Apr 18, 2013
Publication date	Jul 16, 2019
Grant date	Jul 16, 2019

Abstract

A method, system, and computer program for non-invasively monitoring a physiological parameter and providing biofeedback. The method, system, and computer program provide for the non-invasive detection of a physiological parameter by detecting changes in color channel values of a user in a live video feed and presenting biofeedback to the user indicating the relative position of the physiological parameter to an optimal range.

First claim

The invention claimed is:

1. A method for non-invasively optimizing a user's exercise routine, the method comprising the steps of:
collecting information about a user for determining said user's optimal range;
tracking a facial area of the user in a live video feed;
detecting a first set of at least two channel values from the facial area of the user in each frame of the live video feed;
making corrective adjustments for user motion and changes in lighting conditions on the first set of at least two channel values, wherein the results of the correction produce a second set of at least two channel values corresponding to the first set of at least two channel values, such that a total of at least four channel values are associated to each frame of the live video feed;
converting each of the at least four channel values associated to each frame of the live video feed into a frequency wave pattern;
selecting a single channel amongst the at least four channel values, wherein the frequency wave pattern of said single channel provides the strongest indicia for physiological parameter detection;
processing the single channel for detecting a physiological parameter; and
presenting a biofeedback to the user on a display, wherein the biofeedback notifies the user at least where the detected physiological parameter is relative to the user's optimal range.

2. The method of claim 1 , further comprising the step of automatically adjusting intensity levels on an exercise machine such that the user's physiological parameter is brought into the user's optimal range.

3. The method of claim 1 , wherein the user's optimal range is a training zone determined by at least the user's minimum heart rate value and the user's maximum heart rate value.

4. The method of claim 1 , wherein the facial area tracking step utilizes skin-color detection.

5. The method of claim 1 , wherein the facial area tracking step utilizes Haar-like feature detection.

6. The method of claim 1 wherein the physiological parameter is heart rate.

7. The method of claim 1 , wherein the corrective adjustment step is an independent component analysis.

8. The method of claim 1 , wherein the conversion into a frequency wave pattern step is a Fast Fourier Transformation.

9. The method of claim 1 , wherein the selecting of a single channel step selects a frequency spike indicative of a highest ratio of peak power over a cumulative power.

10. The method of claim 1 , wherein the selecting of a single channel step selects a frequency spike where a ratio between a highest spike and a second highest spike is maximized.

11. The method of claim 1 , wherein the selecting of a single channel step is a most common frequency rate produced by a majority number of channels.

12. The method of claim 1 , wherein the video feed is captured utilizing a webcam or mobile device camera.

13. The method of claim 1 , further comprising the step of resizing the resolution of video frames for faster processing.

14. A non-transitory computer-readable medium having a computer program stored thereon for execution by a processor, the computer program operable to non-invasively optimize a user's exercise routine, wherein execution of the computer program by the processor performs the steps of:
collecting information about a user for determining said user's optimal range;
tracking a facial area of the user in a live video feed;
detecting a first set of at least two channel values from the facial area of the user in each frame of the live video feed;
making corrective adjustments for user motion and changes in lighting conditions on the first set of at least two channel values, wherein the results of the correction produce a second set of at least two channel values corresponding to the first set of at least two channel values, such that a total of at least four channel values are associated to each frame of the live video feed;
converting each of the at least four channel values associated to each frame of the live video feed into a frequency wave pattern;
selecting a single channel amongst the at least four channel values, wherein the frequency wave pattern of said single channel provides the strongest indicia for physiological parameter detection;
processing the single channel for detecting a physiological parameter; and
presenting a biofeedback to the user on a display, wherein the biofeedback notifies the user at least where the detected physiological parameter is relative to the user's optimal range.

15. The non-transitory computer-readable medium of claim 14 , further comprising the step of automatically adjusting intensity levels on an exercise machine such that the user's physiological parameter is brought into the optimal range.

16. The non-transitory computer-readable medium of claim 14 , wherein the optimal range is a training zone having a minimum heart rate value and maximum heart rate value.

17. The non-transitory computer-readable medium of claim 14 , wherein the facial area tracking step utilizes skin-color detection.

18. The non-transitory computer-readable medium of claim 14 , wherein the facial area tracking step utilizes Haar-like feature detection.

19. The non-transitory computer-readable medium of claim 14 wherein the physiological parameter is heart rate.

20. The non-transitory computer-readable medium of claim 14 , wherein the corrective adjustment step is an independent component analysis.

21. The non-transitory computer-readable medium of claim 14 , wherein the conversion into a frequency wave pattern step is a Fast Fourier Transformation.

22. The non-transitory computer-readable medium of claim 14 , wherein the selecting of a single channel step selects a frequency spike indicative of a highest ratio of peak power over a cumulative power.

23. The non-transitory computer-readable medium of claim 14 , wherein the selecting of a single channel step selects a frequency spike where a ratio between a highest spike and a second highest spike is maximized.

24. The non-transitory computer-readable medium of claim 14 , wherein the selecting of a single channel step is a most common frequency rate produced by a majority number of channels.

25. The non-transitory computer-readable medium of claim 14 , wherein the video feed is captured utilizing a webcam or mobile device camera.

26. The non-transitory computer-readable medium of claim 14 , further comprising the step of resizing the resolution of video frames for faster processing.

27. A system for non-invasively optimizing a user's exercise routine, the system comprising:
at least one video camera mounted in or on a housing and operably connected to a computing module, said at least one video camera oriented towards a user and operable to capture a live video feed of the user;
a computing module with a processor and a memory, said computing module mounted within the housing and configured to:
store optimal range values of a user, wherein the optimal range values are the lower and upper heart rate boundaries defined by a training zone determined by at least a user's resting heart rate and maximum heart rate;
receive the live video feed of the user from the at least one video camera, said live video feed comprising a plurality of frames, said computing module being configured to perform the following actions for each frame:
detect a first set of at least two channel values;
make corre

Assignees

• Univ Wichita State

Inventors

• He Jibo
• Patterson Jeremy

Classifications

• A61B5/7257

  using Fourier transforms · CPC title

• A61B5/024

  Measuring pulse rate or heart rate · CPC title

• A61B5/0077

  Devices for viewing the surface of the body, e.g. camera, magnifying lens · CPC title

• A63B24/0062

  Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance · CPC title

• A61B5/02438

  with portable devices, e.g. worn by the patient · CPC title