System and method of biomechanical posture detection and feedback including sensor normalization

• US 9,541,994 B2
• Filed: 07/31/2015
• Issued: 01/10/2017
• Est. Priority Date: 07/13/2011
• Status: Active Grant

• Current Assignee: Seismic Holdings, Inc.
• Original Assignee: LUMO BodyTech, Inc.
• Inventors: Chang, Andrew Robert, Perkash, Monisha, Wang, C. Charles, Hauenstein, Andreas Martin
• Primary Examiner(s): MCNALLY, KERRI L
• Application Number:
  US14/815,781
• Publication Number:
  US 20150335280A1
• Time in Patent Office: 529 Days
• Field of Search: 340/573.7
• US Class Current: 1/1
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/067 using accelerometers or gyroscopes
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/4561 Evaluating static posture, e.g. undesirable back curvature A61B5/1116 takes precedence
• CPC Class Codes: A61B 5/486 Bio-feedback A61B5/375 takes precedence
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00

Abstract

A system and method are described herein for a sensor device which biomechanically detects in real-time a user'"'"'s movement state and posture and then provides real-time feedback to the user based on the user'"'"'s real-time posture. The feedback is provided through immediate sensory feedback through the sensor device (e.g., a sound or vibration) as well as through an avatar within an associated application with which the sensor device communicates. The sensor device detects the user'"'"'s movement state and posture by capturing data from a tri-axial accelerometer in the sensor device. Streamed data from the accelerometer is normalized to correct for sensor errors as well as variations in sensor placement and orientation. Normalization is based on accelerometer data collected while the user is wearing the device and performing specific actions.

Claims

1. A method comprising:

capturing, by a tri-axial accelerometer attached to a user, first tri-axial accelerometer data over a first period of time while the user is walking;

averaging, by a microprocessor, the captured first tri-axial accelerometer data;

creating, by the microprocessor, a first normalization matrix for vertical alignment based on the averaged first tri-axial accelerometer data;

capturing, by the tri-axial accelerometer attached to the user, second tri-axial accelerometer data over a second period of time, while the user is stationary;

averaging, by the microprocessor, the captured second tri-axial accelerometer data;

creating, by the microprocessor, a second normalization matrix for lateral alignment based on an averaged third tri-axial accelerometer data;

capturing, by the tri-axial accelerometer attached to the user, third tri-axial accelerometer data at a third point in time;

creating, by the microprocessor, normalized accelerometer data by applying the first normalization matrix and the second normalization matrix to the captured third tri-axial accelerometer data; and

analyzing at least the normalized accelerometer data and determining a movement and posture state of the user.

2. The method of claim 1 further comprising, before averaging by the microprocessor the captured first tri-axial accelerometer data:

calculating, by the microprocessor, smoothed power from the captured first tri-axial accelerometer data;

identifying, by the microprocessor, data in the captured first tri-axial accelerometer data which results in the calculated power being below a threshold; and

discarding, by the microprocessor, the identified data from the captured first tri-axial accelerometer data.

3. The method of claim 1 further comprising, after creating by the microprocessor the normalized accelerometer data:

recognizing, by the microprocessor, that the user is moving;

averaging, by the microprocessor, the normalized accelerometer data;

calculating, by the microprocessor, a shift angle from the averaged normalized accelerometer data; and

adjusting, by the microprocessor, the normalized accelerometer data based on the calculated shift angle.

4. The method of claim 3 where recognizing by the microprocessor that the user is moving comprises comparing a smoothed power calculated from the normalized accelerometer data to a threshold.

5. The method of claim 1 where the tri-axial accelerometer is attached to the user on the user'"'"'s trunk, head, neck, or a limb.

6. The method of claim 1 further comprising, after creating by the microprocessor the normalized accelerometer data:

recognizing, by the microprocessor, that the normalized accelerometer data indicates the tri-axial accelerometer is upside-down; and

correcting, by the microprocessor, the normalized accelerometer data to account for the indication the tri-axial accelerometer is upside-down.

12. The method of claim 1 wherein analyzing at least the normalized accelerometer data and determining a movement and posture state of the user comprises directly identifying the movement and posture state from the normalized accelerometer data.

13. The method of claim 1 wherein analyzing at least the normalized accelerometer data and determining a movement and posture state of the user comprises indirectly identifying the movement state through movement state transitions.

14. The method of claim 1 wherein the movement and posture state include a status descriptor selected from the set of states including at least standing, sitting, lying, running, and walking.

15. The method of claim 1 wherein the movement and posture state include classification of posture quality.

16. The method of claim 1 further comprising providing sensory feedback to the user in real-time based on the determined movement and posture state.

7. A postural feedback apparatus comprising:

a tri-axial accelerometer configured to be attached to a user, the tri-axial accelerometer configured to;

capture first tri-axial accelerometer data over a first period of time while the user is moving as instructed, capture second tri-axial accelerometer data while the user is stationary, and capture third tri-axial accelerometer data at a third point in time; and

a microprocessor configured to;

average the captured first tri-axial accelerometer data,

create a first normalization matrix based on the averaged captured first tri-axial accelerometer data,

average the captured second tri-axial accelerometer data;

create a second normalization matrix based on the averaged captured second tri-axial accelerometer data;

create normalized accelerometer data by applying the first normalization matrix and the second normalization matrix to the captured third tri-axial accelerometer data; and

analyze at least the normalized accelerometer data and determining a movement and posture state of the user.

8. The apparatus of claim 7 where the microprocessor is further configured to:

calculate a smoothed power from the captured first tri-axial accelerometer data,

identify data in the captured first tri-axial accelerometer data which results in the calculated smoothed power being below a threshold; and

discard the identified data from the captured first tri-axial accelerometer data, prior to averaging the captured first tri-axial accelerometer data.

9. The apparatus of claim 7 where the microprocessor is further configured to:

recognize that the user is moving based on the normalized accelerometer data;

average the normalized accelerometer data;

calculate a shift angle from the averaged normalized accelerometer data; and

adjust the normalized accelerometer data based on the calculated shift angle.

10. The apparatus of claim 7 where the tri-axial accelerometer is attached to the user on the user'"'"'s trunk, head, neck, or a limb.

11. The apparatus of claim 7 where the microprocessor is further configured to:

recognize that the normalized accelerometer data indicates the tri-axial accelerometer is upside-down; and

correct the normalized accelerometer data to account for the indication that the tri-axial accelerometer is upside-down.

17. A method comprising:

capturing, by a tri-axial accelerometer attached to a user, first tri-axial accelerometer data over a first period of time while the user is moving at a first point in time;

averaging, by a microprocessor, the captured first tri-axial accelerometer data, wherein before averaging by the microprocessor the captured first tri-axial accelerometer data;

calculating, by the microprocessor, smoothed power from the captured first tri-axial accelerometer data;

identifying, by the microprocessor, data in the captured first tri-axial accelerometer data which results in the calculated power being below a threshold; and

discarding, by the microprocessor, the identified data from the captured first tri-axial accelerometer data;

creating, by the microprocessor, a first normalization matrix based on the averaged first tri-axial accelerometer data;

capturing, by the tri-axial accelerometer attached to the user, second tri-axial accelerometer data at a second point in time;

creating, by the microprocessor, first normalized accelerometer data by applying the first normalization matrix to the captured second tri-axial accelerometer data;

recognizing, by the microprocessor, that the user is moving at a second point in time;

averaging, by the microprocessor, the first normalized accelerometer data;

calculating, by the microprocessor, a shift angle from the averaged first normalized accelerometer data; and

adjusting, by the microprocessor, the first normalized accelerometer data based on the calculated shift angle; and

analyzing at least the first normalized accelerometer data and determining a movement and posture state of the user.

20. The method of claim 17 where the tri-axial accelerometer is attached to the user on the user'"'"'s trunk, head, neck, or a limb.

21. The apparatus of claim 17 wherein the microprocessor is further configured to provide sensory feedback to the user in real-time based on the determined movement and posture state.

18. A method comprising:

capturing, by a tri-axial accelerometer attached to a user, first tri-axial accelerometer data over a first period of time while the user is moving at a first point in time;

averaging, by a microprocessor, the captured first tri-axial accelerometer data;

creating, by the microprocessor, a first normalization matrix based on the averaged first tri-axial accelerometer data;

capturing, by the tri-axial accelerometer attached to the user, second tri-axial accelerometer data at a second point in time;

creating, by the microprocessor, normalized accelerometer data by applying the first normalization matrix to the captured second tri-axial accelerometer data;

after creating by the microprocessor the first normalized accelerometer data;

capturing, by the tri-axial accelerometer attached to the user, third tri-axial accelerometer data over a third period of time, while the user is stationary as instructed,

averaging, by the microprocessor, the captured third tri-axial accelerometer data,

creating, by the microprocessor, a second normalization matrix based on an averaged third tri-axial accelerometer data, and

creating, by the microprocessor, second normalized accelerometer data by applying the second normalization matrix to the normalized accelerometer data;

recognizing, by the microprocessor, that the user is moving at a second point in time;

averaging, by the microprocessor, the first normalized accelerometer data;

calculating, by the microprocessor, a shift angle from the averaged first normalized accelerometer data; and

adjusting, by the microprocessor, the first normalized accelerometer data based on the calculated shift angle; and

analyzing at least the first normalized accelerometer data and determining a movement and posture state of the user.

19. The method of claim 18 where recognizing by the microprocessor that the user is moving comprises comparing a smoothed power calculated from the first normalized accelerometer data to a threshold.

22. The method of claim 18 where the tri-axial accelerometer is attached to the user on the user'"'"'s trunk, head, neck, or a limb.

23. The apparatus of claim 18 wherein the microprocessor is further configured to provide sensory feedback to the user in real-time based on the determined movement and posture state.