Method for sensor orientation invariant gait analysis using gyroscopes

1. A method for invariant gait analysis using gyroscope data comprising:

obtaining, from at least one gyroscope, at least one pair of raw data measurements;

obtaining, from said at least one pair of raw data measurements, at least two 3D rotation vectors;

obtaining, from said at least one gyroscope, at least a second pair of raw data measurements;

obtaining, from said at least a second pair of raw data measurements, at least a second set of two 3D rotation vectors;

determining, from said at least two 3D rotation vectors and said at least a second set of two 3D rotation vectors, Gait Dynamics Images (GDIs);

determining sequences by matching features of said GDIs to sequences; and

outputting identification and or classification of features from said determined sequences,

whereby said pairs of raw measurements are used to factor out orientation, providing a motion representation which is both invariant to sensor orientation changes and highly discriminative, thereby providing high-performance gait analysis.

2. The method of claim 1 , wherein said at least one gyroscope comprises a second gyroscope, wherein said at least a second pair of raw data measurements is obtained from said second gyroscope.

3. The method of claim 1 , wherein said 3D rotation vectors are rotation rate or rotation angle integrated over a fixed-length time interval.

4. The method of claim 1 , wherein said GDI is a generalized GDI through applying a linear operator to said raw data measurements.

5. The method of claim 1 , comprising a pair of motion vectors from times t1 and t2.

6. The method of claim 1 wherein said features comprise entries and or rows and or columns of said GDI images and features derived from said GDIs.

7. The method of claim 1 , wherein inertial measurement comprises Direction Cosine Matrix (DCM) Inertial Measurement Unit (IMU) theory, wherein measurement intervals comprise a small time dt.

8. The method of claim 1 , wherein an inner product between a pair of the 3D rotation axis vectors is invariant to sensor rotation.

9. The method of claim 1 , wherein said GDIs encode both dynamics for a time series and local interactions.

10. The method of claim 1 , wherein quaternions are computed to represent rotation changes.

11. The method of claim 1 , wherein a 3D rotation is represented using three Euler angles.

12. The method of claim 1 , wherein 3D rotation is alternatively represented using a rotation axis vector and a rotation angle around an axis.

13. The method of claim 1 , wherein a first row of an inner product GDI image are inner products of observation pairs with time lag zero.

14. The method of claim 13 , wherein remaining rows contain interactions at varying time lags that contribute to additional discriminating information of gait dynamics.

15. A device for invariant gait analysis comprising:

providing at least one gyroscope;

obtaining, from said at least one gyroscope, at least a first pair of raw data measurements;

obtaining, from said at least a first pair of raw data measurements, at least two 3d rotation vectors;

obtaining, from said at least one gyroscope, at least a second pair of raw data measurements;

obtaining, from said at least a second pair of raw data measurements, at least a second set of two 3D rotation vectors;

determining, from said at least two 3D rotation vectors and said at least a second set of two 3D rotation vectors, Gait Dynamics Images (GDIs);

determining sequences by matching corresponding images of said GDIs to sequences; and

outputting gait biometrics and or activity classification.

16. The device of claim 15 , wherein said at least one gyroscope is a three-axis gyroscope measuring rotation rate along three orthogonal axes of said gyroscope.

17. The device of claim 15 , wherein said at least one pair of raw data measurements and said at least a second pair of raw data measurements are measured at arbitrary locations.

18. The device of claim 15 , wherein measurements taken from said at least one gyroscope are sampled at regular time intervals.

19. The device of claim 18 , wherein said regular time intervals are longer than an average gait cycle and may depend on application, whereby all contexts within a gait cycle when computing GDIs are preserved.

20. A system for invariant gait analysis comprising:

providing one or two three-axis gyroscopes;

obtaining, from said one or two gyroscopes, at least one pair of raw data measurements;

obtaining, from said at least one pair of raw data measurements, at least two 3D rotation vectors;

obtaining, from said one or two gyroscopes, at least a second pair of raw data measurements;

obtaining, from said at least a second pair of raw data measurements, at least a second set of two 3D rotation vectors;

determining, from said at least two 3D rotation vectors and said at least a second set of two 3D rotation vectors, Gait Dynamics Images (GDIs), wherein said 3D rotation vectors are rotation angle integrated over a fixed-length time interval, said time interval being longer than an average gait cycle, whereby all contexts within a gait cycle when computing GDIs are preserved;

determining sequences by matching corresponding images of said GDIs to sequences; and

outputting gait biometrics and activity classification,

whereby said pairs of raw data measurements are used to factor out orientation, providing a motion representation which is both invariant to sensor orientation changes and highly discriminative, thereby providing high-performance gait analysis for biometric authentication, activity monitoring, and fall prediction.