METHOD FOR STEP DETECTION AND GAIT DIRECTION ESTIMATION

• US 20130311134A1
• Filed: 03/14/2013
• Published: 11/21/2013
• Est. Priority Date: 05/18/2012
• Status: Active Grant

• Current Assignee: TRX Systems, Inc.
• Original Assignee: TRX Systems, Inc.
• Inventors: Kordari, Kamiar, Funk, Benjamin, Napora, Jared, Verma, Ruchika, Teolis, Carole, Young, Travis
• Granted Patent: US 8,930,163 B2
• Time in Patent Office: Days
• US Class Current: 702/160
• CPC Class Codes: G01C 21/10 by using measurements of speed or acceleration G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 22/00 Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G01C 25/005 initial alignment, calibration or starting-up of inertial devices
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544

Abstract

A method for detecting a human'"'"'s steps and estimating the horizontal translation direction and scaling of the resulting motion relative to an inertial sensor is described. When a pedestrian takes a sequence of steps the displacement can be decomposed into a sequence of rotations and translations over each step. A translation is the change in the location of pedestrian'"'"'s center of mass and a rotation is the change along z-axis of the pedestrian'"'"'s orientation. A translation can be described by a vector and a rotation by an angle.

Claims

1. A computer-implemented method for detecting the steps of a person and estimating the person'"'"'s gait direction, comprising the steps of:

collecting accelerometer data from a device worn by the person for a x-axis, a y-axis and z-axis of motion of the person and storing the accelerometer data in a non-transitory memory of a computer having a processor;

utilizing the processor to remove tilt data from the accelerometer data a for the x-axis, the y-axis and the z-axis to produce first improved accelerometer data and storing the first improved accelerometer data in the memory;

utilizing the processor to remove gravitation acceleration from the first improved accelerometer data for the z-axis to produce second improved accelerometer data and storing the second improved accelerometer data in the memory;

utilizing the processor to filter the second improved accelerometer data and the first improved accelerometer data for the x-axis and the y-axis to remove additional bias and high frequency noise and to produce a filtered accelerometer data for the x-axis, the y-axis, and the z-axis;

utilizing the processor to calculate a hip elevation estimate based on the filtered accelerometer data for the z-axis and storing the hip elevation estimate in the memory;

utilizing the processor to correct the hip elevation estimate if the hip elevation estimate drifts away from a mean over time;

utilizing the processor to find a local minima and a local maxima to detect each step by the person and storing the local minima and the local maxima in the memory;

utilizing the processor to classify the person'"'"'s gait as a level gait, an up gait, or a down gait based on at least the local minima and the local maxima of the device;

utilizing the processor to find an x-displacement along the x-axis and a y-displacement along the y-axis for each step by the person based on the filtered accelerometer data for the x-axis and the y-axis and storing the x-displacement and the y-displacement in the memory;

calculating a 2D movement displacement for each stride by the person based at least on the x-displacement and the y-displacement;

if the person'"'"'s gait is classified as the up gait or the down gait, calculating the elevation change of the person and storing the elevation change in the memory;

calculating a path of the person based at least on the 2D movement displacement and the elevation change and storing the path in the memory; and

updating the path in the memory, if the path had previously been calculated, to estimate the person'"'"'s gait direction.

2. The computer-implemented method as recited in claim 1, wherein the device is a smartphone that includes an accelerometer.

3. The computer-implemented method as recited in claim 1, wherein the accelerometer data is sampled at a frequency greater than twice a Nyquist frequency for the device.

4. The computer-implemented method as recited in claim 1, wherein the accelerometer data includes x-axis, v-axis and z-axis data for the device, and wherein the step of utilizing the processor to remove tilt includes the steps of:

establishing a ground frame oriented around the device with the z-axis up and down from the device, the x-axis is right and left of the device and the y-axis is forward and back of the device;

determining pitch data and roll data based on x-axis, y-axis and z-axis data relative to the ground frame; and

determining the tilt data based on the pitch data and roll data of the device

5. The computer-implemented method as recited in claim 1, wherein the device further includes a gyroscope adding to the x-axis, y-axis and z-axis data for the device.

6. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to remove gravitation acceleration is based on ā

_z=a_z−

g, where a_z is improved accelerometer data for the z-axis, g is gravity, and z_z is improved accelerometer data for the z-axis minus gravitational acceleration.

7. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to calculate the hip elevation includes a double integration of the filtered accelerometer data for the z-axis.

8. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to correct the hip elevation includes correcting the hip elevation each time a new value is calculated for the hip elevation.

9. The computer-implemented method as recited in claim 1, wherein local minima occurs after each heal strike and wherein the local maxima occurs after each passive position.

10. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to find the local minima and the local maxima includes the step of utilizing the processor to reduce extraneous detections by determining if there are any neighboring minima within a sample window of n samples before a local minima and n samples after each local minima, and not counting any neighboring minima within the sample window as a local minima. The computer-implemented method as recited in claim 1, wherein the processor utilizes a neural network to classify the person'"'"'s gait.

14. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to find the x-displacement and the y-displacement is performed in a time interval between the local minima and the local maxima for each step.

15. The computer-implemented method as recited in claim 1, further comprising the step of utilizing the processor to determine a translation direction for each step, wherein a most frequent direction of translation is assumed to be forward, and wherein the ground frame is corrected to the y-axis.

16. The computer-implemented method as recited in claim 1, further comprising the step of utilizing the processor to determine a translation direction for each step, wherein a most frequent direction of translation is determined by assigning each possible direction of motion based on each step to a bin for the direction of motion and the bin with the highest frequency is considered the most frequent direction of translation.

17. The computer-implemented method as recited in claim 1, further comprising the step of utilizing the processor to determine a translation direction for each step, and further comprising the step of detecting a transition corresponding to an abrupt change in orientation of the device and discontinuing the step of utilizing the processor to determine a translation direction for each step until the transition has completed.

18. The computer-implemented method as recited in claim 1, wherein the step of utilizing the processor to remove tilt data further includes determining an accelerometer estimate of pitch and yaw and an gyroscope estimate of pitch and yaw and combining the accelerometer estimate and the gyroscope estimate with a spherical linear interpolation.

12. The computer-implemented method as recited in claim 11, wherein the processor classifies the person'"'"'s gait on a per step basis.

13. The computer-implemented method as recited in claim 12, wherein the step of utilizing the processor to classify the person'"'"'s gait includes the steps of:

inputting to the neural network n values of each of the x-axis, y-axis and x-axis components of angle vectors for each step;

inputting to the neural network n values of each of the x-axis, y-axis and x-axis components of velocity vectors for each step;

inputting to the neural network a minimum and a maximum acceleration amplitude difference over each step;

inputting to the neural network an orientation vector at the end of each step; and

inputting to the neural network an index where a magnitude of the x-axis and y-axis plane acceleration achieves a minimum value for each step.