Pedestrian Pace Estimation with Pace Change Updating

• US 20160334433A1
• Filed: 05/14/2015
• Published: 11/17/2016
• Est. Priority Date: 05/14/2015
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Kazemi, Pejman Lotfali
• Granted Patent: US 11,131,562 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 22/006 Pedometers

Abstract

Systems, methods and non-transitory, computer-readable mediums are disclosed for pedestrian pace estimation with pace change detection. In some implementations, a method comprises: receiving, by a processor of a mobile device, raw pedometer data from a pedometer included in or coupled to the mobile device; receiving, by the processor, raw GNSS data from a GNSS receiver included in or coupled to the mobile device; estimating, using a first filter implemented on the processor, a step frequency of a user wearing or holding the mobile device, the estimating including using the raw pedometer data; determining, by the processor, a pace change, the pace change determined from the estimated step frequency; responsive to the pace change, adapting by the processor, a bandwidth of a second filter implemented by the processor; and estimating, by the second filter, an estimated pace or speed of the user.

Claims

1. A method comprising:

receiving, by a processor of a mobile device, raw pedometer data from a pedometer included in or coupled to the mobile device;

receiving, by the processor, raw Global Navigation Satellite System (GNSS) data from a GNSS receiver included in or coupled to the mobile device;

estimating, using a first filter implemented on the processor, a step frequency of a user wearing or holding the mobile device, the estimating including using the raw pedometer data;

determining, by the processor, a pace change, the pace change determined from the estimated step frequency;

responsive to the pace change, adapting by the processor, a bandwidth of a second filter implemented by the processor; and

estimating, by the second filter, an estimated pace or speed of the user.

2. The method of claim 1, wherein the raw pedometer data is step count or step frequency and the raw GNSS data is speed or velocity.

3. The method of claim 1, wherein the pace change is determined by comparing estimated step frequency with a threshold value.

4. The method of claim 1, wherein the first and second filters are Kalman filters.

5. The method of claim 4, wherein the first Kalman filter is configured to estimate step count and step frequency using raw step counts and the second Kalman filter is configured to estimate GNSS speed.

6. The method of claim 5, wherein the second Kalman filter is configured to estimate GNSS speed and pedometer bias.

7. The method of claim 6, wherein adapting the bandwidth of the second filter further comprises:

replacing a process noise value in the second Kalman filter with a different process noise value.

8. The method of claim 7, wherein the different process noise value is used by the second Kalman filter for a time window and then reverts back to a previous process noise value or another process noise value.

9. The method of claim 1, further comprising:

determining a change in a motion activity classification; and

adapting the bandwidth of the second filter based on the determining.

10. The method of claim 1, wherein determining a pace change further comprises:

filtering, by a moving median filter, a set of step frequency estimates; and

determining the pace change based on a median estimated step frequency determined by the moving median filter.

11. A system comprising:

one or more processors;

one or more computer-readable mediums coupled to the one or more processors and configured to store instructions, which, when executed by the one or more processors, causes the one or more processors to perform operations comprising;

receiving, by a processor of a mobile device, raw pedometer data from a pedometer included in or coupled to the mobile device;

receiving, by the processor, raw Global Navigation Satellite System (GNSS) data from a GNSS receiver included in or coupled to the mobile device;

estimating, using a first filter implemented on the processor, a step frequency of a user wearing or holding the mobile device, the estimating including using the raw pedometer data;

determining, by the processor, a pace change, the pace change determined from the estimated step frequency;

responsive to the pace change, adapting by the processor, a bandwidth of a second filter implemented by the processor; and

estimating, by the second filter, an estimated pace or speed of the user.

12. The system of claim 11, wherein the raw pedometer data is step count or step frequency and the raw GNSS data is speed or velocity.

13. The system of claim 11, wherein the pace change is determined by comparing estimated step frequency with a threshold value.

14. The system of claim 11, wherein the first and second filters are Kalman filters.

15. The system of claim 14, wherein the first Kalman filter is configured to estimate step count and step frequency using raw step counts and the second Kalman filter is configured to estimate GNSS speed.

16. The system of claim 15, wherein the second Kalman filter is configured to estimate GNSS speed and pedometer bias.

17. The system of claim 16, wherein adapting the bandwidth of the second filter further comprises:

replacing a process noise value in the second Kalman filter with a different process noise value.

18. The system of claim 17, wherein the different process noise value is used by the second Kalman filter for a time window and then reverts back to a previous process noise value or another process noise value.

19. The system of claim 11, wherein the operations further comprise:

determining a change in a motion activity classification; and

adapting the bandwidth of the second filter based on the determining.

20. The system of claim 11, wherein determining a pace change further comprises:

filtering, by a moving median filter, a set of step frequency estimates; and

determining the pace change based on a median estimated step frequency determined by the moving median filter.