Half step frequency feature for reliable motion classification

Patent metadata

Field	Value
Publication number	US-9622687-B2
Application number	US-201414476482-A
Country	US
Kind code	B2
Filing date	Sep 3, 2014
Priority date	Sep 5, 2013
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

Disclosed is an apparatus and method for classifying a motion state of a mobile device. In one embodiment, accelerometer data representing acceleration components along orthogonal x, y, and z axes of the mobile device are collected. A presence or absence of a half-step frequency relationship between the accelerometer data is determined. Last, the motion state of the device is determined based at least in part on the presence or absence of the half-step frequency relationship.

First claim

What is claimed is:

1. A method of classifying a motion state of a mobile device comprising:
collecting accelerometer data representing acceleration components along orthogonal x, y, and z axes of the mobile device;
determining a presence or absence of a half-step frequency relationship between the accelerometer data; and
determining the motion state of the device based at least in part on the presence or absence of the half-step frequency relationship.

2. The method of claim 1 , wherein the determining of the motion state comprises determining a walk/run state based at least in part on the presence of the half-step frequency relationship.

3. The method of claim 2 , further comprising determining an additional activity the user is performing while walking/running.

4. The method of claim 1 , further comprising determining whether the user is walking or running based at least in part on an amplitude in the accelerometer data.

5. The method of claim 1 , further comprising transforming the accelerometer data from a time domain into a frequency domain, wherein the determining of the presence or absence of the half-step frequency relationship is performed in the frequency domain, and wherein accelerometer data are collected over a time window in the time domain.

6. The method of claim 5 , wherein the transforming of the accelerometer data from the time domain into the frequency domain is performed using a Fast Fourier Transform (FFT).

7. The method of claim 5 , wherein the time window is at least three seconds in duration.

8. The method of claim 1 , wherein the determining of the presence or absence of the half-step frequency relationship occurs in a time domain.

9. An apparatus for classifying a motion state of a mobile device comprising:
a memory; and
a processor configured to:
collect accelerometer data representing acceleration components along orthogonal x, y, and z axes of the mobile device,
determine a presence or absence of a half-step frequency relationship between the accelerometer data, and
determine the motion state of the device based at least in part on the presence or absence of the half-step frequency relationship.

10. The apparatus of claim 9 , wherein the determining of the motion state comprises determining a walk/run state based at least in part on the presence of the half-step frequency relationship.

11. The apparatus of claim 10 , wherein the processor is further configured to determine an additional activity the user is performing while walking/running.

12. The apparatus of claim 9 , wherein the processor is further configured to determine whether the user is walking or running based at least in part on an amplitude in the accelerometer data.

13. The apparatus of claim 9 , wherein the processor is further configured to:
transform the accelerometer data from a time domain into a frequency domain, wherein the determining of the presence or absence of the half-step frequency relationship is performed in the frequency domain, and
wherein accelerometer data are collected over a time window in the time domain.

14. The apparatus of claim 13 , wherein the transforming of the accelerometer data from the time domain into the frequency domain is performed using a Fast Fourier Transform (PIT).

15. The apparatus of claim 13 , wherein the time window is at least three seconds in duration.

16. The apparatus of claim 9 , wherein the determining of the presence or absence of the half-step frequency relationship occurs in a time domain.

17. An apparatus for classifying a motion state of a mobile device comprising:
means for collecting accelerometer data representing acceleration components along orthogonal x, y, and z axes of the mobile device;
means for determining a presence or absence of a half-step frequency relationship between the accelerometer data; and
means for determining the motion state of the device based at least in part on the presence or absence of the half-step frequency relationship.

18. The apparatus of claim 17 , wherein the means for determining the motion state comprises means for determining a walk/run state based at least in part on the presence of the half-step frequency relationship.

19. The apparatus of claim 18 , further comprising means for determining an additional activity the user is performing while walking/running.

20. The apparatus of claim 17 , further comprising means for determining whether the user is walking or running based at least in part on an amplitude in the accelerometer data.

21. The apparatus of claim 17 , further comprising means for transforming the accelerometer data from a time domain into a frequency domain, wherein the determining of the presence or absence of the half-step frequency relationship is performed in the frequency domain, and
wherein accelerometer data are collected over a time window in the time domain.

22. The apparatus of claim 21 , wherein the transforming of the accelerometer data from the time domain into the frequency domain is performed using a Fast Fourier Transform (PIT).

23. The apparatus of claim 21 , wherein the time window is at least three seconds in duration.

24. The apparatus of claim 17 , wherein the determining of the presence or absence of the half-step frequency relationship occurs in a time domain.

25. A non-transitory computer-readable medium including code which, when executed by a processor, causes the processor to perform a method comprising:
collecting accelerometer data representing acceleration components along orthogonal x, y, and z axes of the mobile device;
determining a presence or absence of a half-step frequency relationship between the accelerometer data; and
determining the motion state of the device based at least in part on the presence or absence of the half-step frequency relationship.

26. The non-transitory computer-readable medium of claim 25 , wherein the determining of the motion state comprises determining a walk/run state based at least in part on the presence of the half-step frequency relationship.

27. The non-transitory computer-readable medium of claim 26 , further comprising code for determining an additional activity the user is performing while walking/running.

28. The non-transitory computer-readable medium of claim 25 , further comprising code for determining whether the user is walking or running based at least in part on an amplitude in the accelerometer data.

29. The non-transitory computer-readable medium of claim 25 , further comprising code for transforming the accelerometer data from a time domain into a frequency domain, wherein the determining of the presence or absence of the half-step frequency relationship is performed in the frequency domain, and
wherein accelerometer data are collected over a time window in the time domain.

30. The non-transitory computer-readable medium of claim 29 , wherein the transforming of the accelerometer data from the time domain into the frequency domain is performed using a Fast Fourier Transform (FFT).

31. The non-transitory computer-readable medium of claim 29 , wherein the time window is at least three seconds in duration.

32. The non-transitory computer-readable medium of claim 25 , wherein the determining of the presence or absence of the half-step frequency relationship occurs in a time dom

Assignees

• Qualcomm Inc

Inventors

• Zhang Lei
• Yang Sichao
• Sadasivam Shankar
• Subramanian Sundar
• Wu Xinzhou

Classifications

• G01P13/00

  Indicating or recording presence, absence, or direction, of movement (electric switches H01H; counting moving objects G06M7/00) · CPC title

• G01P15/00

  Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration · CPC title

• A61B5/1118 Primary

  Determining activity level · CPC title

• G01C22/006 Primary

  Pedometers · CPC title

• A61B5/1126

  using a particular sensing technique · CPC title