Human activity monitoring device

1. A method of monitoring human activity using an inertial sensor, comprising:

assigning a dominant axis with respect to gravity based on an orientation of the inertial sensor;

detecting a change in the orientation of the inertial sensor and updating the dominant axis based on the change; and

counting periodic human motions by monitoring accelerations relative to the dominant axis by counting the periodic human motions when accelerations showing a motion cycle that meets motion criteria is detected within a cadence window; and

updating the cadence window as actual cadence changes.

2. The method of claim 1 , further comprising:

using acceleration measurements along only the dominant axis to count steps.

3. The method of claim 1 , wherein at least one of the motion criteria is a dynamic motion criterion, the dynamic motion criterion updated to reflect current conditions.

4. The method of claim 3 , wherein the dynamic motion criteria includes at least a lower threshold, wherein the lower threshold is adjusted based on at least one of a rolling average of accelerations and the orientation of the inertial sensor.

5. A method of monitoring human activity using an inertial sensor, comprising:

buffering a plurality of periodic human motions, each periodic human motion comprising a motion cycle;

identifying a number of periodic human motions within an appropriate cadence window;

counting each of the periodic human motions to enable the monitoring of human activity; and

updating the cadence window as a cadence of the motion cycle changes.

6. The method of claim 5 , further comprising:

switching the device from the active mode to the non-active mode when a number of expected periodic human motions are not identified in the appropriate cadence windows.

7. The method of claim 5 , further comprising:

switching from a sleep mode to the non-active mode of operation when an acceleration is detected.

8. The method of claim 5 , wherein prior to identifying, the inertial sensor is in a non-active mode, and wherein the non-active mode comprises running the device in one of an exit mode and an entry mode.

9. The method of claim 8 , wherein:

a requirement for switching the device from the exit mode to an active mode is lower than a requirement for switching the device from the entry mode to the active mode.

10. An inertial sensor based device, comprising:

a dominant axis logic to determine an orientation of a device with respect to gravity, to assign a dominant axis, and to update the dominant axis when the orientation of the device changes; and

a counting logic to count periodic human motions by monitoring accelerations relative to the dominant axis by counting the periodic human motions when accelerations showing a motion cycle that meets motion criteria is detected within a cadence window; and

a cadence logic to update the cadence window as actual cadence changes.

11. The device of claim 10 , wherein:

the counting logic uses acceleration measurements along only the dominant axis to count steps.

12. The device of claim 10 , further comprising:

the cadence logic to update a dynamic cadence window; and

the counting logic to count a periodic human motion when an acceleration measurement that meets motion criteria is taken within the cadence window.

13. The device of claim 10 , further comprising:

a comparator, to compare measurements of acceleration to dynamic motion criteria, the dynamic motion criteria updated to reflect current conditions; and

the counting logic to count a periodic human motion when the measurements of acceleration satisfy the dynamic motion criteria.

14. A non-transitory machine readable medium containing executable computer program instructions which, when executed by a processing system, cause said system to perform a method for:

assigning a dominant axis with respect to gravity based on an orientation of the inertial sensor;

detecting a change in the orientation of the inertial sensor and update the dominant axis based on the change; and

counting periodic human motions by monitoring accelerations relative to the dominant axis by counting the periodic human motions when accelerations showing a motion cycle that meets motion criteria is detected within a cadence window; and

updating the cadence window as actual cadence changes.

15. The non-transitory machine readable medium containing executable computer program instructions of claim 14 , which, when executed by the processing system, cause said system to perform the method further for:

using acceleration measurements along only the dominant axis to count steps.

16. The non-transitory machine readable medium containing executable computer program instructions of claim 14 , which, when executed by the processing system, cause said system to perform the method further for:

switching the device from an active mode to a non-active mode when a number of expected periodic human motions are not identified in the appropriate cadence windows.

17. The non-transitory machine readable medium containing executable computer program instructions of claim 14 , which, when executed by the processing system, cause said system to perform the method further for:

maintaining a cadence window, wherein the cadence window is updated as an actual cadence changes; and

counting a periodic human motion when an acceleration measurement that meets motion criteria is within the cadence window.

18. The non-transitory machine readable medium containing executable computer program instructions of claim 17 , wherein at least one of the motion criteria is a dynamic motion criterion, the dynamic motion criterion updated to reflect current conditions.

19. The non-transitory machine readable medium containing executable computer program instructions of claim 14 , wherein the dynamic motion criteria includes at least a lower threshold, wherein the lower threshold is adjusted based on at least one of a rolling average of accelerations and the orientation of the inertial sensor.