Human activity monitoring device with activity identification

• US 10,744,390 B1
• Filed: 02/03/2015
• Issued: 08/18/2020
• Est. Priority Date: 02/08/2007
• Status: Active Grant

• Current Assignee: DP Technologies, Inc.
• Original Assignee: DP Technologies, Inc.
• Inventors: Kahn, Philippe Richard, Kinsolving, Arthur, Christensen, Mark Andrew, Lee, Brian Y., Vogel, David
• Primary Examiner(s): Park, Hyun D
• Application Number:
  US14/613,355
• Time in Patent Office: 2,023 Days
• CPC Class Codes: A63B 2220/40 Acceleration
• CPC Class Codes: A63B 24/0062 Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
• CPC Class Codes: A63B 71/06 Indicating or scoring devices for games or players , or for other sports activities
• CPC Class Codes: G01C 22/006 Pedometers

Abstract

A method for monitoring human activity using an inertial sensor includes monitoring accelerations, identifying a current user activity from a plurality of user activities based on the accelerations, and counting periodic human motions appropriate to the current user activity.

Claims

1. A method of monitoring human activity using an inertial sensor in a device carried by a user, the method comprising:

monitoring, by the device, accelerations representing user movement of the user;

calculating a user movement based on a plurality of accelerations over time;

identifying one or more plurality of potential activities by matching the user movement to characteristics for each of the plurality of potential activities within a cadence window associated with the potential activities,

where the cadence window for an activity is a length of time between a most recent periodic human motion and a next periodic human motion for the activity, and is set when a first periodic human motion is recognized, and

where at least two of the potential activities have non-identical movement characteristics;

when there are a plurality of potential activities, counting movements for each of the plurality of potential activities, and removing a particular potential activity from the plurality of potential activities when the user movement does not match the particular potential activity;

identifying a current user activity from the plurality of potential activities based on the counted movements for the plurality of potential activities;

and

counting periodic human motions appropriate to the current user activity and communicating, by the device carried by the user, the counted periodic human motions appropriate to the current activity to the user.

2. The method of claim 1, wherein the plurality of user activities comprises one or more of the following:

walking, inline skating, bicycling, exercising on an elliptical machine, exercising on a rowing machine, and cross country skiing.

3. The method of claim 1, further comprising, wherein the count for the potential activities that are not the current activity are zeroed out when the current activity is identified.

4. The method of claim 1, further comprising:

placing the inertial sensor in a sleep mode when no periodic human motions are detected after a period of time.

5. The method of claim 1, wherein counting movements for each of the plurality of potential activities comprises:

permitting reentry to continue counting movements for each of the plurality of potential activities.

6. The method of claim 1, wherein the plurality of user activities comprises one or more of the following:

walking and bicycling.

7. An activity monitor comprising:

an inertial sensor to detect user movements;

a processor having a plurality of modes, the plurality of modes comprising;

an entry mode, monitoring data from the inertial sensor, to determine whether the user movements meet a plurality of entry conditions associated with a particular activity, of a plurality of potential activities, within a cadence window associated with the potential activities,

where the cadence window for an activity is a length of time between a most recent periodic human motion and a next periodic human motion for the activity, and is set when a first periodic;

human motion is recognized, and

where at least two of the potential activities have non-identical entry conditions;

an active mode, entered when the user movements meet the plurality of entry conditions for a particular activity, in the active mode the processor counting periodic human motions associated with the particular activity until a negative event occurs;

an exit mode, entered when the negative event occurs, the exit mode permitting reentry into the active mode to continue counting periodic human motions associated with the particular human activity, when the periodic human motions match characteristics associated with the particular activity; and

a mode of communicating the counted periodic human motions appropriate to the particular activity to the user via the activity monitor.

8. The activity monitor of claim 7, further comprising:

the processor to enter a sleep mode when no periodic human motions are detected in the exit mode.

9. The activity monitor of claim 8, further comprising:

the processor to enter the entry mode when periodic human motions are detected in the sleep mode.

10. The activity monitor of claim 7, wherein the negative event comprises not detecting the periodic human motions meeting criteria for the particular activity for a period.

11. The activity monitor of claim 7, wherein the count for the potential activities that are not the current activity are zeroed out when the current activity is identified.

12. The activity monitor of claim 7, wherein the plurality of user activities comprise one or more of the following:

walking, inline skating, bicycling, exercising on an elliptical machine, exercising on a rowing machine, and cross country skiing.

13. A method of identifying a particular activity for monitoring from among a plurality of potential activities comprising:

receiving, by a device carried by the user, motion data from an inertial sensor in the device carried by a user;

matching the motion data to a plurality of sets of criteria within a cadence window associated with the potential activities, each set of criteria associated with one the plurality of potential activities, in a processor,

where the cadence window for an activity is a length of time between a most recent periodic human motion and a next periodic human motion for the activity, and is set when a first periodic human motion is recognized, and

where at least two of the potential activities have non-identical sets of criteria;

identifying one or more of the plurality of potential activities whose criteria the motion data matches;

counting periodic human motions for each of the one or more plurality of potential activities, until the motion data matches only a particular activity;

identifying the particular activity as a current activity, and continuing to count the periodic human motions for the current activity; and

communicating, by the device carried by the user, the periodic human motions for the current activity to the user.

14. The method of claim 13, wherein the count for the potential activities that are not the current activity are zeroed out when the current activity is identified.

15. The method of claim 13, wherein the plurality of user activities comprise one or more of the following:

walking, inline skating, bicycling, exercising on an elliptical machine, exercising on a rowing machine, and cross country skiing.

16. The method of claim 13, further comprising:

placing the processor into a sleep mode when no periodic human motions are detected after a time.

17. The method of claim 16, further comprising:

moving the processor to an entry mode when periodic human motions are detected in a sleep mode.

18. The method of claim 16, further comprising:

stopping counting the periodic human motions for a particular potential activity when a negative event is detected for the particular potential activity.

19. The method of claim 18, wherein the negative event comprises not detecting the periodic human motions meeting criteria for the particular activity for a period.

20. The method of claim 13, wherein counting periodic human motions for each of the one or more plurality of potential activities comprises:

permitting reentry to continue counting periodic human motions for each of the one or more plurality of potential activities, until the motion data matches only a particular activity.