Gesture recognition

Patent metadata

Field	Value
Publication number	US-11243611-B2
Application number	US-201414453997-A
Country	US
Kind code	B2
Filing date	Aug 7, 2014
Priority date	Aug 7, 2013
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

A wrist-worn athletic performance monitoring system, including a gesture recognition processor configured to execute gesture recognition processes. Interaction with the performance monitoring system may be based, at least in part, on gestures performed by the user, and offer an alternative to making selections on the performance monitoring system using physical buttons, which may be cumbersome and/or inconvenient to use while performing an athletic activities. Additionally, recognized gestures may be used to select one or more operational modes for the athletic performance monitoring systems such that a reduction in power consumption may be achieved.

First claim

We claim:

1. A computer-implemented method of operating a device comprising a processor, the method comprising:
entering the device into a training mode and while the device is in the training mode:
prompting, by the processor, a user to perform, in succession, at least a first repetition of a training gesture and second repetition of the training gesture;
during performance of the at least the first repetition of the training gesture and second repetition of the training gesture:
receiving, by the processor and from at least one of one or more sensors associated with the device, first raw user acceleration data associated with the performance of the at least the first repetition of the training gesture and second repetition of the training gesture;
sampling, by the processor and at a plurality of different sampling rates including a first sampling rate, the first raw user acceleration data associated with the training gesture;
identifying, by the processor and from the first raw user acceleration data sampled at the first sampling rate, one or more characteristics common between the at least the first repetition of the training gesture and second repetition of the training gesture; and
identifying, by the processor and based on sampling the first raw user acceleration data at the plurality of different sampling rates, a second sampling rate, of the plurality of different sampling rates, that is less than the first sampling rate and at which the one or more common characteristics are still identified as if the first raw user acceleration data was sampled at the first sampling rate, wherein the second sampling rate is associated with reduced power consumption by the processor; and

storing the training gesture as a first gesture of a plurality of gestures and storing the second sampling rate together with the one or more common characteristics identified from the first raw user acceleration data;

entering the device into a first operational mode that samples data at the first sampling rate; and
while the device is in the first operational mode:
receiving, by the processor and from the at least one of the one or more sensors, second raw user acceleration data sampled at the first sampling rate, wherein the second raw user acceleration data represents movement of an appendage of the user;
classifying, by the processor, at least a first portion of the second raw user acceleration data into a first athletic category, of a plurality of athletic activity categories, being performed by the user;
identifying, from at least a second portion of the second raw user acceleration data, the stored one or more common characteristics, wherein the at least the second portion of the second raw user acceleration data is different from the at least the first portion of the second raw user acceleration data;
recognizing, by the processor and based on identifying the stored one or more common characteristics, the at least the second portion of the second raw user acceleration data as the first gesture of the plurality of gestures;
based on the first athletic category and based on the recognized first gesture, entering a second operational mode of the device that samples data from an accelerometer, of the one or more sensors, at the second sampling rate to reduce power consumption by the processor; and
while in the second operational mode,
sampling additional raw user acceleration data, received from the at least one of the one or more sensors and classified into the first athletic category, at the second sampling rate.

2. The computer-implemented method of claim 1 , wherein the at least the second portion of the second raw user acceleration data is recognized as the first gesture further based on a motion pattern of the device.

3. The computer-implemented method of claim 1 , wherein the at least the second portion of the second raw user acceleration data is recognized as the first gesture further based on a pattern of touches of the device by the user.

4. The computer-implemented method of claim 3 , wherein the pattern of touches comprises a series of taps of the device by the user.

5. The computer-implemented method of claim 1 , wherein the at least the second portion of the second raw user acceleration data is recognized as the first gesture further based on an orientation of the device.

6. The computer-implemented method of claim 1 , wherein the at least the second portion of the second raw user acceleration data is recognized as the first gesture further based on a proximity of the device to a beacon.

7. The computer-implemented method of claim 6 , wherein the device is a first sensor device, and the beacon is associated with a second device worn by a second user.

8. The computer-implemented method of claim 6 , wherein the beacon is associated with a location, and the device is registered at the location based on the proximity of the device to the beacon.

9. The computer-implemented method of claim 1 , further comprising:
comparing a first value of the at least the second portion of the second raw user acceleration data to a plurality of threshold values, wherein recognizing the at least the second portion of the second raw user acceleration data as the first gesture is further based upon a determination that the first value of the at least the second portion of the second raw user acceleration data corresponds to a first threshold value of the plurality of threshold values.

10. The computer-implemented method of claim 1 , wherein the first sampling rate is an upper sampling rate associated with the processor.

11. The computer-implemented method of claim 1 , wherein classifying the at least the first portion of the second raw user acceleration data into the first athletic category comprises:
calculating, based on the at least the first portion of the second raw user acceleration data, a quantity of steps taken by the user; and
classifying the at least the first portion of the second raw user acceleration data into the first athletic category based on the quantity of steps taken by the user.

12. The computer-implemented method of claim 1 , wherein the one or more common characteristics identified from the first raw user acceleration data represents a gesture sample, and wherein the gesture sample is further stored with one or more instructions that cause the device to execute one or more processes when the gesture sample is recognized.

13. A unitary apparatus comprising:
one or more sensors;
a processor;
a non-transitory, computer-readable medium comprising computer-executable instructions that, when executed by the processor, cause the apparatus to:
enter into a training mode and while in the training mode:
prompt a user to perform, in succession, at least a first repetition of a training gesture and a second repetition of the training gesture;
during performance of the at least first repetition of the training gesture and second repetition of the training gesture:
receive, from at least one of the one or more sensors, first raw user acceleration data associated with the performance of the at least the first repetition of the training gesture and second repetition of the training gesture;
sample, at a plurality of different sampling rates including a first sampling rate, the first raw user acceleration data associated with the training gesture;
identify, from the first raw user acceleration data sampled at the first sampling rate, one or more characteristics common between the at least the first repetition of the training gesture and second repetition of the training gesture; and
identify, based on sampling the first raw user acceleration data at

Assignees

• Nike Inc

Inventors

• Goel Manan
• Cummings Kate
• Laigar Peter
• Switzer David
• Imlay Sebastian
• Lapinsky Michael

Classifications

• G06V10/147

  Details of sensors, e.g. sensor lenses (fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19) · CPC title

• G06F1/3231

  Monitoring the presence, absence or movement of users · CPC title

• G06V40/23

  Recognition of whole body movements, e.g. for sport training · CPC title

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06F3/011

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title