Controlling a wearable device using gestures

Patent metadata

Field	Value
Publication number	US-2016282947-A1
Application number	US-201514669387-A
Country	US
Kind code	A1
Filing date	Mar 26, 2015
Priority date	Mar 26, 2015
Publication date	Sep 29, 2016
Grant date	—

Abstract

One embodiment provides a method including: receiving, at a wearable device, non-image data from at least one sensor operatively coupled to the wearable device, wherein the non-image data is based upon a gesture performed by a user; identifying, using a processor, the gesture performed by a user using the non-image data; and performing an action based upon the gesture identified. Other aspects are described and claimed.

First claim

What is claimed is:

1 . A method, comprising:
receiving, at a wearable device, non-image data from at least one sensor operatively coupled to the wearable device, wherein the non-image data is based upon a gesture performed by a user; identifying, using a processor, the gesture performed by a user using the non-image data; and performing an action based upon the gesture identified.

2 . The method of claim 1 , wherein the non-image data comprises at least one of: electromyography data, pressure data, and inertial data.

3 . The method of claim 1 , wherein the identifying comprises associating the non-image data with a gesture.

4 . The method of claim 1 , wherein the non-image data comprises an electromyography data stream, a pressure sensor data stream, and an inertial data stream, and wherein the identifying comprises using each of the data streams to extract at least one feature of the gesture.

5 . The method of claim 4 , further comprising aggregating the data streams into a single nonlinear model.

6 . The method of claim 5 , wherein the aggregating comprises using an unscented Kalman filter.

7 . The method of claim 1 , wherein the non-image data comprises an electromyography data stream, a pressure sensor data stream, and an inertial data stream and wherein the identifying comprises combining the data streams.

8 . The method of claim 7 , wherein the identifying comprises classifying the combined data streams using at least one support vector machine.

9 . The method of claim 1 , wherein the performing an action comprises controlling an alternate device using the gesture identified.

10 . The method of claim 1 , further comprising associating the gesture with an action.

11 . A wearable device, comprising:
a wearable housing; a display screen; at least one sensor; a processor operatively coupled to the display screen and the at least one sensor and housed by the wearable housing; and a memory that stores instructions executable by the processor to: receive non-image data from the at least one sensor, wherein the non-image data is based upon a gesture performed by a user; identify the gesture performed by a user using the non-image data; and perform an action based upon the gesture identified.

12 . The wearable device of claim 11 , wherein the non-image data comprises at least one of: electromyography data, pressure data, and inertial data.

13 . The wearable device of claim 11 , wherein to identify comprises associating the non-image data with a gesture.

14 . The wearable device of claim 11 , wherein the non-image data comprises an electromyography data stream, a pressure sensor data stream, and an inertial data stream, and wherein to identify comprises using each of the data streams to extract at least one feature of the gesture.

15 . The wearable device of claim 14 , wherein the instructions are further executable by the processor to aggregate the data streams into a single nonlinear model.

16 . The wearable device of claim 15 , wherein to aggregate comprises using an unscented Kalman filter.

17 . The wearable device of claim 11 , wherein the non-image data comprises an electromyography data stream, a pressure sensor data stream, and an inertial data stream and wherein to identify comprises combining the data streams.

18 . The wearable device of claim 17 , wherein to identify comprises classifying the combined data streams using at least one support vector machine.

19 . The wearable device of claim 11 , wherein to perform an action comprises controlling an alternate device using the gesture identified.

20 . A product, comprising:
a storage device that stores code executable by a processor, the code comprising: code that receives, at a wearable device, non-image data from at least one sensor operatively coupled to the wearable device, wherein the non-image data is based upon a gesture performed by a user; code that identifies the gesture performed by a user using the non-image data; and code that performs an action based upon the gesture identified.

Assignees

• Lenovo Singapore Pte Ltd

Inventors

• Schwarz David Alexander
• Qian Ming
• Bula Geoffrey Simon
• Nicholson John Weldon

Classifications

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · 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

• G06V40/28

  Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113) · CPC title

• G06F1/163

  Wearable computers, e.g. on a belt · CPC title

• G06F2203/0381

  Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer · CPC title