Gesture-based controls via bone conduction

• US 9,594,433 B2
• Filed: 11/05/2013
• Issued: 03/14/2017
• Est. Priority Date: 11/05/2013
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Baldwin, Christopher, Amento, Brian S.
• Primary Examiner(s): Ma, Calvin C
• Application Number:
  US14/072,126
• Publication Number:
  US 20150128094A1
• Time in Patent Office: 1,225 Days
• Field of Search: 345/173, 345/174, 340/539.12, 705/14.67
• US Class Current: 1/1
• CPC Class Codes: G06F 2203/014 Force feedback applied to GUI
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883

Abstract

Concepts and technologies are disclosed herein for utilizing bone conduction to detect gestures. According to one aspect, a device can generate a signal and send the signal to a sensor network that is connected to a user. The device can receive a modified signal from the sensor network. The modified signal can include the signal as modified by a body of the user. The device can compare the modified signal to the signal to determine a difference in a feature between the signal and the modified signal. The device can determine a gesture performed by the user based upon the difference in the feature between the signal and the modified signal.

Claims

1. A method comprising:

generating, by a device comprising a processor, a signal;

sending, by the device, the signal to a sensor network associated with a user, wherein the sensor network comprises a plurality of vibration sensors positioned at various locations on a body of the user;

receiving, by the device, a modified signal comprising the signal, received by at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through at least one bone of the body of the user, thereby modifying the signal to create the modified signal;

comparing, by the device, the modified signal to the signal to determine a difference in a feature between the signal and the modified signal, wherein the difference in the feature between the signal and the modified signal is associated with a pre-defined gesture that defines the difference in the feature as being indicative of a gesture performed by the user; and

determining, based upon the difference in the feature between the signal and the modified signal being associated with the pre-defined gesture, that the user performed the gesture.

2. The method of claim 1, further comprising:

generating instructions in response to the gesture performed by the user; and

sending the instructions to an application.

3. The method of claim 2, further comprising:

processing the instructions to determine an input to the application; and

performing, by the application executing on the device, a function in response to the input.

4. The method of claim 3, wherein the application provides native support for the gesture.

5. The method of claim 3, wherein the application maps the instructions to a native input of the application.

6. The method of claim 1, further comprising creating a user gesture profile based upon a physical attribute of the user, and wherein the user gesture profile comprises the pre-defined gesture.

7. The method of claim 6, further comprising performing a gesture learning process, and wherein creating the user gesture profile comprises creating the user gesture profile further based upon an output from the gesture learning process.

8. The method of claim 7, wherein the gesture learning process comprises:

generating a test signal;

sending the test signal to the sensor network;

prompting the user to perform the pre-defined gesture;

receiving a modified test signal comprising the test signal, received by the at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through the at least one bone of the body of the user, thereby modifying the test signal to create the modified test signal;

comparing the modified test signal to the test signal to determine a difference in a feature between the test signal and the modified test signal;

associating the difference in the feature between the test signal and the modified test signal with the pre-defined gesture; and

updating the user gesture profile accordingly.

9. The method of claim 1, wherein:

the gesture comprises a movement gesture;

generating the signal comprises generating a plurality of signals comprising the signal;

sending the signal to the sensor network comprises sending the plurality of signals to the sensor network in succession; and

receiving the modified signal comprises receiving a plurality of modified signals in succession, each of the plurality of modified signals being indicative of a frame of motion of the movement gesture.

10. A device comprising:

a processor; and

a memory that stores computer-readable instructions that, when executed by the processor, causes the processor to perform operations comprising

generating a signal,

sending the signal to a sensor network associated with a user, wherein the sensor network comprises a plurality of vibration sensors positioned at various locations on a body of the user,

receiving a modified signal comprising the signal, received by at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through at least one bone of the body of the user, thereby modifying the signal to create the modified signal,

comparing the modified signal to the signal to determine a difference in a feature between the signal and the modified signal, wherein the difference in the feature between the signal and the modified signal is associated with a pre-defined gesture that defines the difference in the feature as being indicative of a gesture performed by the user, and

determining, based upon the difference in the feature between the signal and the modified signal being associated with the pre-defined gesture, that the user performed the gesture.

11. The device of claim 10, wherein the operations further comprise:

generating instructions in response to the gesture performed by the user; and

sending the instructions to an application, where the application processes the instructions to determine an input and perform a function in response to the input.

12. The device of claim 11, where the application provides native support for the gesture or the application maps the instructions to a native input of the application.

13. The device of claim 10, wherein the operations further comprise creating a user gesture profile based upon a physical attribute of the user, and wherein the user gesture profile comprises the pre-defined gesture.

14. The device of claim 13, wherein the operations further comprise performing a gesture learning process, and wherein creating the user gesture profile comprises creating the user gesture profile further based upon an output from the gesture learning process.

15. The device of claim 14, wherein the gesture learning process comprises:

generating a test signal;

sending the test signal to the sensor network;

prompting the user to perform the pre-defined gesture;

receiving a modified test signal comprising the test signal, received by the at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through the at least one bone of the body of the user, thereby modifying the test signal to create the modified test signal;

comparing the modified test signal to the test signal to determine a difference in a feature between the test signal and the modified test signal;

associating the difference in the feature between the test signal and the modified test signal with the pre-defined gesture; and

updating the user gesture profile accordingly.

16. A computer-readable storage medium having instructions stored thereon that, when executed by a processor of a device, cause the device to perform operations comprising:

generating a signal;

sending the signal to a sensor network associated with a user, wherein the sensor network comprises a plurality of vibration sensors positioned at various locations on a body of the user;

receiving a modified signal comprising the signal, received by at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through at least one bone of the body of the user, thereby modifying the signal to create the modified signal;

comparing the modified signal to the signal to determine a difference in a feature between the signal and the modified signal, wherein the difference in the feature between the signal and the modified signal is associated with a pre-defined gesture that defines the difference in the feature as being indicative of a gesture performed by the user; and

determining, based upon the difference in the feature between the signal and the modified signal being associated with the pre-defined gesture, that the user performed the gesture.

17. The computer-readable storage medium of claim 16, wherein the operations further comprise:

generating instructions in response to the gesture performed by the user; and

sending the instructions to an application, where the application processes the instructions in response to the gesture to determine an input and performs a function in response to the input.

18. The computer-readable storage medium of claim 16, wherein the operations further comprise:

performing a gesture learning process; and

creating a user gesture profile based upon a physical attribute of the user and an output of the gesture learning process.

19. The computer-readable storage medium of claim 18, wherein the gesture learning process comprises:

generating a test signal;

sending the test signal to the sensor network;

prompting the user to perform the pre-defined gesture;

receiving a modified test signal comprising the test signal, received by the at least one vibration sensor of the plurality of vibration sensors from the device and propagated by the at least one vibration sensor through the at least one bone of the body of the user, thereby modifying the test signal to create the modified test signal;

comparing the modified test signal to the test signal to determine a difference in a feature between the test signal and the modified test signal;

associating the difference in the feature between the test signal and the modified test signal with the pre-defined gesture; and

updating the user gesture profile accordingly.

20. The computer-readable storage medium of claim 16, wherein:

the gesture comprises a movement gesture;

generating the signal comprises generating a plurality of signals comprising the signal;

sending the signal to the sensor network comprises sending the plurality of signals to the sensor network in succession; and

receiving the modified signal comprises receiving a plurality of modified signals in succession, each of the plurality of modified signals being indicative of a frame of motion of the movement gesture.