Tilt gesture detection

• US 9,354,709 B1
• Filed: 06/17/2014
• Issued: 05/31/2016
• Est. Priority Date: 06/17/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Heller, Geoffrey Scott, Jain, Kritarth, LeGrand, Louis LeRoi III, Roessler, Ross David, Savastinuk, Paul Aksenti
• Primary Examiner(s): Moon, Seokyun
• Application Number:
  US14/306,771
• Time in Patent Office: 714 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 1/1694 the I/O peripheral being a single or a set of motion sensors for pointer control or gesture input obtained by sensing movements of the portable computer
• CPC Class Codes: G06F 2200/1637 Sensing arrangement for detection of housing movement or orientation, e.g. for controlling scrolling or cursor movement on the display of an handheld computer
• 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
• CPC Class Codes: G06F 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors

Abstract

A device may recognize a tilt gesture when a device rotates about an axis and then back again. The gesture may be recognized using a state machine. Recognition of the gesture may be performed based on a context of a device, where the specific movement of the device during a tilt gesture may change based on the context. The tilt gesture may be confirmed using a classifier trained on features describing the gesture and the context.

Claims

1. A computer-implemented method for detecting a tilt gesture, the method comprising:

determining an identity of a user of the device;

identifying, based on the identity, a motion model describing expected outputs from a motion sensor of the device when the device executes a tilt gesture by rotating back and forth about an axis of the device within a predefined period of time, the motion model comprising a plurality of thresholds, the plurality of thresholds comprising a first threshold, a second threshold, and a third threshold;

detecting, based on a first output of the motion sensor, a first acceleration of the device in a first direction about the axis of the device, wherein the motion sensor comprises one or more of an accelerometer or a gyroscope;

determining completion of a first stage of the tilt gesture based on a first comparison of the first output to the first threshold, the first threshold comprising a minimum rotational velocity threshold;

detecting, based on a second output of the motion sensor, a second acceleration of the device in a second direction about the axis of the device, wherein the second direction is opposite the first direction;

determining completion of a second stage of the tilt gesture based on a second comparison of the second output to the second threshold, the second threshold comprising a zero velocity threshold;

generating a third output representing rotational distance traveled by the device, the third output based on the first output and the second output;

determining completion of a tilt gesture based on a third comparison of the third output to a third threshold, the third threshold representing a minimum rotational distance required to be traveled by the device;

sending an indication of the completion of the tilt gesture to an application; and

executing a function based on the tilt gesture by the application.

2. The computer-implemented method of claim 1, further comprising determining a context of a device, the context comprising at least one of an orientation of the device or an application running on the device, wherein the motion model is identified based on the context of the device, the motion model describing expected outputs from the motion sensor when the device executes a tilt gesture in the determined context.

3. A device, comprising:

at least one motion sensor;

at least one memory; and

at least one processor coupled to the at least one memory, the at least one processor being configured for;

determining an identity of a user of the device;

receiving a first rotation signal representing a first rotation of the device in a first direction about a first axis of the device;

comparing the first rotation to a first threshold, wherein the first threshold is based on the identity;

determining completion of a first stage of a tilt gesture based at least in part on the comparing of the first rotation to the first threshold;

receiving a second rotation signal representing a second rotation of the device in a second direction about the first axis, the second direction being opposite the first direction;

comparing the second rotation to a second threshold, wherein the second threshold is based on the identity; and

determining completion of the tilt gesture based at least in part on the comparing of the second rotation to the second threshold.

4. The device of claim 3, wherein:

the determining completion of the first stage is further based at least in part on a first confidence score; and

the determining completion of the tilt gesture is further based at least in part on a second confidence score.

5. The device of claim 4, wherein:

the first confidence score is based at least in part on the first rotation; and

the second confidence score is based at least in part on the second rotation.

6. The device of claim 3, wherein the at least one processor is further configured for:

determining a context of the device, the context comprising at least one of a device orientation, an application running on the device, a position of a head of the user, and whether the device is being operated by a left hand or a right hand, wherein the first threshold and second threshold are further based on the context.

7. The device of claim 3, wherein the at least one motion sensor comprises at least one of an accelerometer, a gyroscope, or a magnetometer configured to generate at least one of the first rotation signal or the second rotation signal.

8. The device of claim 3, wherein the at least one processor is further configured to output an indicator to the user based on determining the first stage of the tilt gesture.

9. The device of claim 8, wherein the indicator comprises one of an audio indicator or a haptic indicator.

10. The device of claim 3, further comprising a display screen, wherein the at least one processor is further configured to execute a function corresponding to the tilt gesture, the function resulting in a menu user interface appearing on a display screen of the device.

11. The device of claim 3, wherein the first rotation occurs at a first time and the second rotation occurs at a second time, the second time being after the first time.

12. A method comprising:

determining an identity of a user of the device;

receiving a first rotation signal representing a first rotation of the device in a first direction about a first axis of the device;

comparing the first rotation to a first threshold, wherein the first threshold is based on the identity;

determining completion of a first stage of a tilt gesture based at least in part on the comparing of the first rotation to the first threshold;

receiving a second rotation signal representing a second rotation of the device in a second direction about the first axis, the second direction being opposite the first direction;

comparing the second rotation to a second threshold, wherein the first threshold is based on the identity; and

determining completion of the tilt gesture based at least in part on the comparing of the second rotation to the second threshold.

13. The method of claim 12, wherein:

the determining completion of the first stage is further based at least in part on a first confidence score; and

the determining completion of the tilt gesture is further based at least in part on a second confidence score.

14. The method of claim 13, wherein:

the first confidence score is based at least in part on the first rotation; and

the second confidence score is based at least in part on the second rotation.

15. The method of claim 12, further comprising determining a context of the device, the context comprising at least one of a device orientation, an application running on the device, a position of a head of the user, and whether the device is being operated by a left hand or a right hand, wherein the first threshold and second threshold are based on the context.

16. The method of claim 12, wherein at least one of the first rotation signal or the second rotation signal is generated by at least one motion sensor comprises at least one of an accelerometer, a gyroscope, or a magnetometer.

17. The method of claim 12, further comprising outputting an indicator to the user based on determining the first stage of the tilt gesture.

18. The method of claim 17, wherein the indicator comprises one of an audio indicator or a haptic indicator.

19. The method of claim 12, further comprising executing a function corresponding to the tilt gesture, the function resulting in a menu user interface appearing on a display screen of the device.

20. The method of claim 12, wherein the first rotation occurs at a first time and the second rotation occurs at a second time, the second time being after the first time.