Wearable device gesture detection
The description relates to smart rings. One example can include a finger band configured to accommodate a user's finger. This example can also include a set of pressure sensors positioned on an inner surface of the finger band and configured to sense changes to tendons of the user's finger as pressure differentials and to output associated signals. The example can further include a gesture component configured to interpret the signals from the set of pressure sensors to identify individual actions performed by the user's finger.
1. A wearable device comprising:
at least one sensor configured to output a sensor signal reflecting movement of the wearable device; and
at least one processor or hardware logic circuit configured to:
receive a report from a remote device with which the wearable device is capable of interacting;
determine, based at least on the report received from the remote device, a current user interface context of the remote device; and
selectively interpret the sensor signal based at least on the current user interface context of the remote device to identify a particular gesture being performed with the wearable device.
2. The wearable device of claim 1 , wherein the at least one processor or hardware logic circuit is further configured to:
determine that the report indicates that the current user interface context of the remote device is a text entry context; and
based at least on determining that the report indicates that the current user interface context of the remote device is the text entry context, identify the particular gesture as a writing stroke.
3. The wearable device of claim 1 , wherein the at least one processor or hardware logic circuit is further configured to:
determine that the report indicates that the current user interface context of the remote device is not a text entry context; and
based at least on determining that the report indicates that the current user interface context of the remote device is not a text entry context, identify the particular gesture as a scroll event.
4. The wearable device of claim 1 , the at least one sensor being an accelerometer.
5. The wearable device of claim 4 , wherein the at least one processor or hardware logic circuit is further configured to:
when an accelerometer signal received from the accelerometer is indicative of a landing on another surface, compare a magnitude of the accelerometer signal to a threshold;
in instances when the magnitude of the accelerometer signal exceeds the threshold, identify the particular gesture as a hard-landing gesture; and
in other instances when the magnitude of the accelerometer signal does not exceed the threshold, identify the particular gesture as a soft-landing gesture.
6. The wearable device of claim 5 , wherein the at least one processor or hardware logic circuit is further configured to:
compare a duration of the hard-landing gesture to a duration threshold;
when the duration of the hard-landing gesture is less than the duration threshold, interpret the hard-landing gesture as a tap gesture; and
when the duration of the hard-landing gesture is greater than the duration threshold, interpret the hard-landing gesture as a swipe gesture.
7. The wearable device of claim 1 , the remote device being a local companion device, wherein the at least one processor or hardware logic circuit is further configured to:
transmit an indication of the particular gesture to the local companion device.
8. The wearable device of claim 7 , wherein the at least one processor or hardware logic circuit is further configured to:
transmit the indication of the particular gesture to the local companion device using short-range wireless communication.
9. A method comprising:
obtaining a sensor signal reflecting movement of a wearable device;
receiving a report from a remote device with which the wearable device is capable of interacting;
determining, based at least on the report received from the remote device, a current user interface context of the remote device; and
selectively interpreting the sensor signal based at least on the current user interface context of the remote device to identify a particular gesture being performed with the wearable device.
10. The method of claim 9 , further comprising:
transmitting an indication of the particular gesture to the remote device.
11. The method of claim 9 , performed entirely by the wearable device.
12. The method of claim 9 , further comprising:
when the current user interface context is a text entry context, interpreting the particular gesture as a writing stroke.
13. The method of claim 12 , further comprising:
identifying a particular character entered at least in part by the writing stroke; and
entering the particular character to the remote device.
14. The method of claim 13 , further comprising:
when the current user interface context is not a text entry context, interpreting the particular gesture as a scroll event.
15. The method of claim 14 , further comprising:
identifying a particular direction of the scroll event; and
causing the remote device to perform a scrolling action in the particular direction.
16. A computer-readable storage medium storing instructions which, when executed by a processor, cause a processor to perform acts comprising:
obtaining a sensor signal reflecting movement of a wearable device;
receiving a report from a remote device with which the wearable device is capable of interacting;
determining, based at least on the report received from the remote device, a current user interface context of the remote device; and
selectively interpreting the sensor signal based at least on the current user interface context of the remote device to identify a particular gesture being performed with the wearable device.
17. The computer-readable storage medium of claim 16 , the acts further comprising:
transmitting an indication of the particular gesture to the remote device using short-range wireless communication.
18. The computer-readable storage medium of claim 16 , the acts further comprising:
processing the sensor signal using a trained classifier to identify the particular gesture.
19. The computer-readable storage medium of claim 18 , the sensor signal comprising an accelerometer signal, the trained classifier comprising a support vector machine configured to classify the accelerometer signal as writing strokes or scroll gestures.
20. The computer-readable storage medium of claim 16 , the acts further comprising:
interpreting the particular gesture as a writing stroke when the report indicates that the current user interface context of the remote device is a text entry context; and
interpreting the particular gesture as a scroll event when the report indicates that the current user interface context of the remote device is not a text entry context.