ENGAGEMENT-DEPENDENT GESTURE RECOGNITION

• US 20130211843A1
• Filed: 02/12/2013
• Published: 08/15/2013
• Est. Priority Date: 02/13/2012
• Status: Abandoned Application

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: CLARKSON, Ian Charles
• Application Number:
  US13/765,668
• Publication Number:
  US 20130211843A1
• Time in Patent Office: Days
• US Class Current: 704/275
• 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 3/04883 for inputting data by handwriting, e.g. gesture or text

Abstract

Methods, apparatuses, systems, and computer-readable media for performing engagement-dependent gesture recognition are presented. According to one or more aspects, a computing device may detect an engagement of a plurality of engagements, and each engagement of the plurality of engagements may define a gesture interpretation context of a plurality of gesture interpretation contexts. Subsequently, the computing device may detect a gesture. Then, the computing device may execute at least one command based on the detected gesture and the gesture interpretation context defined by the detected engagement. In some arrangements, the engagement may be an engagement pose, such as a hand pose, while in other arrangements, the detected engagement may be an audio engagement, such as a particular word or phrase spoken by a user.

Claims

1. A method comprising:

detecting an engagement input;

selecting an input interpretation context from amongst a plurality of input interpretation contexts, the selecting being done based on the detected engagement input;

detecting a gesture input subsequent to the selecting an input interpretation context; and

executing a command based on the detected gesture input and the selected input interpretation context.

2. The method of claim 1, wherein detecting an engagement input comprises detecting an engagement pose being maintained for a threshold amount of time.

3. The method of claim 2, wherein the engagement pose comprises a hand pose and wherein the hand pose comprises a substantially open palm and outstretched fingers.

4. The method of claim 2, wherein the engagement pose comprises a hand pose and wherein the hand pose comprises a closed first and an outstretched arm.

5. The method of claim 2, wherein the engagement pose comprises a hand pose, and wherein the selecting is independent of a position of the hand when the hand pose is detected.

6. The method of claim 1, wherein detecting an engagement input comprises detecting a gesture or an occlusion of a sensor.

7. The method of claim 1, wherein detecting an engagement input comprises detecting an audio engagement, the audio engagement comprising a word or phrase spoken by a user.

8. The method of claim 1, wherein the detected engagement input comprises one of a plurality of engagement inputs, each of the plurality of engagement inputs corresponding to a respective one of the plurality of input interpretation contexts, and wherein the selecting comprises selecting the input interpretation context corresponding to the detected engagement input.

9. The method of claim 1, further comprising:

in response to the detecting an engagement input, displaying a user interface which identifies an active input interpretation context.

10. The method of claim 1, further comprising:

providing audio feedback in response to the detecting an engagement input, wherein the audio feedback identifies an active input interpretation context.

11. The method of claim 1, wherein the selected input interpretation context is defined at an application level such that said selected input interpretation context is defined by an application that is in focus.

12. The method of claim 1, further comprising causing one or more elements to be displayed prior to detecting the engagement input, wherein the selecting is independent of the one or more elements being displayed.

13. The method of claim 1, wherein detecting the gesture input comprises detecting the gesture input based on one or more parameters associated with the selected input interpretation context.

14. The method of claim 1, further comprising ignoring sensor input irrelevant to detecting the engagement input, the ignoring done prior to detecting the engagement input.

15. The method of claim 1,

wherein detecting an engagement input comprises:

detecting a first engagement input associated with a first input interpretation context for controlling a first functionality; and

detecting a second engagement input associated with a second input interpretation context for controlling a second functionality different from the first functionality.

16. The method of claim 15, wherein the first functionality is associated with a first type of subsystem within an automobile control system, and wherein the second functionality is associated with a second type of subsystem within the automobile control system.

17. The method of claim 15, wherein the first functionality is associated with a first type of subsystem within a media player application, and wherein the second functionality is associated with a second type of subsystem within the media player application.

18. The method of claim 1, wherein the selected input interpretation context is globally defined.

19. The method of claim 1, wherein detecting the engagement input comprises detecting an initial engagement input and a later engagement input, and wherein detecting the later engagement input comprises using an input interpretation context associated with the initial engagement input.

20. An apparatus comprising:

an engagement detection module configured to detect an engagement input;

a selection module configured to select an input interpretation context from amongst a plurality of input interpretation contexts, the selection module being configured to perform the selecting based on the detected engagement input;

a detection module configured to detect a gesture input subsequent to the selection module selecting the input interpretation context; and

a processor configured to execute a command based on the detected gesture input and the selected input interpretation context.

21. The apparatus of claim 20, wherein the engagement detection module is configured to detect an engagement pose being maintained for a threshold amount of time.

22. The apparatus of claim 21, wherein the engagement pose comprises a hand pose and wherein the selection module is configured to select the input interpretation context independent of a position of the hand when the hand pose is detected.

23. The apparatus of claim 20, further comprising a display screen, wherein the processor is further configured to cause the display screen to display a user interface in response to detecting an engagement input, and wherein the user interface identifies an active input interpretation context.

24. The apparatus of claim 20, further comprising an audio speaker, wherein the processor is further configured to cause the audio speaker to output audio feedback in response to detecting an engagement input, wherein the audio feedback identifies an active input interpretation context.

25. The apparatus of claim 20, wherein the input interpretation context is defined at an application level such that the input interpretation context is defined by an application that is in focus.

26. The apparatus of claim 20, further comprising a camera configured to capture two-dimensional images, wherein the engagement detection module is configured to detect the engagement input based on at least one image captured by the camera, and wherein the detection module is configured to detect the gesture input using at least one other image captured by the camera.

27. The apparatus of claim 20, further comprising a sensor configured to input sensor data to the engagement detection module, and wherein the processor is further configured to cause the apparatus to ignore sensor data irrelevant to detecting an engagement input.

28. The apparatus of claim 20, wherein the engagement detection module is configured to:

detect a first engagement input associated with a first input interpretation context for controlling a first functionality, and

detect a second engagement input associated with a second input interpretation context for controlling a second functionality different from the first functionality, wherein the first functionality is associated with a first subsystem within an automobile control system or media player application, and wherein the second functionality is associated with a second subsystem within the automobile control system or media player application.

29. The apparatus of claim 20, wherein the detected engagement input comprises one of a plurality of engagement inputs, each of the plurality of engagement inputs corresponding to a respective one of the plurality of input interpretation contexts, and wherein the selection module is configured to select the input interpretation context corresponding to the detected engagement input.

30. The apparatus of claim 20, wherein the selected input interpretation context is globally defined.

31. The apparatus of claim 20, wherein detecting an engagement input comprises detecting an initial engagement input and a later engagement input, and wherein the detecting a later engagement input comprises using an input interpretation context selected based on the initial engagement input.

32. An apparatus comprising:

means for detecting an engagement input;

means for selecting an input interpretation context from amongst a plurality of input interpretation contexts, the selecting being based on the detected engagement input;

means for detecting a gesture input subsequent to the selecting an input interpretation context; and

means for executing a command based on the detected gesture input and the selected input interpretation context.

33. The apparatus of claim 32, wherein the means for detecting an engagement input comprise means for detecting an engagement pose being maintained for a threshold amount of time.

34. The apparatus of claim 33, wherein the engagement pose is a hand pose and wherein the means for selecting comprises means for selecting the input interpretation context independent of a position of the hand when the hand pose is detected.

35. The apparatus of claim 32, wherein the means for detecting an engagement input comprises means for detecting at least one of an engagement gesture, an occlusion of a sensor, or an audio engagement.

36. The apparatus of claim 32, further comprising:

means for providing feedback to a user of the apparatus in response to the selecting, wherein the feedback identifies the selected input interpretation context.

37. The apparatus of claim 32, wherein the detected engagement input comprises one of a plurality of engagement inputs, each of the plurality of engagement inputs corresponding to a respective one of the plurality of input interpretation contexts, and wherein the means for selecting comprises means for selecting the input interpretation context corresponding to the detected engagement input.

38. The apparatus of claim 32, wherein the means for selecting an input interpretation context comprise means for selecting an input interpretation context defined at an application level by an application that is in focus.

39. The apparatus of claim 32, wherein the means for detecting a gesture input comprise means for detecting a gesture input based on parameters associated with the selected input interpretation context.

40. The apparatus of claim 32, further comprising means for ignoring input irrelevant to detecting an engagement input prior to the means for detecting an engagement input detecting the engagement input.

41. The apparatus of claim 32,

wherein the means for detecting a gesture input comprises:

means for detecting a first engagement input associated with a first input interpretation context for controlling a first functionality of a system, and

means for detecting a second engagement input associated with a second input interpretation context for controlling a second functionality of the system different from the first functionality.

42. The apparatus of claim 32, wherein the means for selecting comprises means for selecting a globally defined input interpretation context.

43. The apparatus of claim 32, wherein the means for detecting an engagement input comprises means for detecting an initial engagement input and a later engagement input, and wherein means for detecting the later engagement input comprises means for using an input interpretation context associated with the initial engagement input to detect the later engagement input.

44. A non-transitory computer readable medium having instructions stored thereon, the instructions for causing an apparatus to:

detect an engagement input;

select, based on the detected engagement input, an input interpretation context from amongst a plurality of input interpretation contexts;

detect a gesture input subsequent to selection of the input interpretation context; and

execute a command based on the detected gesture input and the selected input interpretation context.