EVOLVING UNIVERSAL GESTURE SETS

• US 20110169726A1
• Filed: 01/08/2010
• Published: 07/14/2011
• Est. Priority Date: 01/08/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: LeGrow, Ian, Holmdahl, Todd Eric
• Granted Patent: US 9,019,201 B2
• Time in Patent Office: Days
• US Class Current: 345/156
• 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: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

In a gesture-based system, gestures may control aspects of a computing environment or application, where the gestures may be derived from a user'"'"'s position or movement in a physical space. Gesture recognition data, used to recognize gestures from captured data representative of a user'"'"'s input gestures, may be evolved based on captured data from a plurality of users. A common set or default set of gesture recognition data may be evolved by selecting a plurality of users for tracking. Captured data of the plurality of users may be processed to identify input gesture data for the plurality of users, and the gesture recognition data may be evolved based on features of the input gesture data that is common to multiple users. The evolved gesture recognition data may be implemented not only for the users tracked, but for users not tracked. An identifier may identify when the evolved gesture recognition data applies and implement the evolved gesture recognition data when the identifier is present.

Claims

1. A method for evolving a gesture set in a gesture-based system, the method comprising:

selecting a plurality of users for tracking, wherein tracking a user comprises capturing data representative of the user in a physical space;

compiling captured data representative of each of the plurality of users;

processing the captured data to identify input gesture data for each of the plurality of users; and

evolving gesture recognition data in the gesture-based system to correspond to the input gesture data, wherein the gesture recognition data is evolved to comprise a feature of the input gesture data that is common to two or more of the plurality of users.

2. The method of claim 1, further comprising implementing the evolved gesture recognition data for gesture recognition for subsequently captured data of at least one of the selected plurality of users or for a non-selected user.

3. The method of claim 1, further comprising:

comparing the input gesture data to the gesture recognition data; and

determining a level of failure of the captured data representative of each of the plurality of users to correspond to a gesture within the gesture recognition data.

4. The method of claim 1, wherein the common feature of the input gesture data for evolving the gesture recognition data is a parameter that modifies a gesture parameter in the gesture recognition data.

5. The method of claim 1, further comprising associating an identifier with the evolved gesture recognition data, wherein the identifier identifies when to implement the evolved gesture recognition data.

6. The method of claim 5, wherein the identifier is at least one of an operating system, an application, a user, a feature of a user, a location, a type of application, a hardware configuration, a software configuration, a culture, current user, geography, demography, linguistic, culture, or a style.

7. The method of claim 5, further comprising:

capturing data representative of a non-selected user;

correlating a feature of the non-selected user to the identifier; and

;

implementing the evolved gesture recognition data, associated with the identifier, for use with gesture recognition from the captured data of the non-selected user.

8. The method of claim 1, wherein evolving the gesture recognition data comprises at least one of generating new gesture recognition data, supplementing existing gesture recognition data, or modifying previously existing gesture recognition data.

9. The method of claim 1, further comprising verifying an improved performance in the comparison of captured data to the evolved gesture recognition data for subsequently captured data representative of at least one user.

10. The method of claim 1, wherein the plurality of users are selected by the gesture-based system by at least one of explicit or passive request.

11. The method of claim 1, further comprising distributing the evolved gesture recognition data to a second portion of the gesture-based system, wherein the gesture recognition data is evolved by a first portion of the gesture-based system.

12. A method for associating a gesture set to a user, the method comprising:

compiling captured data representative of a user'"'"'s gesture in a physical space;

comparing the captured data representative of the user'"'"'s gesture to gesture recognition data in the gesture-based system;

determining a level of failure of the captured data to correspond to the gesture recognition data; and

implementing an evolved gesture recognition data for gesture recognition of the user'"'"'s gesture, wherein the evolved gesture recognition data comprises an evolution of existing gesture recognition data in a gesture-based system to comprise a feature of input gesture data common to a plurality of users.

13. The method of claim 12, further comprising correlating at least one feature of the user'"'"'s gesture to an identifier associated with the evolved gesture recognition data, and implementing the evolved gesture recognition data associated with the identifier.

14. The method of claim 13, wherein the identifier is at least one of an operating system, an application, a user, a feature of a user, a location, a type of application, a hardware configuration, a software configuration, a culture, current user, geography, demography, linguistic, culture, or a style.

15. The method of claim 12, further comprising verifying an improved performance in gesture recognition between the comparison of captured data of the user'"'"'s gesture to the evolved gesture recognition data

16. The method of claim 12, wherein the level of failure is at least one of a complete failure of the captured data to correspond to the gesture or an unacceptable variation between the gesture recognition data and the gesture to which the captured data corresponds.

17. The method of claim 12, wherein a variation between the captured data representative of the user'"'"'s gesture and filter parameters for the gesture may correspond to the level of failure in a recognition of the user'"'"'s gesture

19. A system for evolving gesture recognition data, the system comprising:

a camera component, wherein the camera component captures data in a physical space; and

a processor, wherein the processor executes computer executable instructions, and wherein the computer executable instructions comprise instructions for;

selecting a plurality of users for tracking, wherein tracking a user comprises capturing data representative of the user in the physical space;

compiling captured data representative of each of the plurality of users;

processing the captured data to identify input gesture data for each of the plurality of users; and

evolving gesture recognition data in the gesture-based system to correspond to the input gesture data, wherein the gesture recognition data is evolved to comprise a feature of the input gesture data that is common to two or more of the plurality of users.

20. The system of claim 19, wherein the instructions further comprise instructions for implementing the evolved gesture recognition data for gesture recognition for subsequently captured data of at least one of the selected plurality of users or for a non-selected user.

21. The system of claim 19, wherein the instructions further comprise instructions for an identifier with the evolved gesture recognition data, wherein the identifier identifies when to implement the evolved gesture recognition data.