CONTEXT-SENSITIVE GESTURE CLASSIFICATION

• US 20150078613A1
• Filed: 09/13/2013
• Published: 03/19/2015
• Est. Priority Date: 09/13/2013
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Forutanpour, Babak, Balasubramanyam, Shivakumar, Carvalho, Vitor R.
• Granted Patent: US 9,582,737 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/24 Classification techniques
• 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
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

Various arrangements for recognizing a gesture are presented. User input may be received that causes a gesture classification context to be applied from a plurality of gesture classification contexts. This gesture classification context may be applied, such as to a gesture analysis engine. After applying the gesture classification context, data indicative of a gesture performed by a user may be received. The gesture may be identified in accordance with the applied gesture classification context.

Claims

1. A method for recognizing a gesture, the method comprising:

receiving, by a computer system, user input that causes a gesture classification context to be applied from a plurality of gesture classification contexts available for a gesture analysis engine;

applying, by the computer system, the gesture classification context to the gesture analysis engine;

after applying the gesture classification context, receiving, by the computer system, data indicative of the gesture performed by a user; and

identifying, by the computer system, using the gesture analysis engine, the gesture in accordance with the applied gesture classification context.

2. The method for recognizing the gesture of claim 1, the method further comprising:

prior to receiving the user input, calculating, by the computer system, a first set of metrics to differentiate among only a first subset of gestures selected from a set of available gestures, wherein;

only the first subset of gestures are eligible to be identified when the gesture classification context is active.

3. The method for recognizing the gesture of claim 2, the method further comprising:

receiving an indication of a second subset of gestures from the set of available gestures, wherein;

each gesture of the second subset of gestures is valid in a second gesture classification context;

calculating, by the computer system, a second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures, wherein;

only the second subset of gestures are eligible to be identified when the second gesture classification context is active, and

the second subset of gestures and the first subset of gestures contain at least one different gesture;

after calculating the second set of metrics, receiving, by the computer system, user input that causes the second gesture classification context to be applied to the gesture analysis engine;

after applying the second gesture classification context, receiving, by the computer system, data indicative of a second gesture performed by the user; and

interpreting, by the computer system, the second gesture in accordance with the applied second gesture classification context.

4. The method for recognizing the gesture of claim 1, wherein receiving the user input that causes the gesture classification context to be applied comprises:

receiving, by the computer system, user input that selects an application within a user interface.

5. The method for recognizing the gesture of claim 4, wherein receiving the user input that causes the gesture classification context to be applied further comprises:

receiving, by the computer system, user input that causes a cursor to hover over an icon presented by the user interface.

6. The method for recognizing the gesture of claim 2, wherein calculating the first set of metrics to differentiate among only the first subset of gestures comprises:

calculating, by the computer system, metrics for each gesture of the first subset of gestures, wherein the metrics for each gesture of the first subset of gestures is at least partially based on gesture training data and other gestures of the first subset of gestures.

7. The method for recognizing the gesture of claim 3, wherein:

receiving the indication of the second subset of gestures from the set of available gestures; and

calculating the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures occur in response to an application being installed at the computer system.

8. The method for recognizing the gesture of claim 3, wherein:

receiving the indication of the second subset of gestures from the set of available gestures; and

calculating the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures occur during creation of a gesture subset database, wherein the gesture subset database comprises gesture classification contexts for multiple subsets of the set of available gestures.

9. A system for recognizing a gesture, the system comprising:

one or more processors; and

a memory communicatively coupled with and readable by the one or more processors and having stored therein processor-readable instructions which, when executed by the one or more processors, cause the one or more processors to;

receive user input that causes a gesture classification context to be applied from a plurality of gesture classification contexts available for a gesture analysis engine;

apply the gesture classification context to the gesture analysis engine;

after applying the gesture classification context, receive data indicative of the gesture performed by a user; and

identify using the gesture analysis engine, the gesture in accordance with the applied gesture classification context.

10. The system for recognizing the gesture of claim 9, wherein the processor-readable instructions, when executed, further cause the one or more processors to:

prior to receiving the user input, calculate a first set of metrics to differentiate among only a first subset of gestures selected from a set of available gestures, wherein only the first subset of gestures are eligible to be identified when the gesture classification context is active.

11. The system for recognizing the gesture of claim 10, wherein the processor-readable instructions, when executed, further cause the one or more processors to:

receive an indication of a second subset of gestures from the set of available gestures, wherein;

each gesture of the second subset of gestures is valid in a second gesture classification context;

calculate a second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures, wherein;

only the second subset of gestures are eligible to be identified when the second gesture classification context is active, and

the second subset of gestures and the first subset of gestures contain at least one different gesture;

after calculating the second set of metrics, receive user input that causes the second gesture classification context to be applied to the gesture analysis engine;

after applying the second gesture classification context, receive data indicative of a second gesture performed by the user; and

interpret the second gesture in accordance with the applied second gesture classification context.

12. The system for recognizing the gesture of claim 9, wherein the processor-readable instructions that cause the one or more processors to receive the user input that causes the gesture classification context to be applied comprise processor-readable instructions which, when executed, cause the one or more processors to:

receive user input that selects an application within a user interface.

13. The system for recognizing the gesture of claim 12, wherein the processor-readable instructions that cause the one or more processors to receive the user input that causes the gesture classification context to be applied comprise processor-readable instructions which, when executed, cause the one or more processors to:

receive user input that causes a cursor to hover over an icon presented by the user interface.

14. The system for recognizing the gesture of claim 10, wherein the processor-readable instructions that cause the one or more processors to calculate the first set of metrics to differentiate among only the first subset of gestures comprise processor-readable instructions which, when executed, cause the one or more processors to:

calculate metrics for each gesture of the first subset of gestures, wherein the metrics for each gesture of the first subset of gestures is at least partially based on gesture training data and other gestures of the first subset of gestures.

15. The system for recognizing the gesture of claim 11, wherein the processor-readable instructions which, when executed, cause the one or more processors to:

receive the indication of the second subset of gestures from the set of available gestures; and

calculate the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures;

are executed in response to an application being installed at the computer system.

16. The system for recognizing the gesture of claim 11, wherein the processor-readable instructions which, when executed, cause the one or more processors to:

receive the indication of the second subset of gestures from the set of available gestures; and

calculate the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures are executed as part of processor-readable instructions which, when executed by the one or more processors, cause the one or more processors to;

create a gesture subset database, wherein the gesture subset database comprises gesture classification contexts for multiple subsets of the set of available gestures.

17. A non-transitory processor-readable medium for recognizing a gesture, comprising processor-readable instructions configured to cause one or more processors to:

receive user input that causes a gesture classification context to be applied from a plurality of gesture classification contexts available for a gesture analysis engine;

apply the gesture classification context to the gesture analysis engine;

after applying the gesture classification context, receive data indicative of the gesture performed by a user; and

identify using the gesture analysis engine, the gesture in accordance with the applied gesture classification context.

18. The non-transitory processor-readable medium for recognizing the gesture of claim 17, wherein the processor-readable instructions are further configured to cause the one or more processors to:

prior to receiving the user input, calculate a first set of metrics to differentiate among only a first subset of gestures selected from a set of available gestures, wherein

only the first subset of gestures are eligible to be identified when the gesture classification context is active.

19. The non-transitory processor-readable medium for recognizing the gesture of claim 18, wherein the processor-readable instructions are further configured to cause the one or more processors to:

receive an indication of a second subset of gestures from the set of available gestures, wherein;

each gesture of the second subset of gestures is valid in a second gesture classification context;

calculate a second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures, wherein;

only the second subset of gestures are eligible to be identified when the second gesture classification context is active, and

the second subset of gestures and the first subset of gestures contain at least one different gesture;

after calculating the second set of metrics, receive user input that causes the second gesture classification context to be applied to the gesture analysis engine;

after applying the second gesture classification context, receive data indicative of a second gesture performed by the user; and

interpret the second gesture in accordance with the applied second gesture classification context.

20. The non-transitory processor-readable medium for recognizing the gesture of claim 17, wherein the processor-readable instructions configured to cause the one or more processors to receive the user input that causes the gesture classification context to be applied comprise processor-readable instructions configured to cause the one or more processors to:

receive user input that selects an application within a user interface.

21. The non-transitory processor-readable medium for recognizing the gesture of claim 20, wherein the processor-readable instructions configured to cause the one or more processors to receive the user input that causes the gesture classification context to be applied comprise processor-readable instructions configured to cause the one or more processors to:

receive user input that causes a cursor to hover over an icon presented by the user interface.

22. The non-transitory processor-readable medium for recognizing the gesture of claim 18, wherein the processor-readable instructions configured to cause the one or more processors to calculate the first set of metrics to differentiate among only the first subset of gestures comprise processor-readable instructions configured to cause the one or more processors to:

calculate metrics for each gesture of the first subset of gestures, wherein the metrics for each gesture of the first subset of gestures is at least partially based on gesture training data and other gestures of the first subset of gestures.

23. The non-transitory processor-readable medium for recognizing the gesture of claim 19, wherein the processor-readable instructions configured to cause the one or more processors to:

receive the indication of the second subset of gestures from the set of available gestures; and

calculate the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures;

are executed in response to an application being installed at the computer system.

24. The non-transitory processor-readable medium for recognizing the gesture of claim 19, wherein the processor-readable instructions configured to cause the one or more processors to:

receive the indication of the second subset of gestures from the set of available gestures; and

calculate the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures are executed as part of processor-readable instructions configured to cause the one or more processors to;

create a gesture subset database, wherein the gesture subset database comprises gesture classification contexts for multiple subsets of the set of available gestures.

25. A apparatus for recognizing a gesture, the apparatus comprising:

means for receiving user input that causes a gesture classification context to be applied from a plurality of gesture classification contexts that are available for a means for gesture analysis;

means for applying the gesture classification context to the means for gesture analysis;

means for receiving data indicative of the gesture performed by a user after applying the gesture classification context; and

means for identifying using the means for gesture analysis, the gesture in accordance with the applied gesture classification context.

26. The apparatus for recognizing the gesture of claim 25, the apparatus further comprising:

means for calculating a first set of metrics to differentiate among only a first subset of gestures selected from a set of available gestures prior to receiving the user input, wherein;

only the first subset of gestures are eligible to be identified when the gesture classification context is active.

27. The apparatus for recognizing the gesture of claim 26, the apparatus further comprising:

means for receiving an indication of a second subset of gestures from the set of available gestures, wherein;

each gesture of the second subset of gestures is valid in a second gesture classification context;

means for calculating a second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures, wherein;

only the second subset of gestures are eligible to be identified when the second gesture classification context is active, and

the second subset of gestures and the first subset of gestures contain at least one different gesture;

means for receiving user input that causes the second gesture classification context to be applied to the means for gesture analysis after calculating the second set of metrics;

means for receiving data indicative of a second gesture performed by the user after applying the second gesture classification context; and

means for interpreting the second gesture in accordance with the applied second gesture classification context.

28. The apparatus for recognizing the gesture of claim 25, wherein the means for receiving the user input that causes the gesture classification context to be applied comprises:

means for receiving user input that selects an application within a user interface.

29. The apparatus for recognizing the gesture of claim 28, wherein the means for receiving the user input that causes the gesture classification context to be applied further comprises:

means for receiving user input that causes a cursor to hover over an icon presented by the user interface.

30. The apparatus for recognizing the gesture of claim 26, wherein the means for calculating the first set of metrics to differentiate among only the first subset of gestures comprises:

means for calculating metrics for each gesture of the first subset of gestures, wherein the metrics for each gesture of the first subset of gestures is at least partially based on gesture training data and other gestures of the first subset of gestures.

31. The apparatus for recognizing the gesture of claim 27, wherein:

the means for receiving the indication of the second subset of gestures from the set of available gestures; and

the means for calculating the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures are contingent on an application being installed at the computer system.

32. The apparatus for recognizing the gesture of claim 27, wherein:

the means for receiving the indication of the second subset of gestures from the set of available gestures; and

the means for calculating the second set of metrics for the second subset of gestures to differentiate among only the second subset of gestures are part of a means for creating a gesture subset database, wherein the gesture subset database comprises gesture classification contexts for multiple subsets of the set of available gestures.