Systems and methods for performing anytime motion recognition
First Claim
Patent Images
1. A method for performing anytime motion recognition, the method comprising:
- receiving a motion signal about a motion from a motion-sensitive device being manipulated by a user as a way to interact with an application;
generating a final recognition signal for the motion signal in response to a motion recognizer which includes a set of prototypes, wherein said generating a final recognition signal comprises identifying a current node in a disambiguation tree to represent a set of moves currently confused with each other given how much of the motion signal has been received so far, wherein the disambiguation tree is prebuilt before receiving the motion signal; and
returning the current node to the application at any point in time before the motion signal is received in entirety so that the current node facilitates the application to start an immediate animation of the motion, even when moves are confused.
0 Assignments
0 Petitions
Accused Products
Abstract
Techniques for performing anytime motion recognition are disclosed. Based on a motion signal received from a motion-sensitive device being manipulated by a user as a way to interact with an application, a processing unit is configured to a set of prototypes included in a motion recognizer to generate a recognition signal from the motion signal in response to the motion recognizer. A prototype is eliminated out of the set of the prototypes from further consideration when a corresponding running distance of the prototype to the motion signal is beyond a predefined measurement so that the motion recognition speeds up as time passes.
-
Citations
18 Claims
-
1. A method for performing anytime motion recognition, the method comprising:
-
receiving a motion signal about a motion from a motion-sensitive device being manipulated by a user as a way to interact with an application; generating a final recognition signal for the motion signal in response to a motion recognizer which includes a set of prototypes, wherein said generating a final recognition signal comprises identifying a current node in a disambiguation tree to represent a set of moves currently confused with each other given how much of the motion signal has been received so far, wherein the disambiguation tree is prebuilt before receiving the motion signal; and returning the current node to the application at any point in time before the motion signal is received in entirety so that the current node facilitates the application to start an immediate animation of the motion, even when moves are confused. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A system for performing anytime motion recognition, the system comprising:
-
at least one motion-sensitive device; a processing unit receiving a motion signal from the motion-sensitive device when the motion-sensitive device is being manipulated by a user, the processing unit being loaded with at least one motion recognizer including a set of prototypes, and configured to; generate a recognition signal from the motion signal in response to the motion recognizer, identify a current node in a disambiguation tree to represent a set of moves currently confused with each other given how much of the motion signal has been received so far, wherein the disambiguation tree is prebuilt before receiving the motion signal; and returning a current node to the application at any point in time before the motion signal is received in entirety so that the current node facilitates the application to start an immediate animation of the motion, even when moves are confused. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A method for performing anytime motion recognition, the method comprises:
-
receiving a motion signal from a motion-sensitive device being manipulated by a user as a way to interact with an application; accessing at least a motion recognizer embedded with a disambiguation tree that organizes a collection of sets of moves that are commonly confused with each other at certain points in time; identifying a current node in the disambiguation tree that represents a set of moves that are currently confused with each other given how much of the motion signal has been received so far; and returning a set of currently confused moves to the application at any point in time to start an immediate animation of a move before a final recognition signal to the motion signal is determined. - View Dependent Claims (12, 13, 14)
-
-
15. A system for performing anytime motion recognition, the system comprising:
-
at least one motion-sensitive device; a processing unit receiving a motion signal from the motion-sensitive device when the motion-sensitive device is being manipulated by a user interacting with an application, the processing unit being loaded with at least one motion recognizer embedded with a disambiguation tree that organizes a collection of sets of moves that are commonly confused with each other at certain points in time, and wherein the processing unit is configured to identify a current node in the disambiguation tree that represents a set of moves that are currently confused with each other; and
return the set of currently confused moves to the application at any point in time to start an immediate animation of a move before a final recognition signal to the motion signal is determined. - View Dependent Claims (16, 17, 18)
-
Specification