METHODS AND APPARATUSES FOR FACILITATING GESTURE RECOGNITION

• US 20120272194A1
• Filed: 04/21/2011
• Published: 10/25/2012
• Est. Priority Date: 04/21/2011
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Yang, Jun, Pang, Hawk-Yin, Liu, Zhigang
• Granted Patent: US 8,873,841 B2
• Time in Patent Office: Days
• US Class Current: 715/863
• 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 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: G06V 10/17 using hand-held instruments
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• 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

Methods and apparatuses are provided for facilitating gesture recognition. A method may include constructing a matrix based at least in part on an input gesture and a template gesture. The method may further include determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold. In an instance in which the relationship does not satisfy the predefined threshold, the method may also include eliminating the template gesture from further consideration for recognition of the input gesture. In an instance in which the relationship satisfies the predefined threshold, the method may further include determining a rotation matrix based at least in part on the constructed matrix. Corresponding apparatuses are also provided.

Claims

1. A method comprising:

constructing a matrix based at least in part on an input gesture and a template gesture;

determining, by a processor, whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold;

in an instance in which the relationship does not satisfy the predefined threshold, eliminating the template gesture from further consideration for recognition of the input gesture; and

in an instance in which the relationship satisfies the predefined threshold, determining a rotation matrix based at least in part on the constructed matrix.

2. The method of claim 1, further comprising:

calculating a plurality of eigenvalues based at least in part on the constructed matrix; and

wherein determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold comprises determining whether a relationship between the eigenvalues satisfies a predefined threshold.

3. The method of claim 2, wherein determining whether a relationship between the eigenvalues satisfies the predefined threshold comprises determining whether a ratio between the eigenvalue having the largest positive value and another of the eigenvalues is greater than the predefined threshold.

4. The method of claim 1, wherein determining the rotation matrix comprises:

determining the eigenvector of the constructed matrix having the largest positive eigenvalue as a unit quaternion; and

determining the rotation matrix represented by the unit quaternion.

5. The method of claim 1, further comprising:

prior to constructing the matrix, comparing a property of the input gesture to a property of the template gesture; and

wherein constructing the matrix comprises constructing the matrix only in an instance in which the comparison between the property of the input gesture and the property of the template gesture satisfies a second predefined threshold.

6. The method of claim 5, wherein comparing a property of the input gesture to a property of the template gesture comprises comparing one or more of a length, rate, or acceleration of the input gesture to a respective one or more of a length, rate, or acceleration of the template gesture.

7. The method of claim 1, further comprising, in an instance in which the relationship satisfies the predefined threshold:

using the rotation matrix to rotate a gravity vector associated with the template gesture to a coordinate system of the input gesture;

comparing the rotated gravity vector associated with the template gesture to a gravity vector associated with the input gesture to determine whether an angle between the rotated gravity vector associated with the template gesture and the gravity vector associated with the input gesture satisfies a second predefined threshold; and

eliminating the template gesture from further consideration for recognition of the input gesture in an instance in which the angle does not satisfy the second predefined threshold.

8. The method of claim 1, further comprising, in an instance in which the relationship satisfies the predefined threshold:

using the rotation matrix to rotate the template gesture to a coordinate system of the input gesture;

calculating a pairwise distance based at least in part on the rotated template gesture and the input gesture;

determining whether the pairwise distance satisfies a second predefined threshold; and

eliminating the template gesture from further consideration for recognition of the input gesture in an instance in which the pairwise distance does not satisfy the second predefined threshold.

9. The method of claim 1, further comprising:

using a gesture recognition classifier to determine whether the input gesture matches the template gesture in an instance in which the template gesture is not eliminated from further consideration for recognition of the input gesture.

10. The method of claim 1, further comprising repeating the constructing and determining for each of a plurality of template gestures, thereby filtering out template gestures that fail to satisfy the predefined threshold.

11. An apparatus comprising at least one processor and at least one memory storing computer program code, wherein the at least one memory and stored computer program code are configured, with the at least one processor, to cause the apparatus to at least:

construct a matrix based at least in part on an input gesture and a template gesture;

determine whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold;

in an instance in which the relationship does not satisfy the predefined threshold, eliminate the template gesture from further consideration for recognition of the input gesture; and

in an instance in which the relationship satisfies the predefined threshold, determine a rotation matrix based at least in part on the constructed matrix.

12. The apparatus of claim 11, wherein the at least one memory and stored computer program code are configured, with the at least one processor, to further cause the apparatus to:

calculate a plurality of eigenvalues based at least in part on the constructed matrix;

determine whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold at least in part by determining whether a relationship between the eigenvalues satisfies a predefined threshold.

13. The apparatus of claim 12 wherein the at least one memory and stored computer program code are configured, with the at least one processor, to cause the apparatus to determine whether a relationship between the eigenvalues satisfies the predefined threshold at least in part by determining whether a ratio between the eigenvalue having the largest positive value and another of the eigenvalues is greater than the predefined threshold.

14. The apparatus of claim 11, wherein the at least one memory and stored computer program code are configured, with the at least one processor, to cause the apparatus to determine the rotation matrix at least in part by:

determining the eigenvector of the constructed matrix having the largest positive eigenvalue as a unit quaternion; and

determining the rotation matrix represented by the unit quaternion.

15. The apparatus of claim 11, wherein the at least one memory and stored computer program code are configured, with the at least one processor, to further cause the apparatus to:

prior to constructing the matrix, compare a property of the input gesture to a property of the template gesture; and

construct the matrix only in an instance in which the comparison between the property of the input gesture and the property of the template gesture satisfies a second predefined threshold.

16. The apparatus of claim 11, wherein, in an instance in which the relationship satisfies the predefined threshold, the at least one memory and stored computer program code are configured, with the at least one processor, to further cause the apparatus to:

use the rotation matrix to rotate a gravity vector associated with the template gesture to a coordinate system of the input gesture;

compare the rotated gravity vector associated with the template gesture to a gravity vector associated with the input gesture to determine whether an angle between the rotated gravity vector associated with the template gesture and the gravity vector associated with the input gesture satisfies a second predefined threshold; and

eliminate the template gesture from further consideration for recognition of the input gesture in an instance in which the angle does not satisfy the second predefined threshold.

17. The apparatus of claim 11, wherein, in an instance in which the relationship satisfies the predefined threshold, the at least one memory and stored computer program code are configured, with the at least one processor, to further cause the apparatus to:

use the rotation matrix to rotate the template gesture to a coordinate system of the input gesture;

calculate a pairwise distance based at least in part on the rotated template gesture and the input gesture;

determine whether the pairwise distance satisfies a second predefined threshold; and

eliminate the template gesture from further consideration for recognition of the input gesture in an instance in which the pairwise distance does not satisfy the second predefined threshold.

18. The apparatus of claim 11, wherein the at least one memory and stored computer program code are configured, with the at least one processor, to further cause the apparatus to:

use a gesture recognition classifier to determine whether the input gesture matches the template gesture in an instance in which the template gesture is not eliminated from further consideration for recognition of the input gesture.

19. The apparatus of claim 11, wherein the apparatus comprises or is embodied on a mobile phone, the mobile phone comprising user interface circuitry and user interface software stored on one or more of the at least one memory;

wherein the user interface circuitry and user interface software are configured to;

facilitate user control of at least some functions of the mobile phone through use of a display; and

cause at least a portion of a user interface of the mobile phone to be displayed on the display to facilitate user control of at least some functions of the mobile phone.

20. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program instructions stored therein, the computer-readable program instructions comprising:

program instructions configured to construct a matrix based at least in part on an input gesture and a template gesture;

program instructions configured to calculate a plurality of eigenvalues based at least in part on the constructed matrix;

program instructions configured to determine whether a relationship between the eigenvalues satisfies a predefined threshold;

program instructions configured, in an instance in which the relationship does not satisfy the predefined threshold, to eliminate the template gesture from further consideration for recognition of the input gesture; and

program instructions configured, in an instance in which the relationship satisfies the predefined threshold, to determine a rotation matrix based at least in part on the constructed matrix.