SELECTIVE MOTOR CONTROL CLASSIFICATION

• US 20110221770A1
• Filed: 03/15/2010
• Published: 09/15/2011
• Est. Priority Date: 03/15/2010
• Status: Active Grant

• Current Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Kruglick, Ezekiel
• Granted Patent: US 8,614,663 B2
• Time in Patent Office: Days
• US Class Current: 345/633
• 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

Techniques for detecting and classifying motion of a human subject are generally described. More particularly, techniques are described for detecting and classifying motion as either a broad selection or a precise selection to facilitate interaction with augmented reality (AR) systems. An example may include detecting a motion of human and repeatedly analyzing a step response associated with the motion to determine one or more of a peak time t_p, an estimated overshoot magnitude M_p, a damping ratio ζ of the step response and/or one or more polynomial poles of the step response. Such information may be useful in classifying the motion as either a precise selection or as a broad selection.

Claims

1. A method of identifying selective motor control associated with motion of a human subject, the method comprising:

detecting at least a portion of the motion associated with the human subject;

repeatedly analyzing a step response associated with the detected motion to determine a peak time t_p, the peak time t_p being a time in which a magnitude of the step response reaches a peak;

estimating an overshoot magnitude M_p, the overshoot magnitude M_p being the difference of the magnitude of the step response at the peak time t_p and a target magnitude of the step response; and

classifying the motion as either a precise selection or as a broad selection based, at least in part, on the overshoot magnitude M_p.

2. The method of claim 1, the method further comprising repeating classifying the motion if the motion is classified as a broad selection.

3. The method of claim 1, wherein analyzing the step response further comprises determining a damping ratio ζ

of the step response; and

wherein classifying the motion is further based, at least in part, on the damping ratio ζ

.

4. The method of claim 3, the method further comprising repeating classifying the motion if the motion is classified as a broad selection.

5. The method of claim 1, wherein analyzing the step response further comprises determining two or more polynomial poles based, at least in part, on one or more of the magnitude of the step response, a frequency of the step response and the damping ratio ζ

, and wherein classifying the motion is further based, at least in part, on the two or more polynomial poles.

6. The method of claim 5, the method further comprising repeating classifying the motion if the motion is classified as a broad selection.

7. The method of claim 5, wherein the classification is weighted towards a precise selection when a polynomial pole is determined to have a negative real component.

8. The method of claim 5, wherein the classification is weighted towards a broad selection when a polynomial pole is determined to have at least one of a positive real component and a zero real component.

9. The method of claim 5, wherein the classification is weighted towards a precise selection when the step response is determined to have a frequency less than 3 Hz.

10. The method of claim 5, wherein the classification is weighted towards a broad selection when the step response is determined to have a frequency greater than 3 Hz.

11. The method of claim 1, wherein the motion associated with the human subject comprises one or more of a motion associated with a human hand, a motion associated with a human finger and/or a motion associated with a human eye.

12. The method of claim 1, wherein the motion associated with the human subject comprises one or more of a motion associated with a gesture and/or a motion associated with an interaction.

13. The method of claim 1, wherein detecting a motion of at least a portion of the human subject comprises one or more of:

reading the motion on a touch screen display;

tracking the motion using a mouse;

tracking the motion using a camera; and

/or

tracking the motion using an eye tracking device.

14. The method of claim 1, wherein the motion comprises an interaction with an augmented reality system comprising a plurality of objects within a plurality of selectable object types, each selectable object type corresponding to a different level of refinement.

15. The method of claim 14, further comprising upon classifying the motion as a broad selection, refining one of the plurality of selectable object types to a selectable object type having a more detailed level of refinement.

16. The method of claim 14, further comprising upon classifying the motion as a precise selection, selecting the selectable object type.

22. The method of claim 1, wherein analyzing the step response further comprises determining two or more polynomial poles based, at least in part, on one or more of a magnitude of the step response, a frequency of the step response and the damping ratio ζ

, and wherein classifying the motion is further based, at least in part, on the two or more polynomial poles.

17. A computer program product, comprising:

a signal-bearing medium comprising computer-readable instructions stored thereon, which, when executed by one or more processing units, operatively enable a computing platform to;

receive a signal representative of a motion associated with at least a portion of a human subject;

repeatedly analyze a step response associated with the signal representative of the motion to determine one or more of a peak time t_p of the step response, an estimated overshoot magnitude M_p of the step response, a damping ratio ζ

of the step response and one or more polynomial poles of the step response; and

classify the motion as either a precise selection or as broad selection based, at least in part, on one or more of the peak time t_p, the estimated overshoot magnitude M_p, the damping ratio ζ and

/or the two or more polynomial poles.

18. The computer program product of claim 17, wherein the signal representative of a motion associated with at least a portion of a human subject is generated by one or more of a hand position sensor, a finger position sensor, a foveated gaze detector and/or eye tracker.

19. A computing device adapted to detect selective motor control, comprising:

a motion tracking component configured to generate a signal representative of at least a portion of a motion associated with a human subject;

a step response analysis component configured to repeatedly analyze a step response associated with the signal to determine one or more of a peak time t_p of the step response, an estimated overshoot magnitude M_p of the step response, a damping ratio ζ

of the step response and one or more polynomial poles of the step response; and

a motion classification component configured to classify the motion as either a precise selection or a broad selection based, at least in part, on one or more of the peak time t_p, the estimated overshoot magnitude M_p, the damping ratio ζ and

/or the two or more polynomial poles.

20. The computing device of claim 19, wherein the motion classification component is further configured to repeat the classifying operation until the motion is classified as a precise selection.

21. A method of identifying selective motor control associated with motion of a human subject, the method comprising:

detecting at least a portion of the motion associated with the human subject;

repeatedly analyzing a step response associated with the detected motion to determine a damping ratio ζ

of the step response; and

classifying the motion as either a precise selection or as a broad selection based, at least in part, on the damping ratio ζ

.