Gesture detection and compact representation thereof

• US 9,075,443 B2
• Filed: 12/27/2011
• Issued: 07/07/2015
• Est. Priority Date: 12/27/2011
• Status: Active Grant

• Current Assignee: Maxim Integrated Products, Inc. (Analog Devices, Inc.)
• Original Assignee: Maxim Integrated Products, Inc. (Analog Devices, Inc.)
• Inventors: Kettle, Paul J.
• Primary Examiner(s): Johnson, Gerald
• Application Number:
  US13/337,733
• Publication Number:
  US 20130162520A1
• Time in Patent Office: 1,288 Days
• US Class Current: 1/1
• CPC Class Codes: G05B 2219/23021 Gesture programming, camera sees hand, displays it on screen, grasp buttons
• 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 3/0416 Control or interface arrangements specially adapted for digitisers
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text

Abstract

Techniques are described that may be implemented with an electronic device to detect a gesture within a field of view of a sensor and generate a compact data representation of the detected gesture. In implementations, a sensor is configured to detect a gesture and provide a signal in response thereto. An estimator, which is in communication with the sensor, is configured to generate an elliptical representation of the gesture. Multiple coefficients for the compact representation of the gesture can be used to define the ellipse representing the gesture.

Claims

1. An electronic device comprising:

a sensor configured to detect a gesture and provide a signal in response thereto; and

an estimator communicatively coupled to the sensor, the estimator configured to receive the signal from the sensor and generate one or more velocity vectors based upon the gesture, the estimator configured to generate one or more estimated values corresponding to an elliptical representation of the gesture, the one or more estimated values based upon the velocity vectors,

wherein the elliptical representation of the gesture comprises a plurality of coefficients based upon the one or more velocity vectors, the plurality of coefficients comprising at least one of a center coefficient representing a center coordinate of an ellipse within a geographic plane, a first radius coefficient representing a semi-major radius value of the ellipse within the geographic plane, a second radius coefficient representing a semi-minor radius value of the ellipse within the geographic plane, or a theta coefficient representing an orientation of the ellipse within the geographic plane.

2. The electronic device as recited in claim 1, further comprising an illumination source configured to emit light within a limited spectrum of wavelengths, wherein the sensor comprises a photodetector configured to detect light within the limited spectrum of wavelengths for detecting the gesture.

3. The electronic device as recited in claim 1, wherein the estimator is further configured to derive at least one bias offset state.

4. The electronic device as recited in claim 1, wherein the estimator comprises a Kalman Estimator.

5. The electronic device as recited in claim 1, wherein the elliptical representation of the gesture is determined using a Least Squares model.

6. The electronic device as recited in claim 1, wherein the sensor comprises a photodetector configured as at least one of a quad segmented photodetector, a 2×

2 array of photodiodes, or a 4×

4 array of photodiodes.

7. A system comprising:

an illumination source configured to emit light in a limited spectrum of wavelengths;

a sensor configured to detect a gesture within the limited spectrum of wavelengths and provide a signal in response thereto;

a processor communicatively coupled to the sensor, the processor configured to receive the signal from the sensor;

an estimator communicatively coupled to the processor, the estimator configured to generate one or more velocity vectors based upon the signal; and

control programming executable on the processor and configured to generate an elliptical representation of the gesture based upon the velocity vectors,

wherein the elliptical representation of the gesture comprises a plurality of coefficients based upon the one or more velocity vectors, the plurality of coefficients comprising at least one of a center coefficient representing a center coordinate of an ellipse within a geographic plane, a first radius coefficient representing a semi-major radius value of the ellipse within the geographic plane, a second radius coefficient representing a semi-minor radius value of the ellipse within the geographic plane, or a theta coefficient representing an orientation of the ellipse within the geographic plane.

8. The system as recited in claim 7, wherein the estimator is a Kalman Estimator.

9. The system as recited in claim 7, wherein the signal represents one or more characteristics of the detected light comprising at least one of the intensity of the detected light incident upon the photodetector, how long the light was incident upon the photodetector, or the orientation of the detected light incident upon the photodetector.

10. The system as recited in claim 7, further comprising a display configured to display the elliptical representation of the gesture.

11. The system as recited in claim 7, wherein the elliptical representation for the gesture is determined using a Least Squares model.

12. The system as recited in claim 7, wherein the sensor comprises a photodetector configured as at least one of a quad segmented photodetector, a 2×

2 array of photodiodes, or a 4×

4 array of photodiodes.

13. A method comprising:

receiving a signal from a sensor in response to the sensor detecting a gesture occurring within a field of view of the sensor;

estimating one or more velocity vectors based upon the signal; and

estimating one or more values based upon the velocity vectors, the one or more values corresponding to an elliptical representation of the gesture,

wherein the elliptical representation of the gesture comprises a plurality of coefficients based upon the one or more velocity vectors, the plurality of coefficients comprising at least one of a center coefficient representing a center coordinate of an ellipse within a geographic plane, a first radius coefficient representing a semi-major radius value of the ellipse within the geographic plane, a second radius coefficient representing a semi-minor radius value of the ellipse within the geographic plane, or a theta coefficient representing an orientation of the ellipse within the geographic plane.

14. The method as recited in claim 13, further comprising deriving a plurality of coefficients defining the elliptical representation of the gesture.

15. The method as recited in claim 13, wherein estimating one or more values relating to the signal comprises estimating the one or more values relating to the signal using a Kalman Estimator.

16. The method as recited in claim 13, wherein the elliptical representation of the gesture is determined using a Least Squares model.