CONTEXT AWARE MOVEMENT RECOGNITION SYSTEM

• US 20170192521A1
• Filed: 01/04/2017
• Published: 07/06/2017
• Est. Priority Date: 01/04/2016
• Status: Active Grant

• Current Assignee: Texas A&M University System
• Original Assignee: Texas A&M University System
• Inventors: Jafari, Roozbeh, Wu, Jian
• Granted Patent: US 10,678,337 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 2203/0381 Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• 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: G06F 3/038 Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry

Abstract

A movement recognition system includes a feature extraction circuit and a classification circuit that is orientation independent. The feature extraction circuit is configured to receive a plurality of acceleration or angular velocity measurements from a sensor or multiple sensors that include a three dimensional (3D) accelerometer and 3D gyroscope. Each of the measurements is taken at different times. The feature extraction circuit is also configured to determine a difference between a first of the measurements and each other of the measurements. The classification circuit is configured to classify a movement of an object attached to the sensor irrespective of an orientation of the sensor on the object utilizing a signal recognition technique based on the difference between the first of the measurements and each other of the measurements.

Claims

1. A movement recognition system, comprising:

a feature extraction circuit configured to;

receive a plurality of acceleration or angular velocity measurements from a sensor that includes a three dimensional (3D) accelerometer and a 3D gyroscope, each of the measurements taken at different times; and

determine a difference between a first of the measurements and each other of the measurements; and

a classification circuit configured to classify a movement of an object attached to the sensor irrespective of an orientation of the sensor on the object utilizing a signal recognition technique based on the difference between the first of the measurements and each other of the measurements.

2. The movement recognition system of claim 1, wherein the movement is a reversible movement and the classification circuit is further configured to classify the reversible movement based on an amplitude of acceleration or rotational velocity of the sensor.

3. The movement recognition system of claim 1, further comprising a direction detection circuit configured to receive a plurality of magnetic field measurements surrounding the sensor, receive temporal alignment information from the classification circuit, and determine a direction of the sensor or the movement based on templates for the classified movement.

4. The movement recognition system of claim 3, wherein the direction detection circuit is further configured to determine the direction of the sensor or the movement by interpolating between two direction templates for the classified movement.

5. The movement recognition system of claim 3, further comprising a location detection circuit configured to determine a location of the sensor.

6. The movement recognition system of claim 5, further comprising a context detection circuit configured to determine which one of a plurality of target objects the sensor is interacting based on the location of the sensor, the direction of the sensor or the movement, and a location of the target objects.

7. The movement recognition system of claim 6, wherein the context detection circuit is further configured to generate and transmit a control signal to the one target object the sensor is interacting to control the one target object based on the classified movement.

8. The movement recognition system of claim 1, wherein the classification circuit is further configured to determine consistent aspects of a stored classification template and inconsistent aspects of the stored classification template and mark the consistent aspects of the stored classification template and inconsistent aspects of the stored classification template in the stored classification template.

9. The movement recognition system of claim 8, wherein the classification circuit is configured to classify the movement by matching the difference between the first of the measurements and each other of the measurements to the consistent aspects of the stored classification template while ignoring the inconsistent aspects of the stored classification template.

10. A non-transitory computer-readable medium storing instructions that when executed on a computing system cause the computing system to:

receive a plurality of acceleration or angular velocity measurements from a sensor that includes a three dimensional (3D) accelerometer and 3D gyroscope, each of the measurements taken at different times;

determine a difference between a first of the measurements and each other of the measurements; and

classify a movement of an object attached to the sensor irrespective of an orientation of the sensor on the object utilizing a signal recognition technique based on the difference between the first of the measurements and each other of the measurements.

11. The computer-readable medium of claim 10, wherein movement is a reversible movement and the instructions further cause the computing system to classify the reversible movement based on an amplitude of acceleration or rotational velocity of the sensor.

12. The computer-readable medium of claim 10, wherein the instructions further cause the computing system to:

receive a plurality of magnetic field measurements surrounding the sensor;

receive temporal alignment information; and

determine a direction of the sensor or the movement based on templates for the classified movement.

13. The computer-readable medium of claim 12, wherein the instructions further cause the computing system to:

determine a location of the sensor; and

determine which one of a plurality of target objects the sensor is interacting based on the location of the sensor, the direction of the sensor or the movement, and a location of the target objects.

14. The computer-readable medium of claim 13, wherein the instructions further cause the computing system to:

generate a control signal to control the one target object based on the classified movement; and

transmit the control signal to the one target object.

15. The computer-readable medium of claim 12, wherein the instructions cause the computing system to classify the movement by:

identifying consistent aspects of stored movement information for the movement;

identifying inconsistent aspects of the stored movement information; and

matching the difference between the first of the measurements and each other of the measurements to the consistent aspects of the stored movement information while ignoring the inconsistent aspects of the stored movement information.

16. A method for context aware movement recognition comprising:

receiving a plurality of acceleration or angular velocity measurements from a sensor that includes a three dimensional (3D) accelerometer and 3D gyroscope, each of the measurements taken at different times;

determining a difference between a first of the measurements and each other of the measurements; and

classifying a movement of an object attached to the sensor irrespective of an orientation of the sensor on the object utilizing a signal recognition technique based on the difference between the first of the measurements and each other of the measurements.

17. The method of claim 16, wherein the movement is a reversible movement and classifying the reversible movement of the object is based on an amplitude of acceleration or rotational velocity of the sensor.

18. The method of claim 16, further comprising:

receiving a plurality of magnetic field measurements surrounding the sensor;

receiving temporal alignment information; and

determining a direction of the sensor or the movement based on a template for the classified movement.

19. The method of claim 18, further comprising:

determining a location of the sensor; and

determining which one of a plurality of target objects the sensor is interacting based on the location of the sensor, the direction of the sensor or the movement, and a location of the target objects.

20. The method of claim 19, further comprising:

generating a control signal to control the one target object based on the classified movement;

transmitting the control signal to the one target object; and

in response to the one target object receiving the control signal, altering a state of the one target object.