Granted Patent B2

US 10,254,849 · App. 15/933,199 · Granted Apr 9, 2019

Abstract

Claims (48)

1. A system for gesture-recognition, comprising:

an image-capture device for obtaining digital images of an object in 3D space;

a processor-executable analysis module for computationally determining a path of movement of the object based on captured images;

a computer memory for storing a digital representation of the path of movement; and

a processor-executable mode-control module configured for:

interpreting user gestures in accordance with a first mode of operation;

analyzing the path of movement to determine an intent of a user to change modes of operation by:

determining an amount of curvature of the path of movement; and

determining whether a velocity, an acceleration, and a range of motion of movement along the path of movement crosses a threshold to overcome a hysteresis associated with the first mode of operation;

wherein the hysteresis is determined using a physics-based model of the first mode of operation; and

upon determining the intent of the user to change modes of operation, interpreting user gestures in accordance with a second mode of operation.

2. The system of claim 1 , wherein determining the amount of curvature includes determining a maximum distance the path of movement is from a straight line between a starting point and ending point of the path of movement.

3. The system of claim 1 , wherein the mode-control module is configured to analyze the path of movement by determining a direction of curvature of the path of movement.

4. The system of claim 3 , wherein determining the direction of curvature of the path of movement includes determining which side of a virtual reference plane a midpoint of the path of movement is on.

5. The system of claim 1 , wherein the mode-control module is configured to determine whether the path of movement intersects a virtual reference plane wherein the virtual reference plane is created based on analyzing a path of movement of one or more prior gestures to determine an intent of a user in making the prior gestures.

6. The system of claim 5 , wherein the virtual reference plane is created based on analyzing a path of movement of a prior gesture to determine an intent of a user to create a virtual reference plane in making the prior gesture.

7. The system of claim 1 , wherein the mode-control module is configured to analyze a second path of movement to determine the intent of the user to perform a multi-object gesture and change the modes of operation, the mode-control module subsequently interpreting user gestures in accordance with the second mode of operation based on the intent.

8. The system of claim 1 , wherein the mode-control module is further configured to determine the intent of the user to change modes based on prior gestures.

9. The system of claim 1 , wherein the mode-control module is configured to implement a hysteresis-like effect between modes in which gestures falling below a threshold for small or slow gestures are interpreted as user intent to stay within a current mode and gestures with similarly shaped paths performed with a range of motion or velocity greater than a threshold are interpreted as user intent to switch modes.

10. A method of computationally recognizing and interpreting gestures, the method comprising:

obtaining, using an image-capture device, digital images of a real-world object in 3D space;

computationally determining a path of movement of the real-world object based on captured images;

storing, in a computer memory, a digital representation of the path of movement;

interpreting user gestures in accordance with a first mode of operation;

analyzing the path of movement to determine an intent of a user to change modes of operation by:

determining an amount of curvature of the path of movement; and

determining whether a velocity, an acceleration, and a range of motion of movement along the path of movement crosses a threshold to overcome a hysteresis associated with the first mode of operation;

wherein the hysteresis is determined using a physics-based model of the first mode of operation; and

upon determining the intent of the user to change modes of operation, interpreting user gestures in accordance with a second mode of operation.

11. The method of claim 10 , wherein determining the amount of curvature includes determining a maximum distance the path of movement is from a straight line between a starting point and ending point of the path of movement.

12. The method of claim 10 , wherein analyzing the path of movement comprises determining a direction of curvature of the path of movement.

13. The method of claim 12 , wherein determining the direction of curvature of the path of movement includes determining which side of a virtual reference plane a midpoint of the path of movement is on.

14. The method of claim 10 , wherein analyzing the path of movement comprises determining whether the path of movement intersects a virtual reference plane wherein the virtual reference plane is created based on analyzing a path of movement of one or more prior gestures to determine an intent of a user in making the prior gestures.

15. The method of claim 14 , wherein the virtual reference plane is created based on analyzing a path of movement of a prior gesture to determine an intent of a user to create a virtual reference plane in making the prior gesture.

16. The method of claim 10 , further comprising analyzing a second path of movement to determine the intent of the user to perform a multi-object gesture and changing from the first mode of operation to the second mode of operation based on the intent.

17. The method of claim 10 , wherein the intent of the user to change modes is inferred based on prior gestures.

18. The method of claim 10 , wherein analyzing the path of movement further comprises implementing a hysteresis-like effect between modes in which gestures falling below a threshold for small or slow gestures are interpreted as user intent to stay within a current mode and gestures with similarly shaped paths performed with a range of motion or velocity greater than a threshold are interpreted as user intent to switch modes.

19. A non-transitory computer readable storage medium impressed with computer program instructions to computationally interpret gestures, which instructions, when executed on a processor, implement a method comprising:

obtaining, using an image-capture device, digital images of a real-world object in 3D space;

computationally determining a path of movement of the real-world object based on captured images;

storing, in a computer memory, a digital representation of the path of movement;

interpreting user gestures in accordance with a first mode of operation;

analyzing the path of movement to determine an intent of a user to change modes of operation by:

determining an amount of curvature of the path of movement; and

determining whether a velocity, an acceleration, and a range of motion of movement along the path of movement crosses a threshold to overcome a hysteresis associated with the first mode of operation;

wherein the hysteresis is determined using a physics-based model of the first mode of operation; and

upon determining the intent of the user to change modes of operation, interpreting user gestures in accordance with a second mode of operation.

20. The non-transitory computer readable storage medium of claim 19 , wherein analyzing the path of movement further comprises implement a hysteresis-like effect between modes in which gestures falling below a threshold for small or slow gestures are interpreted as user intent to stay within a current mode and gestures with similarly shaped paths performed with a range of motion or velocity greater than a threshold are interpreted as user intent to switch modes.

Assignments (11)