Virtual object

• US 8,509,479 B2
• Filed: 06/16/2009
• Issued: 08/13/2013
• Est. Priority Date: 05/29/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Margolis, Jeffrey
• Primary Examiner(s): Liew, Alex
• Application Number:
  US12/485,711
• Publication Number:
  US 20100303291A1
• Time in Patent Office: 1,519 Days
• Field of Search: 382/103
• US Class Current: 382/103
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

An image of a scene may be observed, received, or captured. The image may then be scanned to determine one or more signals emitted or reflected by an indicator that belongs to an input object. Upon determining the one or more signals, the signals may be grouped together into a cluster that may be used to generate a first vector that may indicate the orientation of the input object in the captured scene. The first vector may then be tracked, a virtual object and/or an avatar associated with the first vector may be rendered, and/or controls to perform in an application executing on the computer environment may be determined based on the first vector.

Claims

1. A computer-implemented method for processing an image of a scene, the computer-implemented method comprising:

receiving the image of the scene;

scanning the image for at least one signal reflected by an object;

grouping the at least one signal reflected by the object in a cluster;

calculating a first vector based on the cluster;

analyzing the first vector to determine a highest and lowest coordinate in a first direction along the first vector;

determining a delta distance from the first vector, the delta distance being determined by subtracting the lowest coordinate in the first direction along the first vector from the highest coordinate in the first direction along the first vector; and

calculating an angle of the object by comparing the delta distance to a known pixel distance of the object in the first direction, the angle of the object indicating an angle at which the object is leaning towards or away from a capture device in the scene.

2. The computer-implemented method of claim 1, wherein grouping the at least one signal into the cluster further comprises distinguishing the at least one signal from a false reading.

3. The computer-implemented method of claim 1, wherein grouping the at least one signal into the cluster further comprises analyzing a location of the at least one signal within the image.

4. The computer-implemented method of claim 3, wherein analyzing the location of the at least one signal further comprises preventing the at least one signal from being grouped in the cluster when a location associated with the at least one signal indicates that a relational distance has been exceeded.

5. The computer-implemented method of claim 1, wherein the first vector is a vector of best fit, and wherein a pixel location of the at least one signal is close to the first vector based on the vector of best fit.

6. The computer-implemented method of claim 1, wherein calculating the first vector based on the cluster further comprises analyzing a location of the at least one signal within the image to determine a highest x coordinate, a lowest x coordinate, a highest y coordinate, and a lowest y coordinate for the first vector.

7. The computer-implemented method of claim 1, wherein the first direction is a y direction, the delta distance is a delta height, the known pixel distance is a known pixel height, and the angle of the object is a pitch angle.

8. The computer-implemented method of claim 7, further comprising:

analyzing the first vector to determine whether the at least one signal that corresponds to a highest y coordinate is of a higher signal strength than the at least one signal that corresponds to a lowest y coordinate;

referencing the pitch angle to indicate that the object is leaning towards the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a higher signal strength than the at least one signal that corresponds to the lowest y coordinate; and

referencing the pitch angle to indicate that the object is leaning away from the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a lower signal strength than the at least one signal that corresponds to the lowest y coordinate.

9. The computer-implemented method of claim 1, wherein the first direction is an x direction, the delta distance is a delta width, the known pixel distance is a known pixel width, and the angle of the object is a yaw angle.

10. The computer-implemented method of claim 9, further comprising:

analyzing the first vector to determine whether the at least one signal that corresponds to a highest x coordinate is of a higher signal strength than the at least one signal that corresponds to a lowest x coordinate;

referencing the yaw angle to indicate that the object is leaning to the right of the capture device in the scene when the at least one signal that corresponds to the highest x coordinate is of a higher signal strength than the at least one signal that corresponds to the lowest x coordinate; and

referencing the yaw angle to indicate that the object is to the left of the capture device in the scene when the at least one signal that corresponds to the highest x coordinate is of a lower signal strength than the at least one signal that corresponds to the lowest x coordinate.

14. The computer-implemented method of claim 1, wherein the object is a user.

15. The computer-implemented method of claim 1, wherein the object is a non-human object.

11. A computer-readable storage medium for processing an image of a scene, the computer-readable medium having stored thereon computer executable instructions comprising:

receiving the image of the scene;

scanning the image for at least one signal reflected by an object;

grouping the at least one signal reflected by the object in a cluster;

calculating a first vector based on the cluster;

analyzing the first vector to determine a highest and lowest coordinate in a first direction along the first vector;

determining a delta distance from the first vector, the delta distance being determined by subtracting the lowest coordinate in the first direction along the first vector from the highest coordinate in the first direction along the first vector; and

calculating an angle of the object by comparing the delta distance to a known pixel distance of the object in the first direction, the angle of the object indicating an angle at which the object is leaning towards or away from a capture device in the scene.

12. The computer-readable storage medium of claim 11, wherein the object is a user.

13. The computer-readable storage medium of claim 11, wherein the object is a non-human object.

20. The computer-readable storage medium of claim 11, wherein the computer executable instructions further comprise:

analyzing the first vector to determine whether the at least one signal that corresponds to a highest y coordinate is of a higher signal strength than the at least one signal that corresponds to a lowest y coordinate;

referencing a pitch angle to indicate that the object is leaning towards the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a higher signal strength than the at least one signal that corresponds to the lowest y coordinate; and

referencing the pitch angle to indicate that the object is leaning away from the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a lower signal strength than the at least one signal that corresponds to the lowest y coordinate.

16. A system for processing an image of a scene comprising:

a capture device, the capture device for capturing the image of the scene;

a processor; and

memory having stored therein computer executable instructions comprising;

receiving the image of the scene;

scanning the image for at least one signal reflected by an object;

grouping the at least one signal reflected by the object in a cluster;

calculating a first vector based on the cluster;

analyzing the first vector to determine a highest and lowest coordinate in a first direction along the first vector;

determining a delta distance from the first vector, the delta distance being determined by subtracting the lowest coordinate in the first direction along the first vector from the highest coordinate in the first direction along the first vector; and

calculating an angle of the object by comparing the delta distance to a known pixel distance of the object in the first direction, the angle of the object indicating an angle at which the object is leaning towards or away from a capture device in the scene.

17. The system of claim 16, wherein the object is a user.

18. The system of claim 16, wherein the object is a non-human object.

19. The system of claim 16, wherein the computer executable instructions further comprise:

analyzing the first vector to determine whether the at least one signal that corresponds to a highest y coordinate is of a higher signal strength than the at least one signal that corresponds to a lowest y coordinate;

referencing a pitch angle to indicate that the object is leaning towards the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a higher signal strength than the at least one signal that corresponds to the lowest y coordinate; and

referencing the pitch angle to indicate that the object is leaning away from the capture device in the scene when the at least one signal that corresponds to the highest y coordinate is of a lower signal strength than the at least one signal that corresponds to the lowest y coordinate.