VISUAL TARGET TRACKING

• US 20100197399A1
• Filed: 01/30/2009
• Published: 08/05/2010
• Est. Priority Date: 01/30/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Geiss, Ryan M.
• Granted Patent: US 8,267,781 B2
• Time in Patent Office: Days
• US Class Current: 463/32
• CPC Class Codes: A63F 13/213 comprising photodetecting means, e.g. cameras, photodiodes or infrared cells A63F13/219, A63F13/655 take precedence
• CPC Class Codes: A63F 13/428 involving motion or position input signals, e.g. signals representing the rotation of an input controller or a player's arm motions sensed by accelerometers or gyroscopes
• CPC Class Codes: A63F 2300/1093 using visible light
• CPC Class Codes: A63F 2300/6607 for animating game characters, e.g. skeleton kinematics
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/251 involving models

Abstract

A method of tracking a target includes receiving an observed depth image of the target from a source and obtaining a posed model of the target. The model is rasterized into a synthesized depth image, and the pose of the model is adjusted based, at least in part, on differences between the observed depth image and the synthesized depth image.

Claims

1. A method of electronic gaming, the method comprising;

representing a human game player with a machine-readable model configured for adjustment into a plurality of different poses;

receiving an observed depth image of the human game player from a source;

rasterizing the machine-readable model of the human game player into a synthesized depth image;

adjusting a pose of the machine-readable model based, at least in part, on differences between the observed depth image and the synthesized depth image; and

using the pose of the machine-readable model, as adjusted, as a parameter to affect an element of game play.

2. The method of claim 1, where the observed depth image includes a plurality of observed pixels, one or more observed pixels including an observed depth value indicating a distance between the source and a portion of the human game player corresponding to that observed pixel.

3. The method of claim 1, where the synthesized depth image includes a plurality of synthesized pixels, one or more synthesized pixels including a synthesized depth value indicating a distance between the source and a portion of the human game player represented by that synthesized pixel.

4. The method of claim 1, where the synthesized depth image includes a plurality of synthesized pixels, one or more synthesized pixels including a body-part index indicating a portion of the human game player to which that synthesized pixel corresponds.

5. The method of claim 1, where adjusting the pose of the machine-readable model is based on a difference between an observed depth value of an observed pixel and a synthesized depth value of a corresponding synthesized pixel.

6. A method of tracking a target, the method comprising:

receiving an observed depth image of the target from a source;

obtaining a model of the target, the model having a pose;

rasterizing the model into a synthesized depth image;

adjusting the pose of the model based, at least in part, on differences between the observed depth image and the synthesized depth image.

7. The method of claim 6, where the observed depth image includes a plurality of observed pixels, one or more observed pixels including an observed depth value indicating a distance between the source and a portion of the target corresponding to that observed pixel.

8. The method of claim 6, where the source includes a depth camera.

9. The method of claim 6, where the source includes stereo cameras.

10. The method of claim 6, where the model includes a plurality of body parts adjustably connected by a plurality of joints.

11. The method of claim 6, where the model includes a plurality of skeletal members adjustably connected by a plurality of joints.

12. The method of claim 6, where the model includes a wireframe mesh including a plurality of polygons adjustably connected at polygonal edges.

13. The method of claim 6, where the synthesized depth image includes a plurality of synthesized pixels, one or more synthesized pixels including a synthesized depth value indicating a distance between the source and a portion of the target represented by that synthesized pixel.

14. The method of claim 6, where the synthesized depth image includes a plurality of synthesized pixels, one or more synthesized pixels including a body-part index indicating a portion of the target to which that synthesized pixel corresponds.

15. The method of claim 6, where the synthesized depth image includes a plurality of synthesized pixels, each synthesized pixel including a target index indicating a target to which that synthesized pixel corresponds.

16. The method of claim 6, where adjusting the pose of the model is based on a difference between an observed depth value of an observed pixel and a synthesized depth value of a corresponding synthesized pixel.

17. The method of claim 6, where adjusting the pose of the model is further based on a body-part index of an observed pixel that differs from a corresponding synthesized pixel.

18. The method of claim 6, where adjusting the pose of the model includes applying one or more forces to force-receiving locations of the model and allowing the model to move responsive to such forces.

19. The method of claim 6, where adjusting the pose of the model includes rectifying the model in accordance with one or more constraints.

20. A computing system, comprising:

a source configured to capture depth information;

a logic subsystem operatively connected to the source; and

a data-holding subsystem holding instructions executable by the logic subsystem to;

receive an observed depth image of a target from the source;

obtain a model of the target, the model having a pose;

rasterize the model into a synthesized depth image;

adjust the pose of the model based, at least in part, on differences between the observed depth image and the synthesized depth image.