Human tracking system

• US 8,861,839 B2
• Filed: 09/23/2013
• Issued: 10/14/2014
• Est. Priority Date: 10/07/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Leyvand, Tommer, Lee, Johnny Chung, Stachniak, Szymon, Peeper, Craig, Liu, Shao
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US14/034,484
• Publication Number:
  US 20140022161A1
• Time in Patent Office: 386 Days
• Field of Search: 382/103, 382/106, 382/154, 348/155
• US Class Current: 382/154
• 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 13/215 comprising means for detecting acoustic signals, e.g. using a microphone
• 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 13/52 involving aspects of the displayed game scene
• CPC Class Codes: A63F 13/833 Hand-to-hand fighting, e.g. martial arts competition A63F13/837 takes precedence
• CPC Class Codes: A63F 2300/1075 using a touch screen
• CPC Class Codes: A63F 2300/5553 user representation in the game field, e.g. avatar
• CPC Class Codes: A63F 2300/6045 for mapping control signals received from the input arrangement into game commands
• CPC Class Codes: A63F 2300/6607 for animating game characters, e.g. skeleton kinematics
• 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: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: G06V 10/34 Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
• CPC Class Codes: G06V 10/426 Graphical representations
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.

Claims

1. A method for tracking a user, the method comprising:

receiving a depth image;

generating a first voxel of a plurality of voxels based on at least one pixel of the depth image that corresponds to a background independent of at least one pixel that corresponds to a human target, the first voxel overlapping another voxel in the plurality of voxels;

removing the first voxel from the plurality of voxels to isolate one or more voxels associated with the human target;

determining a location or position of one or more extremities of the human target based on the one or more voxels associated with the human target; and

adjusting a model based on the location or position of the one or more extremities.

2. The method of claim 1, wherein the model comprises a skeletal model having joints and bones.

3. The method of claim 1, wherein removing the first voxel from the plurality of voxels to isolate one or more voxels associated with the human target comprises:

determining whether an object that is associated with the first voxel is in motion; and

discarding the first voxel in response to determining that the object is not in motion.

4. The method of claim 1, further comprising:

determining dimensions of the one or more extremities, and adjusting at least one joint or bone of the model based on the determined dimensions.

5. The method of claim 1, wherein the one or more extremities comprises:

a head, a centroid, a shoulder, a hip, a leg, an arm, a hand, an elbow, a knee, or a foot.

6. The method of claim 1, further comprising:

processing the adjusted model.

7. The method of claim 1, wherein each of the voxels in the plurality of voxels is generated based on a portion or block of pixels included in the received depth image.

8. The method of claim 1, wherein generating the first voxel of a plurality of voxels comprises:

determining that at least one pixel of a plurality of pixels that are downsampled to generate the first voxel of the plurality of voxels has a valid depth value;

determining that at least one pixel of the plurality of pixels has an invalid depth value; and

generating the first voxel based on the at least one pixel with the valid depth value without using the at least one pixel with the invalid depth value.

9. The method of claim 1, wherein adjusting the model based on the location or position of the one or more extremities comprises:

refining a location of position of the model based on the human target as it appears in the depth image.

10. A computer-readable storage device bearing computer-readable instructions that, when executed on a computer, cause the computer to perform operations comprising:

receiving a depth image;

generating a first voxel of a plurality of voxels based on at least one pixel of the depth image that corresponds to a background independent of at least one pixel that corresponds to a human target, the first voxel overlapping another voxel in the plurality of voxels;

removing the first voxel from the plurality of voxels to isolate one or more voxels associated with the human target;

determining a location or position of one or more extremities of the human target based on the one or more voxels associated with the human target; and

adjusting a model based on the location or position of the one or more extremities.

11. The computer-readable storage device of claim 10, wherein adjusting a model based on the location or position of the one or more extremities comprises:

assigning the location or position of the one or more extremities to a corresponding joint of the model.

12. The computer-readable storage device of claim 10, further bearing computer-readable instructions that, when executed on a computer, cause the computer to perform operations comprising:

determining dimensions of the one or more extremities; and

adjusting at least one joint or bone of the model based on the determined dimensions.

13. The computer-readable storage device of claim 10, wherein the one or more extremities comprises a head, a centroid, a shoulder, a hip, a leg, an arm, a hand, an elbow, a knee, or a foot.

14. The computer-readable storage device of claim 10, further comprising

processing the adjusted model.

15. The computer-readable storage device of claim 14, wherein the first voxel is generated based on a portion or block of pixels included in the received depth image.

16. A system for tracking a model associated with a user, the system comprising:

a capture device that receives a depth image of a scene; and

a memory bearing instructions that, upon execution by a processor, cause the system at least to;

receive the depth image from the capture device;

generate a first voxel of a plurality of voxels based on at least one pixel of the depth image that corresponds to a background independent of at least one pixel that corresponds to a human target, the first voxel overlapping another voxel in the plurality of voxels;

remove the first voxel from the plurality of voxels to isolate one or more voxels associated with the human target;

determine a location or position of one or more extremities of the human target based on the one or more voxels associated with the human target; and

adjust a model based on the location or position of the one or more extremities.

17. The system of claim 16, wherein the first voxel is generated based on a portion or block of pixels included in the received depth image.

18. The system of claim 16, wherein the model is adjusted based on the location or position of the one or more extremities by assigning the location or position of the one or more extremities to at least one corresponding joint of the model.

19. The system of claim 16, wherein the one or more extremities comprises a head, a centroid, a shoulder, a hip, a leg, an arm, a hand, an elbow, a knee, or a foot.

20. The system of claim 16, wherein the instructions that, upon execution by the processor, cause the system at least to remove the first voxel from the plurality of voxels to isolate one or more voxels associated with the human target further cause the system at least to:

determine whether an object that is associated with the first voxel is in motion; and

discard the first voxel in response to determining that the object is not in motion.