Human tracking system

Patent metadata

Field	Value
Publication number	US-9821226-B2
Application number	US-201514602333-A
Country	US
Kind code	B2
Filing date	Jan 22, 2015
Priority date	Oct 7, 2009
Publication date	Nov 21, 2017
Grant date	Nov 21, 2017

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.

First claim

What is claimed:

1. A method for estimating a dimension of a joint of a user in a scene, comprising:
receiving, by a computing device comprising a processor and memory, a depth image, the depth image being indicative of the user in the scene;
determining, by the computing device, a plurality of proposed dimensions for the joint of the user in the depth image;
determining, by the computing device, the dimension of the joint based on the plurality of proposed dimensions;
updating, by the computing device, a computer-maintained model that corresponds to the user to have the dimension of the joint, wherein the dimension of the joint comprises a length and a width; and
generating, by the computing device, one or more motions or movements by mapping the updated computer-maintained model.

2. The method of claim 1 , further comprising calculating a mean and a standard deviation for each of the proposed dimensions.

3. The method of claim 1 , further comprising rejecting one or more of the plurality of proposed dimensions that are outside a defined percentage deviation.

4. The method of claim 1 , further comprising determining the dimension of the joint based on an estimator that has a highest ratio between a standard deviation thereof and a number of the plurality of proposed dimensions.

5. The method of claim 1 , wherein the dimension of the joint comprises at least one of length or width.

6. The method of claim 1 , further comprising determining whether the dimension of the joint is correct based on one or more heuristics.

7. A system for estimating a dimension of a joint of a user in a scene, comprising:
one or more memories having stored therein computer-executable instructions; and
one or more processors operable to execute the computer-executable instructions, wherein the computer-executable instructions comprise instructions for performing operations comprising:
receiving a depth image, the depth image being indicative of the user in the scene;
determining a plurality of proposed dimensions for the joint of the user in the depth image;
determining the dimension of the joint based on the plurality of proposed dimensions; and
updating a computer-maintained model that corresponds to the user to have the dimension of the joint, wherein the dimension of the joint comprises a length and a width; and

generating data indicative of one or more motions or movements by mapping the updated computer-maintained model.

8. The system of claim 7 , wherein the operations further comprise rejecting one or more of the plurality of proposed dimensions that are outside a defined percentage deviation.

9. The system of claim 7 , wherein the operations further comprise determining the dimension of the joint based on an estimator that has a highest ratio between a standard deviation thereof and a number of the plurality of proposed dimensions.

10. The system of claim 7 , wherein the dimension of the joint comprises at least one of length or width.

11. The system of claim 7 , wherein the operations further comprise determining whether the dimension of the joint is correct based on one or more heuristics.

12. The system of claim 7 , wherein the operations further comprise calculating a mean for each of the proposed dimensions.

13. The system of claim 7 , wherein the operations further comprise calculating a standard deviation for each of the proposed dimensions.

14. A computer-readable storage device not consisting of only transitory signals, the storage device having stored thereon computer-executable instructions for estimating a dimension of a joint of a user in a scene, wherein the computer-executable instructions comprise instructions for performing operations comprising:
receiving a depth image, the depth image being indicative of the user in the scene;
determining a plurality of proposed dimensions for the joint of the user in the depth image;
determining the dimension of the joint based on the plurality of proposed dimensions; and
updating a computer-maintained model that corresponds to the user to have the dimension of the joint, wherein the dimension of the joint comprises a length and a width; and
generating data indicative of one or more motions or movements by mapping the updated computer-maintained model.

15. The computer-readable storage device of claim 14 , wherein the operations further comprise rejecting one or more of the plurality of proposed dimensions that are outside a defined percentage deviation.

16. The computer-readable storage device of claim 14 , wherein the operations further comprise determining the dimension of the joint based on an estimator that has a highest ratio between a standard deviation thereof and a number of the plurality of proposed dimensions.

17. The computer-readable storage device of claim 14 , wherein the dimension of the joint comprises at least one of length or width.

18. The computer-readable storage device of claim 14 , wherein the operations further comprise determining whether the dimension of the joint is correct based on one or more heuristics.

19. The computer-readable storage device of claim 14 , wherein the operations further comprise calculating a mean for each of the proposed dimensions.

20. The computer-readable storage device of claim 14 , wherein the operations further comprise calculating a standard deviation for each of the proposed dimensions.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Leyvand Tommer
• Lee Johnny
• Peeper Craig
• Stachniak Szymon
• Liu Shao

Classifications

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T7/251

  involving models · CPC title

• G06T7/194

  involving foreground-background segmentation · CPC title

• G06T2207/30196

  Human being; Person · CPC title

• A63F2300/6045

  for mapping control signals received from the input arrangement into game commands · CPC title