Depth gradient based tracking

• US 9,367,731 B2
• Filed: 05/23/2012
• Issued: 06/14/2016
• Est. Priority Date: 05/23/2012
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Vodrahalli, Kiran N.
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): Gilliard, Delomia L
• Application Number:
  US13/977,022
• Publication Number:
  US 20150193655A1
• Time in Patent Office: 1,483 Days
• Field of Search: 382/103, 382/154
• US Class Current: 1/1
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06T 2200/28 involving image processing hardware
• CPC Class Codes: G06T 2207/10016 Video; 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 2207/30241 Trajectory
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06T 7/269 using gradient-based methods
• CPC Class Codes: G06V 40/113 Recognition of static hand signs
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: H04N 5/2226 Determination of depth image, e.g. for foreground/background separation determining depth by image analysis in general G06T7/50; segmentation by image analysis in general G06T7/10

Abstract

Systems and methods may provide for determining depth gradient information based on a depth map of a scene, and determining a threshold parameter. Additionally, a hand may be identified in the scene based on the depth gradient information and the threshold parameter. Moreover, motion information such as time-based, color-based and/or frame-based information can be used to track hand gestures in the scene.

Claims

1. A method comprising:

determining a first set of depth gradient information based on a first depth map;

determining a first threshold parameter corresponding to a first depth gradient value;

determining a second set of depth gradient information based on a second depth map;

determining a second threshold parameter corresponding to a second depth gradient value;

identifying a hand based on the first set of depth gradient information and the first threshold parameter;

classifying a surface based on the second set of depth gradient information and the second threshold parameter;

determining motion information for the hand;

tracking one or more hand gestures based on the motion information; and

generating an outline of the hand and the surface in one or more images of a scene containing the hand and the surface.

2. The method of claim 1, wherein the surface is classified as flat.

3. The method of claim 1, wherein the surface is classified as non-manmade.

4. The method of claim 1, further including:

obtaining the first depth map from a memory location associated with a short-range camera; and

obtaining the second depth map from a memory location associated with a long-range camera.

22. The at least one non-transitory computer-readable medium of claim 1, wherein the one or more instructions are to configure a processor to generate an outline of the hand in an image of a scene containing the hand.

5. A system comprising:

a memory device to store a first depth map;

a gradient logic circuit to determine a first set of depth gradient information based on the first depth map;

a threshold logic circuit to determine a first threshold parameter corresponding to a first depth gradient value;

a hand detection logic circuit to identify a hand based on the first set of depth gradient information and the first threshold parameter; and

a display device to output an image of a scene containing the hand.

6. The system of claim 5, further including a display logic circuit to generate an outline of the hand in the image.

7. The system of claim 5, further including a hand motion logic circuit to determine motion information for the hand and track one or more hand gestures based on the motion information.

8. The system of claim 5, further including a short-range camera, wherein the gradient logic circuit is to obtain the first depth map from a memory location associated with the short-range camera.

9. The system of claim 5, wherein the gradient logic circuit is to determine a second set of depth gradient information based on a second depth map and the threshold logic circuit is to determine a second threshold parameter corresponding to a second depth gradient value, the system further including a classification logic to classify a surface based on the second set of depth gradient information.

10. The system of claim 9, further including a display logic circuit to generate an outline of the surface, wherein the classification logic circuit is to classify the surface as flat.

11. The system of claim 9, wherein the classification logic circuit is to classify the surface as non-manmade.

12. The system of claim 9, further including a short range camera and a long-range camera, wherein the gradient logic circuit is to obtain the first depth map from a memory location associated with the short range camera and the second depth map from a memory location associated with the long-range camera.

13. An apparatus comprising:

a gradient logic circuit to determine a first set of depth gradient information based on a first depth map;

a threshold logic circuit to determine a first threshold parameter corresponding to a first depth gradient value; and

a hand detection logic circuit to identify a hand based on the first set of depth gradient information and the first threshold parameter.

14. The apparatus of claim 13, further including a display logic circuit to generate an outline of the hand in an image of a scene containing the hand.

15. The apparatus of claim 13, further including a hand motion logic circuit to determine motion information for the hand and track one or more hand gestures based on the motion information.

16. The apparatus of claim 13, wherein the gradient logic circuit is to obtain the first depth map from a memory location associated with a short-range camera.

17. The apparatus of claim 13, wherein the gradient logic circuit is to determine a second set of depth gradient information based on a second depth map and the threshold logic circuit is to determine a second threshold parameter corresponding to a second depth gradient, the apparatus further including a classification logic circuit to classify a surface based on the second set of depth gradient information and the second threshold parameter.

18. The apparatus of claim 17, further including a display logic circuit to generate an outline of the surface, wherein the classification logic circuit is to classify the surface as flat.

19. The apparatus of claim 17, wherein the classification logic circuit is to classify the surface as non-manmade.

20. The apparatus of claim 17, wherein the gradient logic circuit is to obtain the first depth map from a memory location associated with a short-range camera and the second depth map from a memory location associated with a long-range camera.

21. At least one non-transitory computer-readable medium comprising one or more instructions that when executed on a processor configure the processor to:

determine a first set of depth gradient information based on a first depth map;

determine a first threshold parameter corresponding to a first depth gradient value; and

identify a hand based on the first set of depth gradient information and the first threshold parameter.

23. The at least one non-transitory computer-readable medium of claim 21, wherein the one or more instructions are to configure a processor to:

determine motion information for the hand; and

track one or more hand gestures based on the motion information.

24. The at least one non-transitory computer-readable medium of claim 21, wherein the one or more instructions are to configure a processor to obtain the first depth map from a memory location associated with a short-range camera.

25. The at least one non-transitory computer-readable medium of claim 21, wherein the one or more instructions are to configure a processor to:

determine a second set of depth gradient information based on a second depth map;

determine a second threshold parameter corresponding to a second depth gradient value; and

classify a surface based on the second set of depth gradient information and the second threshold parameter.

26. The at least one non-transitory computer-readable medium of claim 25, wherein the one or more instructions are to configure a processor to classify the surface as flat and are to generate an outline of the surface.

27. The at least one non-transitory computer-readable medium of claim 25, wherein the one or more instructions are to configure a processor to classify the surface as non-manmade.

28. The at least one non-transitory computer-readable medium of claim 25, wherein the one or more instructions are to configure a processor to obtain the first depth map from a memory location associated with a short-range camera and the second depth map from a memory location associated with a long-range camera.