Systems and methods for detecting a tilt angle from a depth image

• US 8,290,249 B2
• Filed: 03/06/2012
• Issued: 10/16/2012
• Est. Priority Date: 05/01/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mathe, Zsolt, Marais, Charles Claudius
• Primary Examiner(s): Mariam, Daniel
• Application Number:
  US13/413,531
• Publication Number:
  US 20120163669A1
• Time in Patent Office: 224 Days
• Field of Search: 382/103, 382/154, 382/190, 382/289, 348/42, 348/48, 348/50, 348/169
• US Class Current: 382/154
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.

Claims

1. A device, the device comprising:

a processor; and

a memory communicatively coupled to the processor when the device is operational, the memory bearing processor-executable instructions that, when executed on the processor, cause the device to at least;

receive the depth image, the depth image being captured by a camera component;

scan a human target in the depth image;

select a first portion of pixels of the human target based on a location of an upper body part of the human target;

select a second portion of pixels of the human target based on a location of a lower body part of the human target; and

calculate a tilt angle of the camera component based on the first and second portions of pixels.

2. The device of claim 1, wherein the instructions that, when executed upon the processor, cause the device to at least scan the human target in the depth image further cause the device to at least:

determine a location and a measurement of one or more body parts of the human target.

3. The device of claim 2, wherein the location of the one or more body parts comprises a location and a measurement of shoulders of the human target, a location and measurement of hips of the human target, or a location and a measurement of knees of the human target.

4. The device of claim 1, wherein the

location of the upper body part of the human target comprises a location of the shoulders;

and

wherein the location of the lower body part of the human target comprises a midpoint between a location of the hips and knees.

5. The device of claim 1, wherein each of the pixels in the first portion and second portion of pixels has a depth value associated therewith.

6. The device of claim 5, wherein the instructions that, when executed upon the processor, cause the device to at least calculate the tilt angle based on the first and second portion of pixels further cause the device to at least:

calculate a first value associated with a vertical distance between the first and second portions.

7. The device of claim 6, wherein the instructions that, when executed upon the processor, cause the device to at least calculate the tilt angle based on the first and second portion of pixels further cause the device to at least:

calculate a first average depth value using the depth value for each pixel in the first portion;

calculate a second average depth value using the depth value for each pixel in the second portion;

subtract the second average depth value from the first average depth value to calculate a second value.

8. The device of claim 7, wherein the instructions for calculating the tilt angle based on the scanned human target further comprise instructions for:

calculating an arctangent of the second value divided by the first value to determine the tilt angle.

9. A computer-readable storage device having stored thereon computer executable instructions for detecting a tilt, that when executed on a computer, cause the computer to perform operations comprising:

receiving the depth image from;

scanning a human target in the depth image to determine a location of at least an upper body part and a lower body part;

selecting a first portion of pixels of the human target based on a location an upper body part of the human target;

selecting a second portion of pixels of the human target based on a location of a lower body part of the human target; and

calculating a tilt angle of the camera component based on the first and second portions of pixels.

10. The computer-readable storage device of claim 9, wherein the upper body part comprises shoulders of the human target and the lower body part comprises a midpoint between the hips and the knees of the human target.

11. The computer-readable storage device of claim 9, wherein each of the pixels in the first portion and second portion of pixels has a depth value associated therewith.

12. The computer-readable storage device of claim 11, wherein calculating the tilt angle based on the first and second portions of pixels comprises:

calculating a first value associated with a vertical distance between the first and second portions.

13. The computer-readable storage device of claim 12, wherein calculating the tilt angle based on the first and second portions of pixels comprises:

calculating a first average depth value using the depth value for at least one pixel in the first portion;

calculating a second average depth value using the depth value for at least one pixel in the second portion;

subtracting the second average depth value from the first average depth value to calculate a second value.

14. The computer-readable storage device of 13 wherein calculating the tilt angle based on the first and second portions of pixels comprises:

calculating an arctangent of the second value divided by the first value to determine the tilt angle.

15. A method for detecting a tilt, the method comprising:

receiving, by a computer, a depth image of a scene, the depth image being captured by a capture device;

determining, by the computer, a location of an upper body part and a lower body part of human target in the depth image;

selecting, by the computer, a first portion of pixels of the human target associated with the upper body part and a second portion of pixels of the human target associated with the lower body part; and

calculating, by the computer, a tilt angle of the camera component using the first portion of pixels and the second portion of pixels.

16. The method of claim 15, wherein each of the pixels in the first portion and second portion of pixels has a depth value associated therewith.

17. The method of claim 16, wherein calculating the tilt angle comprises:

calculating the tilt angle using the first portion of pixels and the second portion of pixels by calculating a first value associated with the vertical distance between the first and second portions.

18. The method of claim 17, wherein calculating the tilt angle using the first portion of pixels and the second portion of pixels by comprises:

calculating a first average depth value using the depth value for each pixel in the first portion;

calculating a second average depth value using the depth value for each pixel in the second portion;

subtracting the second average depth value from the first average depth value to calculate a second value.

19. The method of 18, wherein calculating the tilt angle using the first portion of pixels and the second portion of pixels by:

calculating an arctangent of the second value divided by the first value to determine the tilt angle.