Foreground subject detection

• US 8,929,668 B2
• Filed: 06/28/2013
• Issued: 01/06/2015
• Est. Priority Date: 11/29/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dedhia, Bhaven, Leyvand, Tommer
• Primary Examiner(s): Do, Anh
• Application Number:
  US13/931,615
• Publication Number:
  US 20130287257A1
• Time in Patent Office: 557 Days
• Field of Search: 382/103, 382/173, 382/118, 382/191, 382/181, 382/224, 345/156, 345/157, 345/158, 348/580, 348/218.1, 348/208.13, 359/463, 273/348.1, 273/409
• US Class Current: 382/224
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20072 Graph-based image processing
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/162 involving graph-based methods
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

Classifying pixels in a digital image includes receiving a primary image from a primary image sensor. The primary image includes a plurality of primary pixels. Depth information from a depth sensor is also received. The depth information and the primary image are cooperatively used to identify whether a primary pixel images a foreground subject or a background subject.

Claims

1. A method of classifying pixels in a digital image, the method comprising:

receiving a primary image from a primary image sensor, the primary image including a plurality of primary pixels;

receiving depth information from a depth sensor, the depth information useable to determine a depth of a subject imaged by a primary pixel; and

cooperatively using the primary image and the depth information to identify whether the primary pixel images a foreground subject or a background subject.

2. The method of claim 1, where depth information is useable to determine depth of subjects imaged by each of the plurality of primary pixels.

3. The method of claim 2, where the primary image and the depth information are cooperatively used to identify whether each of the primary pixels images the foreground subject or the background subject.

4. The method of claim 1, where the depth information includes a depth image from a time-of-flight depth camera.

5. The method of claim 1, where the depth information includes a depth image from a structured light depth camera.

6. The method of claim 1, where the depth information includes a depth image from stereoscopic depth cameras.

7. The method of claim 1, where the primary image includes a color image from a visible light camera.

8. The method of claim 1, where the primary image includes a grayscale image from a visible light camera.

9. The method of claim 1, where the primary image includes an infrared image from an infrared camera.

10. The method of claim 1, where cooperatively using the primary image and the depth information includes:

producing a segmentation map from the depth information, the segmentation map including a plurality of estimated foreground pixels and a plurality of estimated background pixels;

producing a trimap from the segmentation map, the trimap matching the segmentation map but including a plurality of test pixels at one or more boundaries between estimated foreground pixels and estimated background pixels; and

refining each of the test pixels to either a confirmed foreground pixel or a confirmed background pixel based on an analysis of primary pixels registered to test pixels.

11. The method of claim 10, further comprising refining each of the estimated foreground pixels not identified as test pixels to confirmed foreground pixels, and refining each of the estimated background pixels not identified as test pixels to confirmed background pixels.

12. The method of claim 11, where the primary pixels registered to the confirmed foreground pixels are useable without the primary pixels registered to the confirmed background pixels.

13. The method of claim 11, further comprising producing a segmented image including the primary pixels registered to the confirmed foreground pixels but without the primary pixels registered to the confirmed background pixels.

14. The method of claim 13, where pixels of the segmented image registered to the confirmed background pixels are transparent pixels.

15. The method of claim 13, where pixels of the segmented image registered to the confirmed background pixels are from another image.

16. The method of claim 13, where one or more pixels of the segmented image registered to the confirmed foreground pixels are smoothed.

17. The method of claim 16, where the one or more pixels of the segmented image registered to the confirmed foreground pixels are smoothed via anti-aliasing.

18. The method of claim 16, where the one or more pixels of the segmented image registered to the confirmed foreground pixels are smoothed via alpha-blending.

19. A method of classifying pixels in a digital image, the method comprising:

receiving a primary image from one or more primary image sensors, the primary image including a plurality of primary pixels;

receiving one or more secondary images from one or more secondary sensors, the one or more secondary images useable to estimate a depth of a subject imaged by a primary pixel; and

cooperatively using the primary image and the one or more secondary images to identify whether the primary pixel images a foreground subject.

20. A computing system, comprising:

an input for receiving a primary image from a primary image sensor, the primary image including a plurality of primary pixels;

an input for receiving depth information from a depth sensor, the depth information useable to determine a depth of a subject imaged by a primary pixel; and

a logic subsystem for identifying whether the primary pixel images a foreground subject or a background subject.