Image foreground detection

• US 9,299,004 B2
• Filed: 10/24/2013
• Issued: 03/29/2016
• Est. Priority Date: 10/24/2013
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Lin, Zhe, Mech, Radomir, Wang, Peng
• Primary Examiner(s): Desire, Gregory M
• Application Number:
  US14/062,680
• Publication Number:
  US 20150117784A1
• Time in Patent Office: 887 Days
• US Class Current: 1/1
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/20004 Adaptive image processing
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/162 involving graph-based methods
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

In techniques for image foreground detection, a foreground detection module is implemented to generate varying levels of saliency thresholds from a saliency map of an image that includes foreground regions. The saliency thresholds can be generated based on an adaptive thresholding technique applied to the saliency map of the image and/or based on multi-level segmentation of the saliency map. The foreground detection module applies one or more constraints that distinguish the foreground regions in the image, and detects the foreground regions of the image based on the saliency thresholds and the constraints. Additionally, different ones of the constraints can be applied to detect different ones of the foreground regions, as well as to detect multi-level foreground regions based on the saliency thresholds and the constraints.

Claims

1. A method, comprising:

executing a foreground detection module as software executable instructions to perform;

generating saliency thresholds from a saliency map of an image that includes foreground regions of the image;

applying constraints that distinguish the foreground regions in the image, different ones of the constraints applied in different combinations of the constraints;

detecting one or more of the foreground regions of the image based on the saliency thresholds and the different combinations of the constraints; and

determining an image composition of the image based on the detected one or more foreground regions of the image.

2. The method as recited in claim 1, wherein each of the different combinations of the constraints distinguishes a different one of the foreground regions of the image.

3. The method as recited in claim 1, further comprising:

detecting multi-level foreground regions of the one or more foreground regions based on the saliency thresholds and the different combinations of the constraints.

4. The method as recited in claim 1, further comprising:

generating varying levels of the saliency thresholds from the saliency map of the image.

5. The method as recited in claim 1, further comprising:

generating the saliency thresholds based on an adaptive thresholding technique applied to the saliency map of the image.

6. The method as recited in claim 1, further comprising:

generating the saliency thresholds based on saliency map segmentation.

7. The method as recited in claim 6, wherein the saliency map segmentation is a multi-level segmentation of the saliency map to said generate the saliency thresholds.

8. A computing device, comprising:

a memory configured to maintain an image that includes foreground regions of the image;

a processor to implement a foreground detection module that is configured to;

generate saliency thresholds from a saliency map of the image;

apply constraints that distinguish the foreground regions in the image, different ones of the constraints configured to be applied in different combinations of the constraints;

detect one or more of the foreground regions of the image based on the saliency thresholds and the different combinations of the constraints; and

determine an image composition of the image based on the detected one or more foreground regions of the image.

9. The computing device as recited in claim 8, wherein each of the different combinations of the constraints distinguishes a different one of the foreground regions of the image.

10. The computing device as recited in claim 8, wherein

wherein the foreground detection module is configured to detect multi-level foreground regions of the one or more foreground regions based on the saliency thresholds and the different combinations of the constraints.

11. The computing device as recited in claim 8, wherein the foreground detection module is configured to generate varying levels of the saliency thresholds from the saliency map of the image.

12. The computing device as recited in claim 8, wherein the foreground detection module is configured to generate the saliency thresholds based on an adaptive thresholding technique applied to the saliency map of the image.

13. The computing device as recited in claim 8, wherein the foreground detection module is configured to generate the saliency thresholds based on saliency map segmentation.

14. The computing device as recited in claim 13, wherein the saliency map segmentation is a multi-level segmentation of the saliency map to said generate the saliency thresholds.

15. A computer-readable storage memory device comprising a foreground detection module stored as instructions that are executable and, responsive to execution of the instructions by a computing device, the computing device performs operations of the foreground detection module comprising to:

generate saliency thresholds from a saliency map of an image that includes foreground regions of the image;

apply constraints that distinguish the foreground regions in the image, different ones of the constraints configured to be applied in different combinations of the constraints;

detect one or more of the foreground regions of the image based on the saliency thresholds and the different combinations of the constraints; and

determine an image composition of the image based on the detected one or more foreground regions of the image.

16. The computer-readable storage memory device as recited in claim 15, wherein each of the different combinations of the constraints distinguishes a different one of the foreground regions of the image.

17. The computer-readable storage memory device as recited in claim 15, wherein the computing device further performs operations of the foreground detection module comprising to detect multi-level foreground regions of the one or more foreground regions based on the saliency thresholds and the different combinations of the constraints.

18. The computer-readable storage memory device as recited in claim 15, wherein the computing device further performs operations of the foreground detection module comprising to generate varying levels of the saliency thresholds from the saliency map of the image.

19. The computer-readable storage memory device as recited in claim 15, wherein the computing device further performs operations of the foreground detection module comprising to generate the saliency thresholds based on an adaptive thresholding technique applied to the saliency map of the image.

20. The computer-readable storage memory device as recited in claim 15, wherein the computing device further performs operations of the foreground detection module comprising to generate the saliency thresholds based on saliency map segmentation.