System and methods for depth regularization and semiautomatic interactive matting using RGB-D images

Patent metadata

Field	Value
Publication number	US-10089740-B2
Application number	US-201514642637-A
Country	US
Kind code	B2
Filing date	Mar 9, 2015
Priority date	Mar 7, 2014
Publication date	Oct 2, 2018
Grant date	Oct 2, 2018

Abstract

Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.

First claim

What is claimed is:

1. An array camera, comprising:
a plurality of cameras that capture images of a scene from different viewpoints;
memory containing an image processing pipeline application;
wherein the image processing pipeline application direct the processor to:
capture a set of images using a group of cameras from the plurality of cameras;
receive (i) an image comprising a plurality of pixel color values for pixels in the image and (ii) an initial depth map corresponding to the depths of the pixels within the image, wherein the initial depth map is generated using the set of images; and
regularize the initial depth map into a dense depth map using pixels for which depth is known to estimate depths of pixels for which depth is unknown by using affine combinations of the depths of nearby known pixels to compute depths for the unknown pixel depths, wherein regularizing the initial depth map into the dense depth map further comprises performing Laplacian matting to compute a Laplacian L, wherein the Laplacian matting is optimized by solving a reduced linear system for depth values only in unknown regions;
wherein regularizing the initial depth map into the dense depth map further comprises:
 finding an approximate dense depth map using a diffusion process where L D is a diffusion Laplacian constructed such that each pixel is connected to a plurality of its surrounding neighbors using spatial proximity;
pruning the Laplacian L based upon the approximate dense depth map; and
detecting and correcting depth bleeding across edges by computing a Laplacian residual R based upon the pruned Laplacian and removing incorrect depth values based on the Laplacian residual R; and
using the dense depth map to perform image-based rendering.

2. The array camera of claim 1 , wherein pruning the Laplacian L comprises:
for each pair i,j of pixels in affinity matrix A, determine if i and j have depth differences beyond a threshold; and
if the difference is beyond the threshold, purge the pair i,j within the affinity matrix A.

3. The array camera of claim 1 , wherein the computing the Laplacian residual R comprises computing R=Lz* where z* is the regularized depth map, wherein removing incorrect depth values comprises identifying regions where R>0.

4. The array camera of claim 1 , wherein a pixel for which depth is unknown is a pixel that has a confidence value below a particular threshold regarding the accuracy of the depth.

5. The array camera of claim 4 , wherein the image processing application further directs the processor to use a binary confidence map C that indicates whether a depth at a given pixel is confident.

6. The array camera of claim 5 , wherein the confidence map C is obtained by a thresholded gradient of intensity of an input image.

7. The array camera of claim 5 , wherein the confidence map C is defined at texture and object edges within the image.

8. The array camera of claim 5 , wherein the confidence map C is a sparse mn×mn diagonal matrix whose diagonal entries are binary confidence values.

9. The array camera of claim 5 , wherein the image processing application further directs the processor to compute a new confidence map whenever the Laplacian residual R is greater than a threshold.

10. The array camera of claim 1 , wherein the image processing application further directs the processor to utilize the regularized dense depth map to perform depth-based segmentation that can be dilated to create a trimap.

11. The array camera of claim 1 , wherein an unknown pixel's depth is estimated as a weighted average of depths of k-nearest super-pixels.

12. The array camera of claim 11 , where the weights are derived as a function of distance of an RGBxy feature of a pixel from super-pixel centroids.

13. The array camera of claim 1 , wherein the Laplacian matting is optimized by solving a reduced linear system for alpha values only in unknown regions.

14. The array camera of claim 1 , wherein the image processing application further directs the processor:
determine an object of interest to be extracted from the image;
generate an initial trimap using the dense depth map and the object of interest to be extracted from the image; and
apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.

15. The array camera of claim 1 , wherein the image processing pipeline application directs the processor to generate a trimap based on the regularized depth map.

16. The array camera of claim 2 , wherein the Laplacian matting is a kNN-based (K nearest-neighbor) Laplacian that pairs similar pixels without regards to their depth when constructing the affinity matrix A and Laplacian L.

17. The array camera of claim 1 , wherein the image processing application further directs the processor to detect and correct depth bleeding across edges.

Assignees

• Fotonation Ltd

Inventors

• Srikanth Manohar
• Ramamoorthi Ravi
• Venkataraman Kartik
• Chatterjee Priyam

Classifications

• H04N5/2621 Primary

  Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability · CPC title

• G06T2207/20096

  Interactive definition of curve of interest · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• H04N13/15

  for colour aspects of image signals · CPC title

• H04N13/271

  wherein the generated image signals comprise depth maps or disparity maps · CPC title