Method and apparatus for adaptive exposure bracketing, segmentation and scene organization

• US 10,721,448 B2
• Filed: 03/15/2013
• Issued: 07/21/2020
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Golden Edge Holding Corporation
• Original Assignee: Edge Technologies, Inc
• Inventors: El Dokor, Tarek, Cluster, Jordan, King, Joshua
• Primary Examiner(s): Ren, Zhubing
• Application Number:
  US13/831,638
• Publication Number:
  US 20140267612A1
• Time in Patent Office: 2,685 Days
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: H04N 23/743 Bracketing, i.e. taking a series of images with varying exposure conditions
• CPC Class Codes: H04N 23/88 for colour balance, e.g. white-balance circuits or colour temperature control

Abstract

A method, system and computer program are provided that present a real-time approach to Chromaticity maximization to be used in image segmentation. The ambient illuminant in a scene may be first approximated. The input image may then be preprocessed to remove the impact of the illuminant, and approximate an ambient white light source instead. The resultant image is then choma-maximized. The result is an adaptive Chromaticity maximization algorithm capable of adapting to a wide dynamic range of illuminations. A segmentation algorithm is put in place as well that takes advantage of such an approach. This approach also has applications in HDR photography and real-time HDR video.

Claims

1. A method for imaging a scene comprising the steps of:

determining a camera response function based upon one or more images captured with a camera;

synthetically creating profiles of one or more pixels of the one or more images at different exposures;

determining an exposure of the one or more pixels in one or more of the one or more images resulting in a maximized chroma in accordance with at least the determined camera response function and one or more perceptual parameters resulting in color consistency;

imaging the scene at the exposure resulting in the maximized chroma; and

determining a hue associated with the one or more pixels at the exposure resulting in the maximized chroma.

2. The method of claim 1, where in the step of maximizing chroma in an image further comprises the step of employing a set of rolling exposure images to track and compute a max chromaticity.

3. The method of claim 1, wherein the maximizing of chroma maintains color consistency between images.

4. The method of claim 1, further comprising the step of defining color consistency as a hue that is associated with max chromaticity.

5. A method for imaging a scene comprising the steps of:

determining a camera response function based upon one or more images captured with a camera;

segmenting one or more regions of interest within the one or more captured images;

synthetically creating profiles of one or more pixels of the one or more images at different exposures;

determining an exposure of the one or more pixels in the one or more images resulting in maximized chroma in each of the one or more regions of interest in accordance with the determined camera response function;

imaging the scene at the exposure resulting in the maximized chroma for one or more of the regions of interest; and

determining a hue associated with the one or more pixels at the exposure resulting in the maximized chroma.

6. The method of claim 5, further comprising the step of using an ambient illuminant approximator to minimize one or more effects of one or more light sources on the imaging of the scene.

7. The method of claim 6, further comprising the step of tracking color/hue consistency by modeling perceptual elements through the combination of illuminant approximation as well as Chromaticity maximization.

8. The method of claim 5, further comprising the step of segmenting the image based on combining simulated/estimated exposure settings and color/texture/motion features.

9. The method of claim 5, further comprising the step of creating a depth map based on segmentation, combining simulated exposure settings with features of color, texture and motion.

10. A method for imaging a scene comprising the steps of:

determining a camera response function based upon one or more images captured with a camera;

segmenting one or more regions of interest within the one or more captured images;

synthetically creating profiles of one or more pixels of the one or more images comprising the one or more regions of interest at different exposures;

determining an exposure of the one or more pixels in the one or more images resulting in maximized chroma in each of the one or more regions of interest in accordance with the determined camera response function;

imaging the scene at each exposure resulting in a maximized chroma for each of the one or more of the regions of interest; and

generating a composite depth map employing the images generated for each region of interest imaged at the exposure setting resulting in the maximized chroma for that region of interest.

11. The method of claim 10, further comprising the step of using an ambient illuminant approximator to minimize one or more effects of one or more light sources on the imaging of the scene.

12. The method of claim 11, further comprising the step of tracking color/hue consistency by modeling perceptual elements through the combination of illuminant approximation as well as Chromaticity maximization.

13. The method of claim 10, wherein the step of segmenting the image is based on combining simulated/estimated exposure settings and color/texture/motion features.

14. The method of claim 10, wherein the depth map is further generated based on segmentation, combining simulated exposure settings with features of color, texture and motion.