IP Library Granted Patent US 7,340,094
Granted Patent B2
US 7,340,094 · App. 11/640,293 · Granted Mar 4, 2008

Image segmentation by means of temporal parallax difference induction

Assignee: Vision III Imaging, Inc.
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,340,094
App. No.
11/640,293
Granted
Mar 4, 2008
Kind
B2
Abstract

An image compositing and compression method based on the creation and processing of parallax differences in motion photography. A parallax scanning MOE lens creates discrete parallax differences in the objects in the recorded scene that are perceived by the viewer as enhanced texture and depth when displayed. Using parallax differences in a captured scene, a computer can detect objects for the purpose of creating image compositing mattes. This method allows matte passes to be filmed on location at the time of principal photography, thereby saving costly additional blue/green stage production shoot days associated with traveling matte techniques. In addition, because the mattes are based on parallax scan differences in the recorded scene and not on a uniform color and luminance process, certain conflicting scene subject colors will not have to be avoided. Also, because the matte scenes are recorded on location, the lighting in each of the various elements matches in the final composited image.

Claims (18)

1. A method of generating, from a succession of images, a succession of mattes which correspond to scene object layers, respectively, comprising the steps of:

generating a flow map, for one or more of the succession of images, that specifies how pixels move between adjacent images in the succession of images;

separating groups of pixels, for the one or more succession of images, into distinct regions by combining pixels with similar flow values; and

generating a matte for the distinct regions of the one or more of the succession of images to provide the succession of mattes.

2. The method of claim 1 , further comprising selecting and removing selected mattes from the succession of mattes.

3. The method of claim 2 , further comprising using a computer or control device to automatically select the mattes.

4. The method of claim 2 further comprising manually selecting the mattes.

5. The method of claim 1 , further comprising performing region edge processing on at least one matte of the succession of mattes.

6. The method of claim 1 , further comprising:

generating color layers for the one or more of the succession of images by multiplying one or more of the succession of mattes by corresponding original image information.

7. The method of claim 6 , further comprising:

inserting additional image layers into the color layers generated for the one or more of the succession of images.

8. The method of claim 6 , further comprising:

ordering the color layers.

9. The method of claim 6 , further comprising:

generating a composite image by adding together at least two of the color layers corresponding to the one or more of the succession of images.

10. The method of claim 9 , further comprising:

generating a final composite image by adjusting the composite image for brightness or contrast.

Assignments (2)
SECURITY INTEREST Recorded Aug 16, 2017
From: VISION III IMAGING, INC.
To: ECKHART G. GROHMANN REVOCABLE TRUST OF 1985
Reel/Frame 043309/0125 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2016
From: MAYHEW, CHRISTOPHER A.; MARTIN, MICHAEL B.
To: VISION III IMAGING, INC.
Reel/Frame 040514/0817 →
Continuity (3)
Division 1018887200 · Jul 5, 2002
Provisional Application 6030314100 · Jul 6, 2001
Related Publication 20070098258A1 · May 3, 2007