SYSTEM AND METHOD FOR PROCESSING VIDEO IMAGES

• US 20080259073A1
• Filed: 03/11/2008
• Published: 10/23/2008
• Est. Priority Date: 09/23/2004
• Status: Abandoned Application

• Current Assignee: Conversion Works Incorporated
• Original Assignee: Conversion Works Incorporated
• Inventors: Wallner, Natascha, Lowe, Danny D., Spooner, David A., Keech, Gregory R., Simmons, Christopher L., Birtwistle, Steven, Adelman, Jonathan
• Application Number:
  US12/046,267
• Publication Number:
  US 20080259073A1
• Time in Patent Office: Days
• US Class Current: 345/419
• CPC Class Codes: G06T 15/20 Perspective computation
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: H04N 13/111 Transformation of image signals corresponding to virtual viewpoints, e.g. spatial image interpolation
• CPC Class Codes: H04N 13/275 from 3D object models, e.g. computer-generated stereoscopic image signals
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals

Abstract

Embodiments use point clouds to form a three dimensional image of an object. The point cloud of the object may be formed from analysis of two dimensional images of the object. Various techniques may be used on the point cloud to form a 3D model of the object which is then used to create a stereoscopic representation of the object.

Claims

1. A method for forming a three dimensional image of an object comprising:

providing at least two images of the object, wherein a first image has a different view of the object than a second image;

forming a point cloud for the object using the first image and the second image; and

creating the three dimensional image of the object using the point cloud.

2. The method of claim 1, wherein the forming the point cloud comprises:

selecting a plurality of points of the object in the images.

3. The method of claim 2, wherein the selecting is performed by a user.

4. The method of claim 2, wherein the selecting is performed by a computer.

5. The method of claim 2, wherein the plurality of points comprises at least one of a feature of the object, an edge of the object, a shape of the object, a color change of the object, and a change of texture of the object.

6. The method of claim 1, wherein forming the point cloud comprises:

sweeping the object with an energy emitter; and

recording distance and placement information for a plurality of points of the object.

7. The method of claim 1, wherein the images are of a scene and the object is located with the scene.

8. The method of claim 1, wherein the images are frames of a movie.

9. The method of claim 1, wherein the point cloud is a static point cloud and each point comprises X, Y, Z coordinates.

10. The method of claim 1, wherein the point cloud is a dynamic point cloud and each point comprises X, Y, Z coordinates and movement data for the point.

11. The method of claim 1, wherein the creating comprises:

using a triangular mesh technique to form the object.

12. The method of claim 1, wherein the creating comprises:

using a gradient technique to form the object.

13. The method of claim 1, wherein the creating comprises:

using a depth map to form the object.

14. The method of claim 1, further comprising:

placing the three dimensional image of the object into an image of a scene.