SYSTEM AND METHOD FOR 3D SPACE-DIMENSION BASED IMAGE PROCESSING

• US 20070285419A1
• Filed: 05/01/2007
• Published: 12/13/2007
• Est. Priority Date: 07/30/2004
• Status: Active Grant

• Current Assignee: Jungo Connectivity Ltd. (Cisco Systems, Inc.)
• Original Assignee: Extreme Reality Ltd.
• Inventors: Givon, Dor
• Granted Patent: US 8,237,775 B2
• Time in Patent Office: Days
• US Class Current: 345/420
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 2201/12 Acquisition of 3D measurements of objects
• CPC Class Codes: H04N 13/167 Synchronising or controlling image signals
• CPC Class Codes: H04N 13/189 Recording image signals; Reproducing recorded image signals
• CPC Class Codes: H04N 13/275 from 3D object models, e.g. computer-generated stereoscopic image signals

Abstract

Apparatus for 3D representation of image data, comprises: a structure identifier for identifying structures in motion within image data, and a skeleton insertion unit, which associates three-dimensional skeleton elements with the identified structures. The skeleton elements are able to move with the structures to provide a three-dimensional motion and structure understanding of said image data which can be projected back onto the input data. As well as individual elements, complex bodies can be modeled by complex skeletons having multiple elements. The skeleton elements themselves can be used to identify the complex objects.

Claims

1. Method for 3D representation of image data, comprising:

identifying structures within said image data, and associating three-dimensional skeleton elements with said structures, such that said skeleton elements are able to move with said structures to provide a three-dimensional understanding of said structures.

2. Method according to claim 1, comprising recognizing from said image data a complex body made up of a plurality of interrelated structures and inserting three-dimensional skeleton elements into said interrelated structures such as to define three-dimensional movement relations between said skeleton elements.

3. Method according to claim 2, further comprising using said insertion of skeleton elements in order to recognize a complex body.

4. Method according to claim 2, further comprising analyzing relative movement within said image data thereby to provide three-dimensional movement relation definitions.

5. Method according to claim 2, further comprising storing a plurality of predetermined skeletons comprised of basic-shapes for use with recognized complex bodies.

6. Method according to claim 1, wherein said inserting a skeleton element comprises transforming said skeleton element onto an extracted structure from said image using interconnected basic skeleton shapes.

7. Method according to claim 1, wherein said inserting a skeleton element comprises deforming a skeleton element into an extracted structure from said image.

8. Method according to claim 1, wherein said inserting a skeleton element comprises applying texture to a skeleton element.

9. Method according to claim 1, further comprising tracking respective structures at a first level and for moving corresponding skeleton elements at a second level.

10. Method according to claim 9, further comprising tracking respective skeleton elements at said second level and calculating the deviation of the structure at said first level.

11. Method according to claim 1, further comprising animating said image data by applying motion to said skeleton elements.

12. Method according to claim 1 comprising selecting a first viewpoint and projecting using said three dimensional skeleton elements onto a 2D plane associated with said first viewpoint.

13. Method according to claim 12, comprising selecting a second viewpoint and projecting using said three-dimensional skeleton elements onto a 2D plane associated with said second viewpoints.

14. Method according to claim 13, comprising selecting said first and second viewpoints to provide stereoscopic vision.

15. Method according to claim 1, further comprising capturing input data onto said skeleton elements, thereby to provide three-dimensional motion capture.

16. Method according to claim 1, comprising storing data relative to said skeleton elements, thereby to provide three-dimensional image data compression and recording.

17. Method according to claim 1, further comprising forming images at a given resolution by fitting interpolated pixels at said given resolution over said skeleton elements.

18. Method according to claim 1, further comprising the generation of a two-dimensional image from the three-dimensional motion and structure understanding.

19. Method according to claim 18, further comprising the modification of the color and texture parameters of the image color.

20. Recording method for recording image data with depth information, comprising:

identifying Non-Rigid structures within said image data, associating three-dimensional skeleton elements with said structures, such that said skeleton elements are able to move with said structures to provide a three-dimensional motion and three dimensional model with texture of said image data, and recording said input data in relation to at least one of said skeleton elements and a background.

21. Compression method for compressing image data with depth information, comprising:

identifying Non-Rigid structures within said image data, associating three-dimensional skeleton elements with said structures, such that said skeleton elements are able to move with said structures to provide a three-dimensional motion and three dimensional model with texture of said image data, and outputting said input data in relation to at least one of said skeleton elements and a background, such as to provide compression of said input data and to provide depth information thereof.