Method and apparatus for monoscopic to stereoscopic image conversion

• US 6,031,564 A
• Filed: 07/07/1997
• Issued: 02/29/2000
• Est. Priority Date: 07/07/1997
• Status: Expired due to Fees

• Current Assignee: Reveo, Inc.
• Original Assignee: Reveo, Inc.
• Inventors: Ma, Kelvin, Swift, David
• Primary Examiner(s): Le, Vu
• Application Number:
  US08/889,713
• Time in Patent Office: 967 Days
• Field of Search: 348/42-44, 348/96-97, 348/51, 348/571, 348/578, 348/580, 382/154, 345/328, 345/419, 345/326
• US Class Current: 348/43
• CPC Class Codes: G06T 15/10 Geometric effects
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: H04N 13/122 Improving the 3D impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues H04N13/128 takes precedence
• CPC Class Codes: H04N 13/189 Recording image signals; Reproducing recorded image signals
• CPC Class Codes: H04N 13/221 using the relative movement between cameras and objects
• CPC Class Codes: H04N 13/257 Colour aspects
• CPC Class Codes: H04N 13/261 with monoscopic-to-stereoscopic image conversion
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals
• CPC Class Codes: H04N 2013/0092 Image segmentation from stereoscopic image signals

Abstract

A method and apparatus for converting a monoscopic image with one perspective to a stereoscopic image with two perspectives is provided. A foreground object is identified and outlined. The depth of the object is endowed with depth information. The second perspective is generated by image warping. Alternate embodiments comprising additional features, such as removing redundant frames, which reduce the necessary computation are also provided.

Claims

1. A method for converting a monoscopic image comprising a first perspective to a stereoscopic image comprising said first perspective and a second perspective, said monoscopic image having at least one foreground object and at least one background object, said method comprising the steps of:

identifying at least one object in said monoscopic image;

outlining said at least one object to generate a first vector outline;

endowing said at least one object with depth information;

generating a second vector outline for said at least one object based on said depth information;

if said at least one object is determined to be said background object relative to said at least one foreground object and said at least one object overlaps said at least one foreground object, clipping said second vector outline to generate a clipped vector outline; and

generating said second perspective by image warping said at least one object.

2. The method of claim 1 wherein said generating step comprises:

shifting points on said outline of said at least one object from said first perspective to said second perspective; and

shifting points within said outline from said first perspective to said second perspective.

3. The method of claim 1 wherein said generating step is performed on a sequence of successive frames of said monoscopic images to produce a stereoscopic presentation.

4. The method of claim 3 wherein said sequence of successive frames is derived from motion picture film.

5. The method of claim 3 wherein said sequence of successive frames is derived from video media.

6. The method of claim 5 wherein said sequence of successive frames contains redundant frames as a result of conversion from motion picture film.

7. The method of claim 6 further comprising a preliminary step of:

removing said redundant frames from said sequence of successive frames.

8. The method of claim 3 wherein said method is performed only on selected frames of said sequence of successive frames, thereby reducing the number of frames that must be converted to stereoscopic images, thereby reducing computation time while providing a sequence of images which appear to be stereoscopic.