Model based compositing

• US 20060244764A1
• Filed: 06/27/2006
• Published: 11/02/2006
• Est. Priority Date: 10/15/1997
• Status: Active Grant

• Current Assignee: Hanger Solutions, LLC (IP Investments Group LLC)
• Original Assignee: Planet Electric Incorporated
• Inventors: Ahmad, Subutai
• Granted Patent: US 7,663,647 B2
• Time in Patent Office: Days
• US Class Current: 345/629
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: H04N 5/272 Means for inserting a foreground image in a background image, i.e. inlay, outlay

Abstract

Digitally compositing an object from an input image onto a destination image is disclosed. The object is composited from an image having an arbitrary or non-uniform colored background containing some non-static elements onto a destination image with reduced effects from shadows cast by the object and with reduced gaps or holes within the object. The effect of shadows emanating from the object is reduced so that the composited object in the destination image contains only the object clearly outlined by the object'"'"'s physical boundaries without the effect of shadows cast by the object.

Claims

1. A computer-implemented digital video object compositing method of reducing the effect of shadows cast by the object comprising:

comparing the brightness of an input image that contains an object to the brightness of an input image that does not contain the object;

determining whether hue values of the input image that contains the object are within hue tolerances of the input image that does not contain the object;

determining whether portions of the input image that contains the object contain shadows cast by the object; and

adjusting portions of an alpha image that correspond to portions of the input image that contains the object, wherein the portions of the input image contain shadows cast by the object thereby conveying to the alpha image information on which portions of the input image that contains the object are shadows cast by the object.

2. A method as recited in claim 1 further including assigning ranks to the input image that contains the object based on differences in brightness between the input image that contains the object and the input image that does not contain the object.

3. A method as recited in claim 1 further including assigning ranks to the input image that does not contain the object based on differences in brightness between the input image that does not contain the object and the input image that contains the object.

4. A method as recited in claim 1 further including comparing the brightness of the input image that contains the object to a predetermined factor of the brightness of the input image that does not contain the object.

5. A computer-readable medium including program instructions implementing the process of claim 1.

6. A computer-implemented system for reducing the effect of shadows cast by an object digitally composited onto a destination image comprising:

a brightness comparator for comparing the brightness of an input image that contains an object to the brightness of an input image that does not contain the object;

a hue analyzer for determining whether hue values of the input image that contains the object are within hue tolerances of the input image that does not contain the object;

a shadow detector for determining whether portions of the input image that contains the object contain shadows cast by the object; and

an image modifier for adjusting portions of an alpha image that correspond to portions of the input image that contains the object, wherein the portions of the input image contain shadows cast by the object thereby conveying to the alpha image information on which portions of the input image that contains the object are shadows cast by the object.

7. A system as recited in claim 6 further comprising a rank assigner for assigning ranks to the input image that contains the object based on differences in brightness between the input image that contains the object and the input image that does not contain the object.

8. A system as recited in claim 7 wherein the rank assigner assigns ranks to the input image that does not contain the object based on differences in brightness between the input image that does not contain the object and the input image that contains the object.

9. A system as recited in claim 6 wherein the brightness comparator compares the brightness of the input image that contains the object to a predetermined factor of the brightness of the input image that does not contain the object.

10. A computer-implemented system for reducing the effect of shadows cast by a object digitally composited onto a destination image, the system comprising:

means for comparing the brightness of an input image that contains a object to the brightness of an input image that does not contain the object;

means for determining whether hue values of the input image that contains the object are within hue tolerances of the input image that does not contain the object;

means for determining whether portions of the input image that contains the object contain shadows cast by the object; and

means for adjusting portions of an alpha image that correspond to portions of the input image that contains the object, wherein the portions of the input image contain shadows cast by the object thereby conveying to the alpha image information on which portions of the input image that contains the object are shadows cast by the object.

11. A system as recited in claim 10 further comprising means for assigning ranks to the input image that contains the object based on differences in brightness between the input image that contains the object and the input image that does not contain the object.

12. A system as recited in claim 10 further comprising means for assigning ranks to the input image that does not contain the object based on differences in brightness between the input image that does not contain the object and the input image that contains the object.

13. A system as recited in claim 10 further comprising means for comparing the brightness of the input image that contains the object to a predetermined factor of the brightness of the input image that does not contain the object.