Method and apparatus for model-based recovery of packet loss errors

• US 8,813,158 B2
• Filed: 07/11/2013
• Issued: 08/19/2014
• Est. Priority Date: 04/24/2009
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Pratt, James, Sullivan, Marc, Crowe, Keith
• Primary Examiner(s): Lin, Jason K
• Application Number:
  US13/940,078
• Publication Number:
  US 20130329813A1
• Time in Patent Office: 404 Days
• Field of Search: None
• US Class Current: 725/116
• CPC Class Codes: H04N 19/86 involving reduction of coding artifacts, e.g. of blockiness
• CPC Class Codes: H04N 19/895 in combination with error concealment
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59

Abstract

A media processor having a controller operable to recognize a portion of a video stream in an interactive television network having video compression artifacts corresponding to a stored model and perform model-based video correction of the portion recognized using synthetically generated images of objects in a captured video scene. Other embodiments are disclosed.

Claims

1. A method, comprising:

recognizing, by a set top box comprising a processor, a portion of a video stream in an Internet Protocol TV network having video compression artifacts corresponding to a stored model, the stored model including an image or a video model of an image background;

performing, by the set top box, model-based video correction of the portion recognized using synthetically generated images of objects in a captured video scene; and

delivering, by the set top box, to a presentation device a corrected portion of the video stream over a low bit rate connection,

wherein the model-based video correction corresponds to synthetic replacement of the artifacts according to a stored model of replacement images,

wherein recognizing the portion of the video stream further comprises recognizing, within a captured video, a predetermined amount of compression artifacts for the portion of the video stream for an object having a stored corresponding model for the object, and

wherein the model-based video correction is a physical model based enhancement to a video image; and

creating a partially synthetic image of a face to correct a portion of a video stream having video compression artifacts corresponding to a stored model of the face.

2. The method of claim 1, wherein the stored model comprises images of grass, faces, skies, or mountains.

3. The method of claim 1, comprising creating unrecognizable but visually acceptable synthesized images of individuals in a background of a video share stream.

4. The method of claim 3, comprising creating unrecognizable images of individuals in a background of a video share stream sufficient to avoid a right of publicity claim.

5. The method of claim 1, wherein the set top box contains a library of stored models, and wherein the presentation device corresponds to a cellular phone.

6. The method of claim 1, wherein a server contains a library of stored models retrieved by the set top box.

7. The method of claim 1, wherein the set top box uses a digital video recorder as a buffer for temporarily storing a corrected video stream.

8. The method of claim 1, comprising storing the corrected portion of the video stream at the set top box and forwarding the corrected portion of the video stream to a mobile phone.

9. A tangible computer-readable storage device, comprising computer instructions which, when executed by a processor, cause the processor to perform operations comprising:

recognizing within a captured video, a predetermined amount of compression artifacts for a portion of video for an object having a stored corresponding model for the object, the stored model including an image or a video model of an image background; and

synthesizing video using model-based video correction to provide a higher quality image for correcting defects in the captured video,

wherein the model-based video correction corresponds to synthetic replacement of artifacts in the captured video according to a stored model of replacement images, and

wherein the captured video includes compression artifacts from video that have been compressed; and

creating a partially synthetic image of a face to correct a portion of a video stream having video compression artifacts corresponding to a stored model of the face.

10. The tangible computer-readable storage device of claim 9, wherein the operations further comprise recognizing a portion of a video stream in an internet protocol television network having video compression artifacts corresponding to a stored model.

11. The tangible computer-readable storage device of claim 10, wherein the operations further comprise synthetically generating images of objects to correct defects in a captured video scene using model-based video correction of the portion recognized.

12. The tangible computer-readable storage device of claim 9, wherein the operations further comprise delivering a corrected portion of the video stream over a low bit rate connection.

13. The tangible computer-readable storage device of claim 9, wherein the stored model comprises images of grass, faces, skies, or mountains.

14. The tangible computer-readable storage device of claim 9, wherein the operations further comprise storing the corrected portion of the video stream and forwarding the corrected portion of the video stream to a mobile phone.

15. The tangible computer-readable storage device of claim 9, wherein the operations further comprise storing the corrected portion of the video stream at a set top box in an internet protocol television network and forwarding the corrected portion of the video stream to a mobile phone.

16. A media processor, comprising:

a memory to store instructions; and

a controller coupled to the memory, wherein responsive to executing the instructions, the controller performs operations comprising;

recognizing a portion of a video stream in an interactive television network having video compression artifacts corresponding to a stored model, the stored model including an image or a video model of an image background;

performing model-based video correction of the portion recognized using synthetically generated images of objects to correct defects in a captured video scene,

wherein the model-based video correction corresponds to synthetic replacement of the artifacts according to a stored model of replacement images, and

wherein the controller recognizes, within a captured video, a predetermined amount of compression artifacts for a portion of video for an object having a stored corresponding model for the object;

creating a partially synthetic image of an object to correct a portion of a video stream having video compression artifacts corresponding to a stored model of the object;

storing the corrected portion of the video stream; and

combining the corrected portion with a remaining portion of the video stream to form a corrected video stream.

17. The media processor of claim 16, wherein the operations further comprise delivering the corrected portion of the video stream over a low bit rate connection.

18. The media processor of claim 16, wherein the operations further comprise forwarding the corrected portion of the video stream to a mobile phone.

19. The media processor of claim 16, wherein the operations further comprise creating unrecognizable but visually acceptable synthesized images of objects in a background of a video share stream.

20. The media processor of claim 16, wherein the stored model comprises images of grass, faces, skies, or mountains.