Consistent generation of media elements across media

Patent metadata

Field	Value
Publication number	US-11470404-B2
Application number	US-202016883907-A
Country	US
Kind code	B2
Filing date	May 26, 2020
Priority date	May 26, 2020
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

An example method performed by a processing system includes retrieving a digital model of a media element from a database storing a plurality of media elements, wherein the media element is to be inserted into a scene of an audiovisual media, rendering the media element in the scene of the audiovisual media, based on the digital model of the media element and on metadata associated with the digital model to produce a rendered media element, wherein the metadata describes a characteristic of the media element and a limit on the characteristic, and inserting the rendered media element into the scene of the audiovisual media.

First claim

What is claimed is:

1. A method comprising:
retrieving, by a processing system including at least one processor, a digital model of a media element from a database storing a plurality of media elements, wherein the media element is to be depicted in a scene of an audiovisual media;
rendering, by the processing system, the media element based on the digital model of the media element and on metadata associated with the digital model to produce a rendered media element, wherein the metadata describes a characteristic of the media element and a limit on the characteristic; and
inserting, by the processing system, the rendered media element into the scene of the audiovisual media, wherein the method further comprises, prior to the retrieving:
learning, by the processing system, the characteristic of the media element based on an analysis of a plurality of samples comprising at least one of: a plurality of images depicting the media element, a plurality of audio segments depicting the media element, or a plurality of text segments depicting the media element;
learning, by the processing system, the limit on the characteristic of the media element based on an analysis of the plurality of samples; and
encoding, by the processing system, the characteristic and the limit on the characteristic in the metadata.

2. The method of claim 1 , wherein the media element is at least one of: an individual or an object.

3. The method of claim 1 , wherein the characteristic is at least one of: a physical characteristic of the media element, an audio characteristic of the media element, a contextual characteristic of the media element, or a behavioral characteristic of the media element.

4. The method of claim 1 , wherein the limit defines a range of values of the characteristic.

5. The method of claim 4 , wherein the rendering comprises:
applying, by the processing system, a production effect to the digital model, such that a value of the characteristic in the rendered media element falls within the range of values.

6. The method of claim 5 , wherein the production effect alters a physical appearance of the digital model.

7. The method of claim 5 , wherein the production effect alters a sound of the digital model.

8. The method of claim 5 , further comprising:
applying, by the processing system, the production effect to other portions of the scene of the audiovisual media in addition to the rendered media element.

9. The method of claim 1 , wherein the metadata further describes a limitation on a use of the media element.

10. The method of claim 1 , wherein the metadata further describes a fee for using the media element.

11. The method of claim 1 , wherein the metadata further describes a set of alternatives, wherein each alternative in the set of alternatives is consistent with the limit on the characteristic.

12. The method of claim 1 , further comprising:
generating, by the processing system prior to the retrieving, the digital model based on a plurality of images of the media element.

13. The method of claim 1 , wherein the media element has appeared in at least one other media different from the audiovisual media into which the rendered media element is inserted.

14. The method of claim 13 , wherein the digital model and the metadata contain information to ensure that the characteristic is depicted consistently in the scene of the audiovisual media and in the at least one other media.

15. The method of claim 1 , further comprising, prior to the rendering:
requesting, by the processing system, additional information about the media element from a source other than the database, in response to determining that the digital model and the metadata do not provide enough information to render the media element for the scene of the audiovisual media,
wherein the rendering is further based on the additional information.

16. The method of claim 15 , wherein the additional information comprises additional images of the media element.

17. The method of claim 16 , wherein the additional images are provided in real time by a camera.

18. A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:
retrieving a digital model of a media element from a database storing a plurality of media elements, wherein the media element is to be depicted in a scene of an audiovisual media;
rendering the media element based on the digital model of the media element and on metadata associated with the digital model to produce a rendered media element, wherein the metadata describes a characteristic of the media element and a limit on the characteristic; and
inserting the rendered media element into the scene of the audiovisual media, wherein the operations further comprise, prior to the retrieving:
learning the characteristic of the media element based on an analysis of a plurality of samples comprising at least one of: a plurality of images depicting the media element, a plurality of audio segments depicting the media element, or a plurality of text segments depicting the media element;
learning the limit on the characteristic of the media element based on an analysis of the plurality of samples; and
encoding the characteristic and the limit on the characteristic in the metadata.

19. The non-transitory computer readable medium of claim 18 , wherein the operations further comprise, prior to the rendering:
requesting additional information about the media element, in response to determining that the digital model and the metadata do not provide enough information to render the media element for the scene of the audiovisual media,
wherein the rendering is further based on the additional information.

20. A device comprising:
a processing system including at least one processor; and
a non-transitory computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
retrieving a digital model of a media element from a database storing a plurality of media elements, wherein the media element is to be depicted in a scene of an audiovisual media;
rendering the media element based on the digital model of the media element and on metadata associated with the digital model to produce a rendered media element, wherein the metadata describes a characteristic of the media element and a limit on the characteristic; and
inserting the rendered media element into the scene of the audiovisual media, wherein the operations further comprise, prior to the retrieving:
learning the characteristic of the media element based on an analysis of a plurality of samples comprising at least one of: a plurality of images depicting the media element, a plurality of audio segments depicting the media element, or a plurality of text segments depicting the media element;
learning the limit on the characteristic of the media element based on an analysis of the plurality of samples; and
encoding the characteristic and the limit on the characteristic in the metadata.

Assignees

• At & T Ip I Lp
• At & T Mobility Ii Llc

Inventors

• Oetting John
• Zavesky Eric
• Pratt James
• Decuir Jason
• Lecesne Terrel

Classifications

• H04N21/23412

  for generating or manipulating the scene composition of objects, e.g. MPEG-4 objects · CPC title

• G06F16/78

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/58

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• H04N21/26603

  for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques · CPC title

• H04N21/23418

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title