Systems and methods for performing an action based on context of a feature in a media asset

Patent metadata

Field	Value
Publication number	US-10021461-B2
Application number	US-201615056733-A
Country	US
Kind code	B2
Filing date	Feb 29, 2016
Priority date	Feb 29, 2016
Publication date	Jul 10, 2018
Grant date	Jul 10, 2018

Abstract

Systems and methods are provided herein for performing an action based on a feature in a media asset. In many media assets, specific features appear at portions of a program that users find interesting. These features can be compared with a database of stored objects that commonly appear in media assets to determine the object corresponding to the feature. The context of the object in the media asset then may be determined so that an appropriate action is selected for the system to take.

First claim

What is claimed is:

1. A method for performing an action based on context of a feature in a media asset, the method comprising:
storing a plurality of objects;
storing, in a context field of a data structure associated with a first object of the plurality of objects, a first context indicator, wherein progress towards a goal in a sporting event being close to the goal is stored as a first characteristic of the first context indicator;
storing, in the context field of the data structure associated with the first object of the plurality of objects, a second context indicator, wherein progress towards the goal in the sporting event being far from the goal is stored as a second characteristic of the second context indicator;
receiving at least one frame of the media asset;
determining a feature in the at least one frame of the media asset;
comparing the feature to each of the stored plurality of objects to identify the first object of the stored plurality of objects that corresponds to the feature;
retrieving, from the context field of the data structure associated with the first object, a context indicator associated with the first object by:
determining, from data associated with the feature, a characteristic of the first object;
comparing the characteristic to the first and second characteristics of the first and second context indicators stored in the data structure associated with the first object to identify the first context indicator that corresponds to the characteristic; and
retrieving, as the context indicator associated with the first object, the first context indicator from the context field of the data structure associated with the first object;

retrieving from a database of actions corresponding to context indicators an action corresponding to the context indicator associated with the first object; and
performing the action corresponding to the context indicator associated with the first object.

2. The method of claim 1 , wherein storing the plurality of objects comprises:
creating the feature;
associating the created feature with a plurality of media assets, wherein the plurality of media assets contain similar content;
storing the created feature as the first object in a library of objects associated with the plurality of media assets; and
generating an overlay with the first object on the media asset.

3. The method of claim 1 , wherein determining the feature comprises:
analyzing a pixel map associated with the at least one frame of the media asset;
analyzing a group of pixels in the pixel map;
determining shared properties of a subset of pixels in the group of pixels; and
generating a table for the feature containing relative positions and properties of pixels in the subset of pixels.

4. The method of claim 1 , wherein the feature is defined by a first table containing relative positions and properties of a first plurality of pixels, and wherein comparing the feature to each of the stored plurality of objects comprises:
storing a tolerance factor;
accessing a first pixel position of a first pixel stored in the first table;
computing an upper limit based on multiplying coordinates of the first pixel position by the tolerance factor;
computing a lower limit based on dividing the coordinates of the first pixel position by the tolerance factor;
retrieving a second pixel position of one of a second plurality of pixels from a second table containing relative positions and properties of pixels for the first object;
comparing coordinates of the second pixel position to a range of coordinates of the first pixel position defined by the lower limit to the upper limit;
determining the first pixel position matches the second pixel position when the coordinates of the second pixel position is within the range of coordinates of the first pixel position; and
in response to determining a predetermined number of the pixel positions corresponding to the first plurality of pixels in the first table match one of a plurality of pixel positions in the second table, determining the feature corresponds to the first object.

5. The method of claim 1 , wherein the action associated with the context indicator relates to moving a current playback position to another playback position that includes the object, and wherein performing the action comprises:
determining the another playback position based on the at least one frame containing the object;
moving the current playback position to the another playback position; and
playing the media asset from the another playback position.

6. The method of claim 1 , wherein the action associated with the context indicator relates to alerting a user to a media asset listing with subject matter that corresponds to the first object, and wherein performing the action comprises:
retrieving subject matter of the first object from a subject matter field of the data structure associated with the first object;
searching for a first media asset listing associated with the retrieved subject matter; and
promoting the first media asset listing among a plurality of displayed media asset listings.

7. The method of claim 1 , wherein the action associated with the context indicator relates to presenting supplemental information related to the object, and wherein performing the action comprises:
retrieving a pointer to a location of the supplemental information related to the object from a supplemental information field of the data structure associated with the object;
accessing the location of the supplemental information;
retrieving the supplemental information; and
generating a simultaneous display of the media asset and the supplemental information.

8. The method of claim 1 , wherein the media asset is a first media asset, wherein the action is associated with presenting the first media asset to the user simultaneously with a second media asset currently being accessed by the user, and wherein performing the action comprises:
determining the user is not accessing the first media asset;
retrieving the first media asset; and
generating a simultaneous display of the first media asset and the second media asset currently being accessed by the user.

9. A system for performing an action based on context of a feature in a media asset, the system comprising:
storage circuitry configured to:
store a plurality of objects;
store, in a context field of a data structure associated with a first object of the plurality of objects, a first context indicator, wherein progress towards a goal in a sporting event being close to the goal is stored as a first characteristic of the first context indicator; and
store, in the context field of the data structure associated with the first object of the plurality of objects, a second context indicator, wherein progress towards the goal in the sporting event being far from the goal is stored as a second characteristic of the second context indicator; and

control circuitry configured to:
receive at least one frame of the media asset;
determine a feature in the at least one frame of the media asset;
compare the feature to each of the stored plurality of objects to identify a first object of the stored plurality of objects that corresponds to the feature;
retrieve, from the context field of the data structure associated with the first object, a context indicator associated with the first object by:
determining, from data associated with the feature, a characteristic of the first object;
comparing the characteristic to the first and second characteristics of the first and second context indicators stored in the data structure associated with the first object to identify the first context indicator that corresponds to the characteri

Assignees

• Rovi Guides Inc

Inventors

• Roe Glen E
• Mccarty Michael K

Classifications

• H04N21/4882 Primary

  for displaying messages, e.g. warnings, reminders (arrangements for providing short real-time information to substation in data switching networks H04L12/1895) · CPC title

• H04N21/435

  Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream · CPC title

• H04N21/482

  End-user interface for programme selection · CPC title

• H04N21/4826

  using recommendation lists, e.g. of programmes or channels sorted out according to their score · CPC title