Selective content insertion into areas of media objects
One or more computing devices, systems, and/or methods for selective content insertion into areas of media objects are provided. For example, a media object (e.g., an image or video), is selected for composition with content, such as where a message, interactive content, a hyperlink, or other types of content is overlaid or embedded into the media object to create a composite media object. The content is added into an area of the media object that is selectively identified to reduce occlusion and/or improve visual cohesiveness between the content and the media object (e.g., added to an area with a similar or complimentary color, having an adequate size with spare amounts of visual features such as a soccer player, a ball, or other entity, etc.). In this way, the content may be add into the area of the media object to create a composite media object to provide to users.
1. A method of selective content insertion into areas of media objects, the method involving a server comprising a processor, and the method comprising:
executing, on the processor, instructions that cause the server to perform operations, the operations comprising:
identifying a content feature of content;
identifying criteria for pairing the content with media objects;
querying a media object repository using the content feature and the criteria to identify a media object associated with the content feature and the criteria;
assigning cost values to one or more portions of the media object based upon an occlusion criteria;
identifying an area within the media object into which the content is to be added; and
responsive to determining that the area of the media object has a total cost value below a threshold, automatically generating a composite media object by adding the content into the area.
2. The method of claim 1 , wherein the adding the content comprises at least one of:
overlaying the content over the media object to create the composite media object; or
embedding the content into the media object to create the composite media object.
3. The method of claim 1 , wherein the adding the content comprises:
evaluating the media object of the media object repository to identify a feature of the media object, wherein the feature comprises at least one of a visual feature or an aural feature;
identifying the area within the media object into which the content can be added without occluding the feature above a threshold amount; and
adding the content into the area to create the composite media object.
4. The method of claim 3 , wherein the adding the content comprises:
modifying at least one of the media object or the content to reduce occlusion of the feature by the content.
5. The method of claim 1 , wherein the media object is an audio media object, and the area is a temporal period of the audio media object.
6. The method of claim 1 , wherein the adding the content comprises:
determining a topic of the content;
evaluating the media object of the media object repository to identify a feature of the media object as relating to the topic;
identifying the area within the media object as being associated with the feature; and
adding the content into the area to create the composite media object.
7. The method of claim 1 , wherein the media object is a live video stream, and the method comprises:
delaying playback of the live video stream to a user for a delay timespan;
evaluating one or more image frames or audio samples of the live video stream to predict a feature occurring within one or more subsequent image frames or audio samples of the live video stream; and
determining the area of the live video stream to add the content based upon the feature.
8. The method of claim 1 , comprising:
generating a density map for one or more image frames or audio samples of the media object.
9. The method of claim 1 , comprising:
generating a set of density maps for one or more image frames or audio samples; and
determining a total cost of values based upon the set of density maps.
10. The method of claim 1 , comprising:
responsive to receiving a request in real-time from a user interface for the content, creating the composite media object to provide through the user interface.
11. The method of claim 10 , wherein the identifying criteria comprises:
evaluating the user interface to identify a context of the user interface as the criteria.
12. The method of claim 1 , wherein the identifying criteria comprises:
evaluating user signals of a user to identify an interest of the user as the criteria.
13. The method of claim 1 , wherein the criteria comprises at least one of a visual criteria or an aural criteria.
14. The method of claim 1 , wherein the content feature comprises at least one of a visual feature or an aural feature.
15. The method of claim 1 , comprising:
responsive to receiving feedback from a user regarding the composite media object, adjusting the criteria based upon the feedback.
16. The method of claim 1 , comprising:
adding the content into a set of media objects to create a set of composite media objects;
providing the set of composite media objects to users;
tracking user interactivity with the set of composite media objects; and
ranking the set of composite media objects based upon the user interactivity.
17. The method of claim 1 , wherein the querying a media object repository comprises:
extracting a feature from a candidate media object of the media object repository, the feature comprising at least one of a visual feature or an aural feature; and
responsive to the feature corresponding to the content feature and the criteria above a selection threshold, selecting the candidate media object as the media object.
18. The method of claim 1 , wherein the querying a media object repository comprises:
ranking second media objects based upon a degree of matching between features of the second media objects and the content feature and the criteria.
19. A computing device comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
identifying a content feature of content;
identifying criteria for pairing the content with media objects;
querying a media object repository using the content feature and the criteria to identify a media object;
assigning cost values to one or more portions of the media object based upon an occlusion criteria;
evaluating the media object to identify an area within the media object into which the content can be added; and
responsive to determining that the area of the media object has a total cost value below a threshold, automatically generating a composite media object by adding the content into the area.
20. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:
identifying a content feature of content;
identifying criteria for pairing the content with media objects;
querying a media object repository using the content feature and the criteria to identify a media object;
assigning cost values to one or more image frames or audio samples of the media object based upon an occlusion criteria;
identifying an area of the media object; and
responsive to determining that the area of the media object has a total cost value below a threshold, automatically generating a composite media object by adding the content into the area.