Tagging virtualized content
AssigneeOutward, Inc.
InventorClarence Chui
Life of this patent
Estimating the term…
Abstract
Techniques for tagging a scene are disclosed. In some embodiments, information about a scene is inferred by at least in part automatically interpreting a metric associated with the scene that is determined by analyzing data comprising a primitive form of the scene, wherein analyzed data comprising the primitive form of the scene comprises positions of three-dimensional objects in the scene. The scene is tagged with a tag comprising the inferred information.
Claims22
A method, comprising:
- transforming two-dimensional source content into a primitive form of a scene comprising a plurality of three-dimensional object specifications, wherein the primitive form of the scene comprises a three-dimensional representation of the two-dimensional source content;
- determining a metric associated with the scene by analyzing data comprising the primitive form of the scene, wherein analyzed data comprising the primitive form of the scene comprises positions of three-dimensional objects in the scene;
- inferring contextual information about the scene by at least in part automatically interpreting the determined metric;
- and
- tagging the scene with a tag comprising the inferred contextual information.
A system, comprising:
- a processor configured to:
- transform two-dimensional source content into a primitive form of a scene comprising a plurality of three-dimensional object specifications, wherein the primitive form of the scene comprises a three-dimensional representation of the two-dimensional source content;
- determine a metric associated with the scene by analyzing data comprising the primitive form of the scene, wherein analyzed data comprising the primitive form of the scene comprises positions of three-dimensional objects in the scene;
- infer contextual information about the scene by at least in part automatically interpreting the determined metric;
- and
- tag the scene with a tag comprising the inferred contextual information;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A computer program product stored on a non-transitory computer readable storage medium and comprising computer instructions which when executed cause a computer to:
- transform two-dimensional source content into a primitive form of a scene comprising a plurality of three-dimensional object specifications, wherein the primitive form of the scene comprises a three-dimensional representation of the two-dimensional source content;
- determine a metric associated with the scene by analyzing data comprising the primitive form of the scene, wherein analyzed data comprising the primitive form of the scene comprises positions of three-dimensional objects in the scene;
- infer contextual information about the scene by at least in part automatically interpreting the determined metric;
- and
- tag the scene with a tag comprising the inferred contextual information.
Dependencies are inferred from the claim text.