Methods and apparatus for media search, characterization, and augmented reality provision
Methods and apparatus for providing attribute-based search of media assets such as video and audio assets, and associated augmented reality functions including dynamic provision of relevant secondary content relating to the identified attribute(s). In one embodiment, media or content assets are ingested into a processing system and processed according to one or more attribute detection, identification, and characterization algorithms. Attributes detected may include for example the presence of tangible items such as clothing or chattels, particular persons such as celebrities, and/or certain contexts such as sporting activities and musical performances, as rendered within the media asset. In one implementation, the characterized assets are provided a unique ID, and stored so as to permit cross-correlation based on, e.g., the identified and characterized attributes. Secondary content (e.g., advertising or promotional content) is correlated to each identified asset, and dynamically served upon a user providing some threshold level of interaction with the attribute.
1. A method of processing a digital media asset in order to enable reduced processing burden during characterization of the digital media asset, the method comprising:
decoding at least a portion of a digital media asset, the at least portion comprising a plurality of sub-portions;
processing at least a first one of the plurality of sub-portions in order to detect a first object rendered therein, the first one of the plurality of sub-portions associated with a first time coordinate within the digital media asset;
perform one or more object identification processing tasks for the detected first object;
predicting a position of the detected first object within one or more subsequent sub-portions, that are each associated with a future time coordinate within the digital media asset, using movement tracking that tracks a trajectory of the detected first object across two or more of the plurality of sub-portions;
processing at least a second one of the plurality of sub-portions in order to detect a second object rendered therein, the second one of the plurality of sub-portions associated with a second time coordinate, subsequent to the first time coordinate, within the digital media asset;
determining that the detected second object is a same object as the detected first object based at least on the predicted position of the detected first object and a position of the detected second object, even when the same object is not detected within at least one intervening one of the plurality of sub-portions associated with an intervening time coordinate that is chronologically between the first time coordinate and the second time coordinate; and
based at least on the determination that the detected second object is the same object as the detected first object, determining not to perform the one or more object identification processing tasks for the detected second object so as to reduce processing burden.
2. The method of claim 1 , wherein the plurality of sub-portions comprises a plurality of I-frames of video data of the digital media asset.
3. The method of claim 1 , wherein the one or more other object identification processing tasks comprise at least one of color, texture, or shape analysis.
4. The method of claim 1 , further comprising, based at least on the determination that the detected second object is the same object as the detected first object, generating at least one logical association between the detected first object and the detected second object.
5. The method of claim 1 , further comprising determining not to process the at least one intervening one of the plurality of sub-portions.
6. The method of claim 1 , wherein determining that the detected second object is the same object as the detected first object comprises identifying that the detected second object shares a common context with the detected first object.