Method for object-based coding of video information

摘要

The present invention relates to a method, system and related devices for encoding video information. The video encoder recognizing, at least one object in an image of said video information and characterizing said at least one object recognized, by means of meta-information and said video encoder, determining for each of said at least one object recognized a corresponding object model, optimum matching said object recognized based on said meta-information corresponding to said object recognized and the video encoder, generating encoded video information, said encoded video information comprising information corresponding to an object model for each of said at least one object recognized in said image of said video information.