Method and system for fusing user specific content into a video production

Abstract

Generally, a method for fusing viewer-specific graphic content into video content being broadcasted to a plurality of viewer terminals are provided. The method may include the following steps: receiving a video content including a plurality of frames representing a scene; deriving a virtual camera model for a subset of frames of the video content; generating a foreground mask for each frame of the subset of frames of the video content; and substituting, in at least part of the frames of the subset of frames of the video content received on at least some of the plurality of viewer terminals, all pixels in the respective frames contained within a predefined content insertion region of a background surface in the scene, except for the pixels indicated by the respective frames' foreground masks, with pixels of viewer-specific graphic contents associated with the respective viewer terminals, using the respective frames' virtual camera models.