Methods and systems for super compression of prior known objects in video and film

摘要

Methods and systems for compressing data representing a video sequence having a plurality of image frames include obtaining a plurality of basis image frames which represent an anticipated range of motion of at least one object in the video sequence and an actual current image frame and a previous image frame of the at least one object. A plurality of feature points of the at least one object are located in each of the plurality of basis image frames, the previous image frame, and the actual current image frame. A mathematical transformation which maps locations of the feature points in each of the plurality of basis image frames and the previous image frame to locations in the actual current image frame is determined. The mathematical transformation is then encoded for transmission. The methods and systems may also include decoding an encoded mathematical transformation and transforming each of the plurality of basis image frames and the previous image frame in accordance with the mathematical transformation to form an estimated current image frame of the actual current image frame.