System and method for generating coded video sequences from still media

摘要

The invention provides a system and method that transforms a set of still/motion media (i.e., a series of related or unrelated still frames, web-pages rendered as images, or video clips) or other multimedia, into a video stream that is suitable for delivery over a display medium, such as TV, cable TV, computer displays, wireless display devices, etc. The video data stream may be presented and displayed in real time or stored and later presented through a set-top box, for example. Because these media are transformed into coded video streams (e.g. MPEG-2, MPEG-4, etc.), a user can watch them on a display screen without the need to connect to the Internet through a service provider. The user may request and interact with the desired media through a simple telephone interface, for example. Moreover, several wireless and cable-based services can be developed on the top of this system. In one possible embodiment, the system for generating a coded video sequence may include an input unit that receives the multimedia input and extracts image data, and derives the virtual camera scripts and coding hints from the image data, a video sequence generator that generates a video sequence based on the extracted image data and the derived virtual camera scripts and coding hints, and a video encoder that encodes the generated video sequence using the coding hints and outputs the coded video sequence to an output device. The system may also provide customized video sequence generation services to subscribers.

主权项

1. A method comprising:
receiving, by an input unit, a plurality of still images, wherein the plurality of still images are independent of a video and the plurality of still images are not related to the video; extracting, by the input unit, image data from the plurality of still images, the image data comprising virtual camera script data and coding hint data; deriving, by the input unit, a virtual camera script from a virtual camera script database based on the image data, the virtual camera script describing operations to transform the plurality of still images into a video sequence, wherein the virtual camera script comprises instructions resulting in simulated camera movement over portions of the plurality of still images during the video sequence; deriving, by the input unit, a coding hint from a coding hints database based on the image data, wherein the coding hint specifies a frame number in a sequence and a number of frames; generating, by a video sequence generator, the video sequence based on the virtual camera script and the coding hint; generating, by a video encoder, a video encoding sequence based on the virtual camera script and the coding hint; and generating a customized sequence by inserting a customized advertisement in the video encoding sequence.