Application of information theory in video abstraction extraction

With the development of Internet and broadband multimedia business, video becomes one of the main-stream vehicles in modern information dissemination. How to reduce the cost of video storage, classification and indexing by analyzing the video content, as well as how to improve the efficiency, availability and accessibility of the video, has become an urgent problem need to solve. Video abstraction is a good solution. In this paper, information theory is used to calculate the size of mutual information between the adjacent key frames, and then to extract the key frames from the initial key frames to form a video abstraction, and experiment results proved to be better.