Video Structured To Achieve

With the rapid development of computer and multimedia technology, we have to deal with more and more video information. Facing so much information, it is very important to index the data we need easily and quickly. So content-based video retrieval becomes a hot research topic. The main tasks of content-based vodeo retrieval is video structural analysis.Video structural analysis is the process of converting the video sequences of two dimensions to structural data, which is the base of content-based video browsing and retrieval. It mainly includes two parts: shot boundary detection and key-frame extraction.Firstly, we summarize the content-based video retrieval, and mainly introduce the content of video structural analysis. Secondly, we introduce the methods of feature abstraction used in shot boundary detection techniques. And we synopsize and analyze the traditional measures of shot boundary detection. Based on these, we mainly analyze color histogram of divided nonuniformly as the difference characteristic among the frames and study information theory and it's application on shot boundary detection, then we advance the fusing of color histogram of divided non-uniformly and information theory to detect shot boundary. The experiment shows: The method which this paper put forward can make better result. The ones that have improved the recall and precision . Thirdly, we introduce some common means used on key-frame extraction, and give a simple and practical method used on key-frame extraction, based on this, we use clusters method to improve the simple method. The experiment shows: the improved method can show the main content of shot bitterly, last but not least, we design and develop the prototype of above video structural analysis system.