With the quick development of technologies on video compression, transmission and storage, video analysis based on content is becoming a hot topic. People are interested in interactive video services and varieties of videos on demand, other than simply playing videos. When video is described by semantic information extracted from it, the compression ratio can be considerably increased, and the functionalities of accessing, indexing and retrieval, manipulating for video can be enhanced. It has attracted much attention from academe and industry.But because the basic video features can not match with the semantic video information exactly, traditional video content analysis technology always faces the problem of"Semantic Gap". Our thesis do much research on the existing video segmentation and content analysis technology then set up a reasonable and effective semantic video information description model and realize the mapping from video feature information to semantic information and at last a multi-hierarchy semantic video object extraction arithmetic is given. The overall scheme is to study existing semantic video information... |