Research On The Content-based Video Scene Segmentation

With the rapid development of multimedia and network technique, efficient and effective video analysis and retrieval become more and more important due to teeming of vast video information. Hence, it comes forth a new research field in the information technology, i.e. Content-Based Video Analysis And Retrieval (CBVAR).CBVAR means video retrieval from enormous video database through matching of patterns from video analysis and feature extraction to represent its content. In a video, the contents include its structure, low-level visual and aural features, and high-level semantic information, which form the base for further video comprehend and analysis. The main work in this thesis is video temporal segmentation,each video sequence could be hierarchically segmented as:scenes, shots and key frames.First, we introduce some fundamental knowledge of digital video as well as theories of video compressed and concepts about MPEG. As a common standard of moving picture, more and more video sequences are stored in MPEG format. So the video segmentation research in this paper is based on MPEG video.Shot detection is the most fundamental operation and very important step in CBVAR. Shot detection is a technique that divides video data into physical units, generally called shots. So the accuracy and execution speed of shot detection is critical. Approaches to shot segmentation can be classified as those that operate in MPEG compressed domain and those in uncompressed domain, shot change can be classified cut and gradual shots. Many algorithms operate in the uncompressed domain are very well and the common known methods among them are based on...