Content-Based Parsing in Video Database

摘要

In order to make video content more accessible, we must achieve content-based indexing and retrieving in a video database. This paper introduces a framework for video parsing and presents algorithms to automate the video parsing task, including segmenting video source into clips and further extracting the salient object in video sequence based on motion analysis. Considering that more and more video materials are stored and transmitted in the form of compressed stream, all our algorithms are based on the compressed video data of MPEG-I.