tailieunhanh - ViBE: A Compressed Video Database Structured for Active Browsing and Search

In most cases, the independence date for each country (reported in Appendix Table 2) provided the relevant benchmark for our data collection efforts. In some cases, such as Finland, Dominica, Grenada, Papua New Guinea, New Zealand, Norway, Slovakia, and Zimbabwe, debt data were available for a few years in advance of independence years and appeared consistent with the trend in later years. These data were retained. Similarly, data were also available and included for Austria-Hungary (reported under Austria) and Czechoslovakia (reported under Czech Republic). . | IEEE TRANSACTIONS ON MULTIMEDIA VOL. 6 NO. 1 FEBRUARY 2004 103 ViBE A Compressed Video Database Structured for Active Browsing and Search Cuneyt Taskiran Student Member IEEE Jau-Yuen Chen Alberto Albiol Member IEEE Luis Torres Senior Member IEEE Charles A. Bouman Fellow IEEE and Edward J. Delp Fellow IEEE Abstract In this paper we describe a unique new paradigm for video database management known as ViBE video indexing and browsing environment . ViBE is a browseable searchable paradigm for organizing video data containing a large number of sequences. The system first segments video sequences into shots by using a new feature vector known as the Generalized Trace obtained from the DC-sequence of the compressed data. Each video shot is then represented by a hierarchical structure known as the shot tree. The shots are then classified into pseudo-semantic classes that describe the shot content. Finally the results are presented to the user in an active browsing environment using a similarity pyramid data structure. The similarity pyramid allows the user to view the video database at various levels of detail. The user can also define semantic classes and reorganize the browsing environment based on relevance feedback. We describe how ViBE performs on a database of MPEG sequences. Index Terms Face detection semantic gap shot boundary detection shot representation shot similarity video browsing video databases video search. I. Introduction The proliferation of multimedia material while offering unprecedented opportunities for users to search and profit from available content also has made it much harder for users to find the material they are looking for in large collections. Depending on the specific information they are seeking users desire flexible and intuitive methods to search and browse multimedia libraries. However the cost of manually extracting the metadata to support such functionalities may be unrealistically high. Therefore over the last decade there has been