Bilkent University Multimedia Database Group
Edit | Recent Changes | Advanced Search | All Pages | Administration | Index |

BilVideo

BilVideo: A Video Database Management System

BilVideo provides an integrated support for queries on spatio-temporal, semantic and low-level features (color, shape, and texture) on video data (see ref.1). A spatio-temporal query may contain any combination of directional, topological, object-appearance, 3D-relation, trajectory-projection and similarity-based object-trajectory conditions. BilVideo handles spatio-temporal queries using a knowledge-base, which consists of a fact-base and a comprehensive set of rules, while the queries on semantic and low-level features are handled by an object-relational database. The query processor interacts with both of the knowledge-base and object-relational database to respond to user queries that contain a combination of spatio-temporal, semantic, and low-level feature query conditions. Intermediate query results returned from these system components are integrated seamlessly by the query processor and sent to Web clients. Moreover, users can browse the video collection before giving complex and specific queries, and a text-based SQL-like query language is also available for users (see ref.2).

BilVideo supports any application with query requirements on spatio-temporal, semantic and low-level features on video data; therefore, it is application-independent. However, it can easily be tailored according to the specific requirements of such applications through the definition of external predicates supported by its query language without much effort and any loss in performance.

Parts of the system

Here, we present the Web-based visual query interface of BilVideo and its tools, Fact-Extractor and Video-Annotator, which are used to populate the facts-base and feature database of the system to support spatio-temporal and semantic video queries, respectively. Furthermore, an auxiliary module used to extract salient objects from video keyframes, called Object Extractor, is also presented (see ref.3).

Web-based Visual Query Interface

BilVideo can handle multiple requests over the Internet through a graphical query interface developed as a Java applet (see ref.4). The interface is composed of query specification windows for different types of queries: spatial, trajectory, semantic, and low-level features. Since video has a time dimension, these two types of primitive queries can be combined with temporal predicates to query temporal contents of videos. The Web-based Query Interface of BilVideo is available here outlink. A demo of the Web-based Query Interface can be seen here outlink.

Fact-Extractor

This tool is used to extract spatio-temporal relations between video objects and store them in the knowledge-base as facts. These facts representing the extracted relations are used to query video data for spatio-temporal conditions. The tool also extracts object trajectories and 3D-relations between objects of interest. A demo facts-base population via the Fact-Extractor tool is available here outlink.

Video-Annotator

This tool is used to extract semantic data from video clips to be stored in the feature database to query video data for its semantic content. It provides some facilities for viewing, updating and deleting semantic data that has already been extracted from video clips and stored in the feature database. A demo of video annotation through the Video-Annotator tool is available here outlink.

Object Extractor

This tool is used to extract salient objects from video keyframes. It also facilitates the fact-extraction process automating the minimum bounding rectangle (MBR) specification of salient objects. A demo of the Object Extractor module is available here outlink.

Related Publications

1. E. Şaykol, Web-based user interface for query specification in a video database system, M.S. thesis, Dept. of Computer Engineering, Bilkent University, Ankara, Turkey, Sept. 2001.
2. E. Şaykol, U. Güdükbay and Ö. Ulusoy, A semi-automatic object extraction tool for querying in multimedia databases, MIS’01, Capri, Italy, November 2001, pp. 11-20.
3. E. Şaykol, U. Güdükbay and Ö. Ulusoy, A histogram-based approach for object-based query-by-shape-and-color in multi-media databases, submitted journal paper and also available as BU-CE-0201, Bilkent Un., January 2002.
4. G. Ünel, M.E. Dönderler, Ö. Ulusoy, U. Güdükbay, An Efficient Query Optimization Strategy for Spatio-Temporal Queries in Video Databases, to appear in the J. of Sys. and Software.
5. M.E. Dönderler, E. Şaykol, U. Arslan, Ö. Ulusoy, U. Güdükbay, BilVideo: Design and Implementation of a Video Database Management System, to appear in Mult. Tools and Applications.
6. M.E. Dönderler, E. Şaykol, Ö. Ulusoy, U. Güdükbay, BilVideo: A Video Database Management System, IEEE Multimedia, Vol. 10, No. 1, pp. 66-70, January/March 2003.
7. M.E. Dönderler, Ö. Ulusoy and U. Güdükbay, A rule-based video database system architecture, Info. Sci., Vol. 143, No. 1-4, pp. 13-45, 2002.
8. M.E. Dönderler, Ö. Ulusoy and U. Güdükbay, Rule-based spatio-temporal query processing for video databases, VLDB Journal, Vol. 13, No. 1, pp. 86–103, January 2004.
9. U. Arslan, M.E. Dönderler, E. Şaykol, Ö Ulusoy, U. Güdükbay, A Semi-Automatic Semantic Annotation Tool for Video Databases, In SOFSEM 2002, Workshop on Multimedia Semantics, Milovy, Czech Republic, November 2002.