Content-Based Retrieval of Spatio-Temporal Video Events

This paper addresses content-based video retrieval with an emphasis on spatio-temporal modeling and querying of events. Our approach is based on a layered model that guides the process of translating raw video data into an efficient internal representation that captures video semantics. We also present a video query language and show that the proposed model facilitates execution of different types of queries. The main ideas have been implemented in order to achieve a prototype of a video database management system. Furthermore, results on real tennis video data are presented demonstrating the validity of the approach.

[1]  Andrzej Duda,et al.  Content-based access to algebraic video , 1994, 1994 Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[2]  Katsumi Tanaka,et al.  OVID: Design and Implementation of a Video-Object Database System , 1993, IEEE Trans. Knowl. Data Eng..

[3]  Atsuo Yoshitaka,et al.  A Survey on Content-Based Retrieval for Multimedia Databases , 1999, IEEE Trans. Knowl. Data Eng..

[4]  Willem Jonker,et al.  An Overview of Data Models and Query Languages for Content-based Video Retrieval , 2000 .

[5]  HongJiang Zhang,et al.  Automatic parsing of TV soccer programs , 1995, Proceedings of the International Conference on Multimedia Computing and Systems.

[6]  Arif Ghafoor,et al.  Object-oriented conceptual modeling of video data , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[7]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[8]  Martin L. Kersten,et al.  Flattening an object algebra to provide performance , 1998, Proceedings 14th International Conference on Data Engineering.

[9]  T. Ozsu,et al.  Modeling of video spatial relationships in an object database management system , 1996, Proceedings of International Workshop on Multimedia Database Management Systems.

[10]  Azriel Rosenfeld,et al.  Content-Based Access to Multimedia Information: From Technology Trends to State of the Art , 1999 .

[11]  Ramesh C. Jain,et al.  Video Data Management Systems: Metadata and Architecture , 1998, Multimedia Data Management.

[12]  Ahmed K. Elmagarmid,et al.  Spatial and temporal content-based access to hypervideo databases , 1998, The VLDB Journal.

[13]  Dragutin Petkovic,et al.  Content-Based Representation and Retrieval of Visual Media: A State-of-the-Art Review , 1996 .

[14]  K. Selçuk Candan,et al.  The Advanced Video Information System: data structures and query processing , 1996, Multimedia Systems.

[15]  Yves Jean,et al.  Lucent Vision: A System for Enhanced Sports Viewing , 1999, VISUAL.

[16]  Willem Jonker,et al.  Modeling and Retrieving Audiovisual Information: A Soccer Video Retrieval System , 1998, Multimedia Information Systems.

[17]  Timos K. Sellis,et al.  Topological relations in the world of minimum bounding rectangles: a study with R-trees , 1995, SIGMOD '95.

[18]  Peter Boncz,et al.  Monet: An Impressionist Sketch of an Advanced Database System , 1994 .

[19]  Azriel Rosenfeld,et al.  Content-Based Access to Multimedia Information , 1999 .