Content-Based Video Retrieval: A Database Perspective

M. Petkovic, Willem Jonker

Research output: Book/ReportBookAcademic

Abstract

Recent advances in computing, communication, and data storage have led to an increasing number of large digital libraries publicly available on the Internet. In addition to alphanumeric data, other modalities, including video play an important role in these libraries. Ordinary techniques will not retrieve required information from the enormous mass of data stored in digital video libraries. Instead of words, a video retrieval system deals with collections of video records. Therefore, the system is confronted with the problem of video understanding. The system gathers key information from a video in order to allow users to query semantics instead of raw video data or video features. Users expect tools that automatically understand and manipulate the video content in the same structured way as a traditional database manages numeric and textual data. Consequently, content-based search and retrieval of video data becomes a challenging and important problem. This book focuses particularly on content-based video retrieval. After addressing basic concepts and techniques in the field, Content-Based Video Retrieval: A Database Perspective concentrates on the semantic gap problem, i.e., the problem of inferring semantics from raw video data, as the main problem of content-based video retrieval. This book identifies and proposes the integrated use of three different techniques to bridge the semantic gap, namely, spatio-temporal formalization methods, hidden Markov models, and dynamic Bayesian networks. As the problem is approached from a database perspective, the emphasis evolves from a database management system into a video database management system. This system allows a user to retrieve the desired video sequence among voluminous amounts of video data in an efficient and semantically meaningful way. This book also presents a modeling framework and a prototype of a content-based video management system that integrates the three methods and provides efficient, flexible, and scalable content-based video retrieval. The proposed approach is validated in the domain of sport videos for which some experimental results are presented. Content-Based Video Retrieval: A Database Perspective is designed for a professional audience, composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and electrical engineering.
Original languageUndefined
Place of PublicationDordrecht
PublisherKluwer Academic Publishers
Number of pages168
ISBN (Print)1-4020-7617-7
Publication statusPublished - 2003

Publication series

NameMultimedia Systems and Applications
PublisherSpringer Verlag
Volume25

Keywords

  • METIS-216338

Cite this

Petkovic, M., & Jonker, W. (2003). Content-Based Video Retrieval: A Database Perspective. (Multimedia Systems and Applications; Vol. 25). Dordrecht: Kluwer Academic Publishers.
Petkovic, M. ; Jonker, Willem. / Content-Based Video Retrieval: A Database Perspective. Dordrecht : Kluwer Academic Publishers, 2003. 168 p. (Multimedia Systems and Applications).
@book{e20e6a6cfffd4de78738b14278aa0002,
title = "Content-Based Video Retrieval: A Database Perspective",
abstract = "Recent advances in computing, communication, and data storage have led to an increasing number of large digital libraries publicly available on the Internet. In addition to alphanumeric data, other modalities, including video play an important role in these libraries. Ordinary techniques will not retrieve required information from the enormous mass of data stored in digital video libraries. Instead of words, a video retrieval system deals with collections of video records. Therefore, the system is confronted with the problem of video understanding. The system gathers key information from a video in order to allow users to query semantics instead of raw video data or video features. Users expect tools that automatically understand and manipulate the video content in the same structured way as a traditional database manages numeric and textual data. Consequently, content-based search and retrieval of video data becomes a challenging and important problem. This book focuses particularly on content-based video retrieval. After addressing basic concepts and techniques in the field, Content-Based Video Retrieval: A Database Perspective concentrates on the semantic gap problem, i.e., the problem of inferring semantics from raw video data, as the main problem of content-based video retrieval. This book identifies and proposes the integrated use of three different techniques to bridge the semantic gap, namely, spatio-temporal formalization methods, hidden Markov models, and dynamic Bayesian networks. As the problem is approached from a database perspective, the emphasis evolves from a database management system into a video database management system. This system allows a user to retrieve the desired video sequence among voluminous amounts of video data in an efficient and semantically meaningful way. This book also presents a modeling framework and a prototype of a content-based video management system that integrates the three methods and provides efficient, flexible, and scalable content-based video retrieval. The proposed approach is validated in the domain of sport videos for which some experimental results are presented. Content-Based Video Retrieval: A Database Perspective is designed for a professional audience, composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and electrical engineering.",
keywords = "METIS-216338",
author = "M. Petkovic and Willem Jonker",
year = "2003",
language = "Undefined",
isbn = "1-4020-7617-7",
series = "Multimedia Systems and Applications",
publisher = "Kluwer Academic Publishers",
address = "Netherlands",

}

Petkovic, M & Jonker, W 2003, Content-Based Video Retrieval: A Database Perspective. Multimedia Systems and Applications, vol. 25, Kluwer Academic Publishers, Dordrecht.

Content-Based Video Retrieval: A Database Perspective. / Petkovic, M.; Jonker, Willem.

Dordrecht : Kluwer Academic Publishers, 2003. 168 p. (Multimedia Systems and Applications; Vol. 25).

Research output: Book/ReportBookAcademic

TY - BOOK

T1 - Content-Based Video Retrieval: A Database Perspective

AU - Petkovic, M.

AU - Jonker, Willem

PY - 2003

Y1 - 2003

N2 - Recent advances in computing, communication, and data storage have led to an increasing number of large digital libraries publicly available on the Internet. In addition to alphanumeric data, other modalities, including video play an important role in these libraries. Ordinary techniques will not retrieve required information from the enormous mass of data stored in digital video libraries. Instead of words, a video retrieval system deals with collections of video records. Therefore, the system is confronted with the problem of video understanding. The system gathers key information from a video in order to allow users to query semantics instead of raw video data or video features. Users expect tools that automatically understand and manipulate the video content in the same structured way as a traditional database manages numeric and textual data. Consequently, content-based search and retrieval of video data becomes a challenging and important problem. This book focuses particularly on content-based video retrieval. After addressing basic concepts and techniques in the field, Content-Based Video Retrieval: A Database Perspective concentrates on the semantic gap problem, i.e., the problem of inferring semantics from raw video data, as the main problem of content-based video retrieval. This book identifies and proposes the integrated use of three different techniques to bridge the semantic gap, namely, spatio-temporal formalization methods, hidden Markov models, and dynamic Bayesian networks. As the problem is approached from a database perspective, the emphasis evolves from a database management system into a video database management system. This system allows a user to retrieve the desired video sequence among voluminous amounts of video data in an efficient and semantically meaningful way. This book also presents a modeling framework and a prototype of a content-based video management system that integrates the three methods and provides efficient, flexible, and scalable content-based video retrieval. The proposed approach is validated in the domain of sport videos for which some experimental results are presented. Content-Based Video Retrieval: A Database Perspective is designed for a professional audience, composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and electrical engineering.

AB - Recent advances in computing, communication, and data storage have led to an increasing number of large digital libraries publicly available on the Internet. In addition to alphanumeric data, other modalities, including video play an important role in these libraries. Ordinary techniques will not retrieve required information from the enormous mass of data stored in digital video libraries. Instead of words, a video retrieval system deals with collections of video records. Therefore, the system is confronted with the problem of video understanding. The system gathers key information from a video in order to allow users to query semantics instead of raw video data or video features. Users expect tools that automatically understand and manipulate the video content in the same structured way as a traditional database manages numeric and textual data. Consequently, content-based search and retrieval of video data becomes a challenging and important problem. This book focuses particularly on content-based video retrieval. After addressing basic concepts and techniques in the field, Content-Based Video Retrieval: A Database Perspective concentrates on the semantic gap problem, i.e., the problem of inferring semantics from raw video data, as the main problem of content-based video retrieval. This book identifies and proposes the integrated use of three different techniques to bridge the semantic gap, namely, spatio-temporal formalization methods, hidden Markov models, and dynamic Bayesian networks. As the problem is approached from a database perspective, the emphasis evolves from a database management system into a video database management system. This system allows a user to retrieve the desired video sequence among voluminous amounts of video data in an efficient and semantically meaningful way. This book also presents a modeling framework and a prototype of a content-based video management system that integrates the three methods and provides efficient, flexible, and scalable content-based video retrieval. The proposed approach is validated in the domain of sport videos for which some experimental results are presented. Content-Based Video Retrieval: A Database Perspective is designed for a professional audience, composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and electrical engineering.

KW - METIS-216338

M3 - Book

SN - 1-4020-7617-7

T3 - Multimedia Systems and Applications

BT - Content-Based Video Retrieval: A Database Perspective

PB - Kluwer Academic Publishers

CY - Dordrecht

ER -

Petkovic M, Jonker W. Content-Based Video Retrieval: A Database Perspective. Dordrecht: Kluwer Academic Publishers, 2003. 168 p. (Multimedia Systems and Applications).