Introduction to MPEG 7 : multimedia content description interface

The MPEG standards are an evolving set of standards for video and audio compression. MPEG 7 technology covers the most recent developments in multimedia search and retreival, designed to standardise the description of multimedia content supporting a wide range of applications including DVD, CD and HDTV.
Multimedia content description, search and retrieval is a rapidly expanding research area due to the increasing amount of audiovisual (AV) data available. The wealth of practical applications available and currently under development (for example, large scale multimedia search engines and AV broadcast servers) has lead to the development of processing tools to create the description of AV material or to support the identification or retrieval of AV documents. Written by experts in the field, this book has been designed as a unique tutorial in the new MPEG 7 standard covering content creation, content distribution and content consumption. At present there are no books documenting the available technologies in such a comprehensive way.
* Presents a comprehensive overview of the principles and concepts involved in the complete range of Audio Visual material indexing, metadata description, information retrieval and browsing
* Details the major processing tools used for indexing and retrieval of images and video sequences
* Individual chapters, written by experts who have contributed to the development of MPEG 7, provide clear explanations of the underlying tools and technologies contributing to the standard
* Demostration software offering step-by-step guidance to the multi-media system components and eXperimentation model (XM) MPEG reference software
* Coincides with the release of the ISO standard in late 2001.
A valuable reference resource for practising electronic and communications engineers designing and implementing MPEG 7 compliant systems, as well as for researchers and students working with multimedia database technology.

Author Notes

B. S. Manjunath and Philippe Salembier are the authors of Introduction to MPEG-7: Multimedia Content Description Interface, published by Wiley.

Leonardo ChiariglioneFernando Pereira and Rob KoenenOlivier Avaro and Philippe SalembierJane Hunter and Claude SeyratJorg Heuer and Cedric Thienot and Michael WollbornPhilippe Salembier and John R. SmithToby Walker and Jorg Heuer and Jose M. MartinezAna B. Benitez and Jose M. Martinez and Hawley Rising and Philippe SalembierPeter van Beek and John R. SmithJohn R. Smith and Ana B. BenitezPeter van Beek and Kyoungro Yoon and A. Mufit FermanB. S. Manjunath and Thomas SikoraJens-Rainer Ohm and Leszek Cieplinski and Heon J. Kim and Santhana Krishnamachari and B. S. Manjunath and Dean S. Messing and Akio YamadaYanglim Choi and Chee Sun Won and Yong Man Ro and B. S. ManjunathMiroslaw Bober and F. Preteux and Whoi-Yul Yura KimSylvie Jeannin and Ajay Divakaran and Benoit MoryAdam T. Lindsay and Ian Burnett and Schuyler Quackenbush and Melanie JacksonJ. P. A. Charlesworth and Philip N. GarnerMichael A. CaseyNeil DayNeil Day and Shun-ichi Sekiguchi and Mikio Sasaki

Contents of the DVD	p. xv
Contributors	p. xvii
Preface	p. xxi
Section I Introduction	p. 1
1 Introduction to MPEG-7: Multimedia Content Description Interface	p. 3
2 Context, Goals and Procedures	p. 7
2.1 Motivation and Objectives	p. 7
2.2 Driving Principles	p. 9
2.3 What is Standardized?	p. 10
2.4 MPEG Standards Development Process	p. 11
2.5 MPEG-7 Types of Tools	p. 13
2.6 Standard Organization and Workplan	p. 15
2.7 Applications	p. 17
2.8 Requirements	p. 18
2.9 Conclusion	p. 27
References	p. 28
Section II Systems	p. 31
3 Systems Architecture	p. 33
3.1 Introduction	p. 33
3.2 Objectives	p. 34
3.3 MPEG-7 Terminal Architecture	p. 35
3.4 Action Units	p. 39
3.5 Delivery of MPEG-7 Descriptions	p. 40
3.6 Conclusion	p. 40
Acknowledgment	p. 40
References	p. 41
4 Description Definition Language	p. 43
4.1 Introduction	p. 43
4.2 Historical Background	p. 44
4.3 XML Schema Structural Components	p. 45
4.4 XML Schema Data Types	p. 53
4.5 MPEG-7-Specific Extensions	p. 58
4.6 Conclusion	p. 59
References	p. 60
5 Binary Format	p. 61
5.1 Overview	p. 61
5.2 Fragment Update Command and Context	p. 63
5.3 Binary Payload Representation	p. 72
5.4 Conclusion	p. 79
Acknowledgment	p. 80
References	p. 80
Section III Description Schemes	p. 81
6 Overview of Multimedia Description Schemes and Schema Tools	p. 83
6.1 Introduction	p. 83
6.2 Organization of MDS Tools	p. 84
6.3 Schema Tools: MPEG7 Root and Top-Level Elements	p. 88
6.4 Conclusion	p. 92
Acknowledgment	p. 93
References	p. 93
7 Basic Elements	p. 95
7.1 Introduction	p. 95
7.2 Basic Data Types	p. 96
7.3 Linking and Localization Tools	p. 97
7.4 Basic Tools	p. 100
References	p. 109
8 Description of a Single Multimedia Document	p. 111
8.1 Introduction	p. 111
8.2 Content Management	p. 112
8.3 Content Structure	p. 116
8.4 Content Semantics	p. 126
8.5 Conclusion	p. 138
References	p. 138
9 Navigation and Summarization	p. 139
9.1 Introduction	p. 139
9.2 Summarization	p. 140
9.3 Views and View Decompositions	p. 144
9.4 Variations	p. 146
9.5 Conclusion	p. 150
References	p. 150
10 Content Organization	p. 153
10.1 Introduction	p. 153
10.2 Collections	p. 155
10.3 Models	p. 156
10.4 Examples of Usage	p. 159
References	p. 161
11 User Interaction	p. 163
11.1 Introduction	p. 163
11.2 Usage History	p. 165
11.3 User Preferences	p. 168
11.4 Examples of Usage	p. 171
11.5 Conclusion	p. 174
References	p. 174
Section IV Visual Descriptors	p. 177
12 Overview of Visual Descriptors	p. 179
12.1 Introduction	p. 179
12.2 Face Descriptor	p. 181
12.3 A Quantitative Evaluation of Visual Descriptors	p. 183
Acknowledgments	p. 185
References	p. 185
13 Color Descriptors	p. 187
13.1 Introduction	p. 187
13.2 Color Spaces	p. 189
13.3 Dominant Color Descriptor	p. 194
13.4 Scalable Color Descriptor	p. 198
13.5 Group-of-Frame or Group-of-Picture Descriptor	p. 201
13.6 Color Structure Descriptor	p. 204
13.7 Color Layout Descriptor	p. 208
13.8 Summary	p. 211
References	p. 212
14 Texture Descriptors	p. 213
14.1 Introduction	p. 213
14.2 Homogeneous Texture Descriptor	p. 214
14.3 Texture Browsing Descriptor	p. 219
14.4 Edge Histogram Descriptor	p. 223
14.5 Summary	p. 227
Acknowledgments	p. 228
References	p. 228
15 Shape Descriptors	p. 231
15.1 Introduction	p. 231
15.2 Overview of Shape Descriptors	p. 232
15.3 Design and Evaluation of the Shape Descriptors	p. 234
15.4 Region-Based Shape Descriptor	p. 238
15.5 Contour-Shape Descriptor	p. 241
15.6 3-D Shape Descriptor	p. 247
15.7 Example applications of the MPEG-7 Shape Descriptor	p. 256
15.8 Conclusion	p. 258
Acknowledgments	p. 259
References	p. 260
16 Motion Descriptors	p. 261
16.1 Introduction	p. 261
16.2 Motion Basics	p. 262
16.3 Overall Organization of Motion Descriptions	p. 265
16.4 Motion Activity	p. 267
16.5 Camera Motion	p. 270
16.6 Motion Trajectory	p. 273
16.7 Parametric Motion	p. 276
16.8 Conclusion	p. 278
Acknowledgments	p. 279
References	p. 279
Section V Audio	p. 281
17 Fundamentals of Audio Descriptions	p. 283
17.1 The Structure of the Standard	p. 283
17.2 Applications	p. 283
17.3 Overview of Audio Descriptors	p. 286
17.4 Summary	p. 297
Acknowledgments	p. 297
References	p. 298
18 Spoken Content	p. 299
18.1 Spoken Content in The Context of MPEG-7	p. 299
18.2 ASR Technology Today	p. 301
18.3 Metadata Errors in Extraction--A Physical Argument	p. 301
18.4 Interoperability Across Extraction Tools--A Technological Argument	p. 303
18.5 Interoperability Across Databases	p. 305
18.6 Structural Overview of the SpokencontentDescriptionScheme	p. 306
18.7 Usage of the SpokenContentDescriptionScheme in an MPEG-7 Description	p. 312
18.8 Spoken Document Retrieval (SDR)	p. 314
18.9 Summary	p. 315
References	p. 315
19 Sound Classification and Similarity	p. 317
19.1 Spectral Basis Functions	p. 317
19.2 Sound Classification Models	p. 320
19.3 Sound Probability Models	p. 322
19.4 Training a Hidden Markov Model (HMM)	p. 324
19.5 Indexing and Similarity Using Model States	p. 325
19.6 Sound Model Applications	p. 327
19.7 Summary	p. 330
References	p. 331
Section VI Applications	p. 333
20 Search and Browsing	p. 335
20.1 Introduction	p. 335
20.2 Growth of Rich Digital Content	p. 336
20.3 MPEG-7 to the Rescue	p. 336
20.4 Real-Time Video Identification	p. 338
20.5 Query-By-Humming Application	p. 339
20.6 Cuidado	p. 342
20.7 Television News Program Applications	p. 344
20.8 Movie Tool	p. 347
20.9 TV-Anytime and MPEG-7	p. 348
20.10 Conclusion	p. 350
Acknowledgment	p. 350
References	p. 351
21 Mobile Applications	p. 353
21.1 What you want, where you want, when you want. (wyw)[superscript 3]	p. 353
21.2 Customized Multimedia Content Delivery for Mobile Users	p. 354
21.3 Real-time Information Retrieval for Mobile Users	p. 357
21.4 Conclusion	p. 359
Acknowledgments	p. 360
References	p. 360
Index	p. 363

Available:*

On Order

Summary

Summary

Author Notes

Table of Contents