Unified Framework for Video Summarization, Browsing & Retrieval (eBook)
296 Seiten
Elsevier Science (Verlag)
978-0-08-048153-1 (ISBN)
The authors discuss the generation of table of contents, extraction of highlights, different techniques for audio and video marker recognition, and indexing with low-level features such as color, texture, and shape. Current applications including this summarization and browsing technology are also reviewed. Applications such as event detection in elevator surveillance, highlight extraction from sports video, and image and video database management are considered within the proposed framework. This book presents the latest in research and readers will find their search for knowledge completely satisfied by the breadth of the information covered in this volume.
* Offers the latest in cutting edge research and applications in surveillance and consumer video
* Presentation of a novel unified framework aimed at successfully sifting through the abundance of footage gathered daily at shopping malls, airports, and other commercial facilities
* Concisely written by leading contributors in the signal processing industry with step-by-step instruction in building video ToC and indices
Large volumes of video content can only be easily accessed by the use of rapid browsing and retrieval techniques. Constructing a video table of contents (ToC) and video highlights to enable end users to sift through all this data and find what they want, when they want are essential. This reference puts forth a unified framework to integrate these functions supporting efficient browsing and retrieval of video content. The authors have developed a cohesive way to create a video table of contents, video highlights, and video indices that serve to streamline the use of applications in consumer and surveillance video applications. The authors discuss the generation of table of contents, extraction of highlights, different techniques for audio and video marker recognition, and indexing with low-level features such as color, texture, and shape. Current applications including this summarization and browsing technology are also reviewed. Applications such as event detection in elevator surveillance, highlight extraction from sports video, and image and video database management are considered within the proposed framework. This book presents the latest in research and readers will find their search for knowledge completely satisfied by the breadth of the information covered in this volume.* Offers the latest in cutting edge research and applications in surveillance and consumer video* Presentation of a novel unified framework aimed at successfully sifting through the abundance of footage gathered daily at shopping malls, airports, and other commercial facilities* Concisely written by leading contributors in the signal processing industry with step-by-step instruction in building video ToC and indices
Front Cover 1
A UNIFIED FRAMEWORK FOR VIDEO SUMMARIZATION, BROWSING, AND RETRIEVAL 4
Copyright Page 5
Contents 8
List of Figures 12
List of Tables 18
Preface 20
Acknowledgments 22
Chapter 1. Introduction 24
1.1 Introduction 24
1.2 Terminology 26
1.3 Video Analysis 29
1.4 Video Representation 30
1.5 Video Browsing and Retrieval 34
1.6 The Rest of the Book 35
Chapter 2. Video Table-of-Content Generation 38
2.1 Introduction 38
2.2 Related Work 40
2.3 The Proposed Approach 43
2.4 Determination of the Parameters 53
2.5 Experimental Results 56
2.6 Conclusions 60
Chapter 3. Highlights Extraction from Unscripted Video 62
3.1 Introduction 62
3.2 Audio Marker Recognition 65
3.3 Visual Marker Detection 75
3.4 Finer-Resolution Highlights Extraction 94
3.5 Conclusions 119
Chapter 4. Video Structure Discovery Using Unsupervised Learning 120
4.1 Motivation and Related Work 120
4.2 Proposed Inlier/Outlier–Based Representation for “Unscripted” Multimedia Using Audio Analysis 121
4.3 Feature Extraction and the Audio Classification Framework 124
4.4 Proposed Time Series Analysis Framework 134
4.5 Ranking Outliers for Summarization 164
4.6 Application to Consumer Video Browsing 177
4.7 Systematic Acquisition of Key Audio Classes 202
4.8 Possibilities for Future Research 215
Chapter 5. Video Indexing 222
5.1 Introduction 222
5.2 Indexing with Low-Level Features: Motion 223
5.3 Indexing with Low-Level Features: Color 235
5.4 Indexing with Low-Level Features: Texture 236
5.5 Indexing with Low-Level Features: Shape 237
5.6 Indexing with Low-Level Features: Audio 238
5.7 Indexing with User Feedback 240
5.8 Indexing Using Concepts 241
5.9 Discussion and Conclusions 242
Chapter 6. A Unified Framework for Video Summarization, Browsing, and Retrieval 244
6.1 Video Browsing 244
6.2 Video Highlights Extraction 246
6.3 Video Retrieval 250
6.4 A Unified Framework for Summarization, Browsing, and Retrieval 252
6.5 Conclusions and Promising Research Directions 258
Chapter 7. Applications 260
7.1 Introduction 260
7.2 Consumer Video Applications 261
7.3 Image/Video Database Management 265
7.4 Surveillance 267
7.5 Challenges of Current Applications 270
7.6 Conclusions 270
Chapter 8. Conclusions 272
Bibliography 276
About the Authors 284
Index 288
Erscheint lt. Verlag | 16.1.2006 |
---|---|
Sprache | englisch |
Themenwelt | Sachbuch/Ratgeber |
Mathematik / Informatik ► Informatik ► Datenbanken | |
Informatik ► Grafik / Design ► Digitale Bildverarbeitung | |
Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
Naturwissenschaften ► Physik / Astronomie ► Elektrodynamik | |
Technik ► Elektrotechnik / Energietechnik | |
ISBN-10 | 0-08-048153-1 / 0080481531 |
ISBN-13 | 978-0-08-048153-1 / 9780080481531 |
Haben Sie eine Frage zum Produkt? |
Kopierschutz: Adobe-DRM
Adobe-DRM ist ein Kopierschutz, der das eBook vor Mißbrauch schützen soll. Dabei wird das eBook bereits beim Download auf Ihre persönliche Adobe-ID autorisiert. Lesen können Sie das eBook dann nur auf den Geräten, welche ebenfalls auf Ihre Adobe-ID registriert sind.
Details zum Adobe-DRM
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen eine
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen eine
Geräteliste und zusätzliche Hinweise
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich