Intelligent Surveillance Systems (eBook)
XX, 168 Seiten
Springer Netherland (Verlag)
978-94-007-1137-2 (ISBN)
Surveillance systems have become increasingly popular. Full involvement of human operators has led to shortcomings, e.g. high labor cost, limited capability for multiple screens, inconsistency in long-duration, etc. Intelligent surveillance systems (ISSs) can supplement or even replace traditional ones. In ISSs, computer vision, pattern recognition, and artificial intelligence technologies are used to identify abnormal behaviours in videos. They present the development of real-time behaviour-based intelligent surveillance systems. The book focuses on the detection of individual abnormal behaviour based on learning and the analysis of dangerous crowd behaviour based on texture and optical flow. Practical systems include a real-time face classification and counting system, a surveillance robot system that utilizes video and audio information for intelligent interaction, and a robust person counting system for crowded environments.
Preface 7
Contents 8
List of Figures 11
List of Tables 16
Chapter 1Introduction 17
1.1 Background 17
1.2 Existing Surveillance Systems 18
1.3 Book Contents 19
1.4 Conclusion 21
Chapter 2 Background/Foreground Detection 22
2.1 Introduction 22
2.2 Pattern Classification Method 22
2.2.1 Overview of Background Update Methods 22
2.2.1.1 Multi-Frame Average Method 23
2.2.1.2 Selection Method 23
2.2.1.3 Selection-Average Method 24
2.2.1.4 Kalman Filter-based Adaptive Background Update Method 24
2.2.1.5 Another Adaptive Background Update Method 24
2.2.1.6 Current Applications of Background Update Methods 25
2.2.2 Pattern Classification-based Adaptive Background Update Method 26
2.3 Frame Differencing Method 31
2.4 Optical Flow Method 35
2.5 Conclusion 36
Chapter 3 Segmentation and Tracking 37
3.1 Introduction 37
3.2 Segmentation 37
3.3 Tracking 42
3.3.1 Hybrid Tracking Method 42
3.3.1.1 Distance Tracking 42
3.3.1.2 Color Tracking 43
3.3.1.3 Fusion of the Two Tracking Approaches 45
3.3.1.4 Experimental Study 45
3.3.2 Particle Filter-based Tracking Method 45
3.3.2.1 Target Model Update 48
3.3.3 Local Binary Pattern-based Tracking Method 49
3.3.3.1 Multiple Target Tracking 52
3.3.3.2 Kalman Filter 52
3.3.3.3 LBP Histogram Distance 54
3.3.3.4 Blob Classification 54
3.3.3.5 Experiment and Discussion 55
3.4 Conclusion 57
Chapter 4 Behavior Analysis of Individuals 58
4.1 Introduction 58
4.2 Learning-based Behavior Analysis 58
4.2.1 Contour-based Feature Analysis 58
4.2.1.1 Preprocessing 58
4.2.1.2 Supervised PCA for Feature Generation 59
4.2.1.3 SVM classifiers 60
4.2.1.4 Experiments 61
4.2.2 Motion-based Feature Analysis 62
4.2.2.1 Mean Shift-based Motion Feature Searching 62
4.2.2.2 Motion History Image-based Analysis 64
4.2.2.3 Frame Work Analysis 65
4.2.2.4 SVM-based Learning 66
4.2.2.5 Recognition using a Bayesian Network 66
4.2.2.6 Experiments 67
4.3 Rule-based Behavior Analysis 68
4.4 Application: Household Surveillance Robot 69
4.4.1 System Implementation 73
4.4.2 Combined Surveillance with Video and Audio 74
4.4.2.1 MFCC Feature Extraction 75
4.4.2.2 Support Vector Machine 77
4.4.3 Experimental Results 78
4.5 Conclusion 81
Chapter 5 Facial Analysis of Individuals 83
5.1 Feature Extraction 85
5.1.1 Supervised PCA for Feature Generation 85
5.1.2 ICA-based Feature Extraction 87
5.2 Fusion of SVM Classifiers 88
5.3 System and Experiments 90
5.3.1 Implementation 91
5.3.2 Experiment Result 92
5.4 Conclusion 92
Chapter 6 Behavior Analysis of Human Groups 93
6.1 Introduction 93
6.2 Agent Tracking and Status Analysis 94
6.3 Group Analysis 95
6.3.1 Queuing 97
6.3.2 Gathering and Dispersing 99
6.4 Experiments 100
6.4.1 Multi-Agent Queuing 102
6.4.2 Gathering and Dispersing 102
6.5 Conclusion 103
Chapter 7 Static Analysis of Crowds: Human Counting and Distribution 104
7.1 Blob-based Human Counting and Distribution 104
7.1.1 Overview 105
7.1.2 Preprocessing 107
7.1.3 Input Selection 107
7.1.4 Blob Learning 109
7.1.5 Experiments 110
7.1.6 Conclusion 112
7.2 Feature-based Human Counting and Distribution 112
7.2.1 Overview 113
7.2.2 Initial Calibration 115
7.2.2.1 Multiresolution Density Cells with a Perspective Projection Model 115
7.2.2.2 Normalization of Density Cells 119
7.2.3 Density Estimation 119
7.2.3.1 Feature Extraction 120
7.2.3.2 Searching for the Characteristic Scale 121
7.2.3.3 System Training 123
7.2.4 Detection of an Abnormal Density Distribution 123
7.2.4.1 Training Data Created by Computer Simulation 123
7.2.4.2 System Training and Testing 124
7.2.5 Experiment Results 125
7.2.6 Conclusion 128
Chapter 8 Dynamic Analysis of Crowd Behavior 129
8.1 Behavior Analysis of Individuals in Crowds 129
8.2 Energy-based Behavior Analysis of Groups in Crowds 130
8.2.1 First Video Energy 133
8.2.1.1 Definition of First Video Energy 133
8.2.1.2 Quartation Algorithm 135
8.2.2 Second Video Energy 137
8.2.2.1 Motion Feature 137
8.2.2.2 Definition of Second Video Energy 139
8.2.3 Third Video Energy 141
8.2.3.1 Definition of Third Video Energy 141
8.2.3.2 Angle Field Analysis 142
8.2.3.3 Weighted Coefficients Design 142
8.2.4 Experiment using a Metro Surveillance System 143
8.2.4.1 Description of Abnormality 144
8.2.4.2 Wavelet Analysis 144
8.2.4.3 Comparison of Two Kinds of Video Energy 146
8.2.5 Experiment Using an ATM Surveillance System 147
8.2.5.1 Sensitive Area Monitoring Subsystem 148
8.2.5.2 Aggressive Behaviors Detection Subsystem 148
8.2.5.3 Logical Decision-Making Subsystem 149
8.2.5.4 Experiments 149
8.3 RANSAC-based Behavior Analysis of Groups in Crowds 156
8.3.1 Random Sample Consensus (RANSAC) 156
8.3.2 Estimation of Crowd Flow Direction 158
8.3.3 Definition of a Group in a Crowd (Crowd Group) 160
8.3.4 Experiment and Discussion 162
References 165
Index 175
| Erscheint lt. Verlag | 19.3.2011 |
|---|---|
| Reihe/Serie | Intelligent Systems, Control and Automation: Science and Engineering | Intelligent Systems, Control and Automation: Science and Engineering |
| Zusatzinfo | XX, 168 p. |
| Verlagsort | Dordrecht |
| Sprache | englisch |
| Themenwelt | Informatik ► Grafik / Design ► Digitale Bildverarbeitung |
| Informatik ► Netzwerke ► Sicherheit / Firewall | |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Technik ► Elektrotechnik / Energietechnik | |
| Technik ► Maschinenbau | |
| Schlagworte | Artificial Intelligence • Computational Intelligence • computer vision • pattern recognition • Surveillance |
| ISBN-10 | 94-007-1137-9 / 9400711379 |
| ISBN-13 | 978-94-007-1137-2 / 9789400711372 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 6,7 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
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 dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
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 dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
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
