Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video (eBook)
XXV, 126 Seiten
Springer International Publishing (Verlag)
978-3-319-75508-3 (ISBN)
This thesis proposes machine learning methods for understanding scenes via behaviour analysis and online anomaly detection in video. The book introduces novel Bayesian topic models for detection of events that are different from typical activities and a novel framework for change point detection for identifying sudden behavioural changes.
Behaviour analysis and anomaly detection are key components of intelligent vision systems. Anomaly detection can be considered from two perspectives: abnormal events can be defined as those that violate typical activities or as a sudden change in behaviour. Topic modelling and change-point detection methodologies, respectively, are employed to achieve these objectives.
The thesis starts with the development of learning algorithms for a dynamic topic model, which extract topics that represent typical activities of a scene. These typical activities are used in a normality measure in anomaly detection decision-making. The book also proposes a novel anomaly localisation procedure.In the first topic model presented, a number of topics should be specified in advance. A novel dynamic nonparametric hierarchical Dirichlet process topic model is then developed where the number of topics is determined from data. Batch and online inference algorithms are developed.
The latter part of the thesis considers behaviour analysis and anomaly detection within the change-point detection methodology. A novel general framework for change-point detection is introduced. Gaussian process time series data is considered. Statistical hypothesis tests are proposed for both offline and online data processing and multiple change point detection are proposed and theoretical properties of the tests are derived.
The thesis is accompanied by open-source toolboxes that can be used by researchers and engineers.
Supervisor’s Foreword 6
Abstract 8
Acknowledgements 9
Contents 10
Acronyms 13
Notation 14
List of Figures 18
List of Tables 21
1 Introduction 22
1.1 Abnormal Behaviour Detection 23
1.1.1 Topic Modeling 23
1.1.2 Change Point Detection 24
1.2 Key Contributions and Outline 25
1.3 Disseminated Results 27
References 28
2 Background 29
2.1 Outline of Video Processing Methods 29
2.1.1 Object Detection 29
2.1.2 Object Tracking 34
2.2 Anomaly Detection 36
2.2.1 Video Representation 37
2.2.2 Behaviour Model 38
2.2.3 Normality Measure 40
2.3 Topic Modeling 41
2.3.1 Problem Formulation 41
2.3.2 Inference 42
2.3.3 Extensions of Conventional Models 45
2.3.4 Dynamic Topic Models 45
2.3.5 Topic Modeling Applied to Video Analytics 46
2.4 Change Point Detection 47
2.4.1 Change Point Detection in Time Series Data 47
2.4.2 Anomaly as Change Point Detection 48
2.5 Summary 49
References 49
3 Proposed Learning Algorithms for Markov Clustering Topic Model 56
3.1 Video Representation 57
3.2 Model 58
3.2.1 Motivation 58
3.2.2 Model Formulation 59
3.3 Parameter Learning 61
3.3.1 Expectation-Maximisation Learning 62
3.3.2 Variational Inference 65
3.3.3 Gibbs Sampling 67
3.3.4 Similarities and Differences of the Learning Algorithms 68
3.4 Anomaly Detection 68
3.4.1 Abnormal Documents Detection 69
3.4.2 Localisation of Anomalies 71
3.5 Performance Validation 72
3.5.1 Performance Measure 74
3.5.2 Parameter Learning 74
3.5.3 Anomaly Detection 75
3.6 Summary 81
References 83
4 Dynamic Hierarchical Dirichlet Process 84
4.1 Hierarchical Dirichlet Process Topic Model 85
4.1.1 Chinese Restaurant Franchise 86
4.2 Proposed Dynamic Hierarchical Dirichlet Process Topic Model 88
4.3 Inference 89
4.3.1 Batch Collapsed Gibbs Sampling 90
4.3.2 Online Inference 93
4.4 Anomaly Detection 94
4.5 Experiments 95
4.5.1 Synthetic Data 96
4.5.2 Real Video Data 97
4.6 Summary 100
References 100
5 Change Point Detection with Gaussian Processes 1
5.1 Problem Formulation 103
5.1.1 Data Model 103
5.1.2 Change Point Detection Problem Formulation 104
5.2 Gaussian Process Change Point Detection Approach Based on Likelihood Ratio Tests 105
5.2.1 Likelihood Ratio Test 105
5.2.2 Generalised Likelihood Ratio Test 106
5.2.3 Discussion 107
5.3 Gaussian Process Online Change Point Detection Approach Based on Likelihood Estimation 108
5.3.1 Test Formulation 108
5.3.2 Theoretical Evaluation of the Test 109
5.3.3 Test with Estimated Hyperparameters 111
5.3.4 Discussion 111
5.4 Performance Validation on Synthetic Data 112
5.4.1 Data Simulated by the Proposed Generative Model 113
5.4.2 Data Simulated by the GP-BOCPD Model 118
5.5 Numerical Experiments with Real Data 119
5.6 Summary 122
References 123
6 Conclusions and Future Work 124
6.1 Summary of Methods and Contributions 124
6.2 Suggestions for Future Work 126
6.2.1 Inference in Topic Modeling 126
6.2.2 Alternative Dynamics in Topic Modeling 126
6.2.3 Gaussian Process Change Point Detection 127
6.2.4 Potential Applications of the Proposed Statistical Methods 128
References 128
A EM for MCTM Derivation 130
Appendix B VB for MCTM Derivation 134
Appendix C Distributions of Quadratic Forms 137
C.1 Quadratic form of the ``Own'' Covariance Matrix 137
C.2 Quadratic form of an Arbitrary Symmetric Matrix 139
Appendix D Proofs of the Theorems for the Proposed Test Statistic 141
D.1 Proof of Theorem 5.1 141
D.2 Proof of Theorem 5.2 141
Appendix E Optimisation of Gaussian Process Covariance Function Hyperparameters 143
References 144
| Erscheint lt. Verlag | 24.2.2018 |
|---|---|
| Reihe/Serie | Springer Theses |
| Zusatzinfo | XXV, 126 p. 27 illus., 25 illus. in color. |
| Verlagsort | Cham |
| Sprache | englisch |
| Themenwelt | Mathematik / Informatik ► Informatik ► Grafik / Design |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Technik ► Elektrotechnik / Energietechnik | |
| Schlagworte | Anomaly Detection • behaviour analysis • Dynamic Type Models • Intelligent Vision Systems • machine learning |
| ISBN-10 | 3-319-75508-0 / 3319755080 |
| ISBN-13 | 978-3-319-75508-3 / 9783319755083 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 4,4 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.
Zusätzliches Feature: Online Lesen
Dieses eBook können Sie zusätzlich zum Download auch online im Webbrowser lesen.
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
