Machine Vision Beyond Visible Spectrum (Augmented Vision And Reality)

✍ Scribed by Hammoud, Riad I(Editor);Ikeuchi, Katsushi(Editor);Fan, Guoliang(Editor);McMillan, Robert W(Editor)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 2011
• Tongue: English
• Leaves: 254
• Series: Augmented vision and reality 1
• Category: Library

✦ Synopsis

The material of this book encompasses many disciplines, including visible,

infrared, far infrared, millimeter wave, microwave, radar, synthetic aperture radar, and

electro-optical sensors as well as the very dynamic topics of image processing, computer

vision and pattern recognition.

This book is composed of six parts:

Advanced background modeling for surveillance

Advances in Tracking in Infrared imagery

Methods for Pose estimation in Ultrasound and LWIR imagery

Recognition in multi-spectral and synthetic aperture radar

Fusion of disparate sensors

Smart Sensors

✦ Table of Contents

1 Introduction......Page 2
1.3 Target Tracking......Page 4
3.1 Motion Compensation......Page 7
Cover......Page 1
Preface......Page 5
Contents......Page 8
5 Descriptor Construction......Page 9
7 Experiments......Page 13
5.3 Simulated Experimental Results......Page 14
2.3 Experimental Results......Page 19
3.1 Local Feature Based Integration of Tracking and Detection......Page 24
4.3 Fringe-Adjusted JTC Based Target Tracking......Page 27
References......Page 28
3 Harmonic Analysis......Page 6
Part ITracking and Recognition in Infrared......Page 10
Local Feature Based Person Detection and Tracking Beyond the Visible Spectrum......Page 11
2.1 Local Feature Based Person Detection......Page 15
6 Conclusion and Discussions......Page 16
3.2 Target Detection and Tracking......Page 17
2.2 Body Part Classification......Page 18
3.3 Test Results......Page 20
4 Discussion......Page 25
3.2 Results and Evaluation......Page 29
4.4 Test Results......Page 30
1 Introduction......Page 12
Machine Vision Beyond Visible Spectrum......Page 3
3 Person Tracking......Page 23
5 Conclusion......Page 33
3.3 Tracking Under Strong Camera Motion......Page 34
3.3 Tracking......Page 21
References......Page 31
4 Conclusion......Page 37
References......Page 38
Appearance Learning for Infrared Tracking with Occlusion Handling......Page 41
1 Introduction......Page 42
2 Related Work......Page 44
3 Problem Formulation......Page 46
4.1 Histogram Similarity......Page 48
4.2 Kalman Filtering......Page 49
4.3 AKF Covariance Matching (AKFcov)......Page 50
4.4 AKF Autocovariance Based Least Squares (AKFals)......Page 51
4.5 Comparison Between AKFals and AKFcov......Page 55
5.1 Dual Foreground--Background Appearance Model......Page 56
5.2 Target Dynamics......Page 57
5.3 Target Tracking with Appearance Learning......Page 58
7.1 Experiments on the AMCOM Dataset......Page 60
7.2 Experiments on the VIVID Dataset......Page 65
8 Conclusion......Page 69
References......Page 70
3D Model-Driven Vehicle Matching and Recognition......Page 73
1 Introduction......Page 74
2.2 Inverse Rendering......Page 76
2.3 Near-IR Illumination......Page 77
3.1 Model Determination......Page 78
3.2 Pose Recovery......Page 79
3.3 Estimation of Reflectance Fraction......Page 80
3.4 Illumination Recovery......Page 82
3.5 Re-lighting......Page 83
3.6 Vehicle Matching......Page 84
4 Near-IR Illumination......Page 85
5 Experimental Results......Page 86
5.1 Matching Experiments......Page 87
References......Page 91
Pattern Recognition and Tracking in Forward Looking Infrared Imagery......Page 94
1 Introduction......Page 95
2 FKT Based Pattern Recognition and Tracking......Page 96
2.1 Global Motion Compensation......Page 98
2.2 Fukunaga--Koontz Transform......Page 100
2.3 FKT Based Detection and Tracking......Page 102
2.4 Test Results......Page 104
2.5 Conclusion......Page 105
3 Pattern Recognition via Optoelectronic Correlation......Page 106
3.1 Fringe-Adjusted JTC......Page 107
3.2 Target Detection and Tracking......Page 110
3.3 Test Results......Page 113
3.4 Conclusion......Page 116
4 Invariant Object Detection and Tracking......Page 117
4.1 Fringe-Adjusted JTC Based Motion Estimation......Page 118
4.3 Fringe-Adjusted JTC Based Target Tracking......Page 120
4.4 Test Results......Page 123
5 Conclusion......Page 126
References......Page 127
A Bayesian Method for Infrared Face Recognition......Page 130
1 Introduction......Page 131
2 Generalized Gaussian Mixture Model......Page 132
3 Bayesian Learning of the GGM......Page 134
3.1 Hierarchical Model, Priors and Posteriors......Page 135
3.2 Complete Algorithm......Page 138
4 Experimental Results......Page 139
5 Conclusion......Page 142
References......Page 143
Part IIMulti-Sensor Fusion and Smart Sensors......Page 146
Fusion of a Camera and a Laser Range Sensor for Vehicle Recognition......Page 147
1 Introduction......Page 148
2 System Configuration......Page 149
3 Segmenting Vehicles from Laser Range Data......Page 150
3.1 Side Surface-Based Method......Page 151
3.3 Detection Results......Page 152
4.1 Calibration Results......Page 154
5 Refinement of Segmentation......Page 155
5.1 Graph Cut Method......Page 156
6.1 Classification Method......Page 157
6.2 Classification Results......Page 159
7 Discussion......Page 160
8 Conclusion......Page 162
1 Introduction......Page 164
1.1 What is Needed?......Page 165
1.2 A System Approach......Page 166
2 System Architecture......Page 167
3 A Bio-Inspired Sensor Design......Page 169
4 Scene Simulation and Sensor Modeling......Page 171
5.1 Detection and Tracking in Peripheral Views......Page 173
5.2 Target Classification Using 3D and HSI Fovea......Page 175
5.3 Simulated Experimental Results......Page 177
6 Conclusion and Discussions......Page 179
References......Page 181
Part III Hyperspectral Image Analysis......Page 182
Affine Invariant Hyperspectral Image Descriptors Based upon Harmonic Analysis......Page 183
1 Introduction......Page 184
2 Heavy-Tailed Distributions......Page 186
3 Harmonic Analysis......Page 188
4 Invariance to Affine Distortions......Page 190
5 Descriptor Construction......Page 191
6 Implementation Issues......Page 194
7 Experiments......Page 195
8 Conclusion......Page 200
References......Page 201
Tracking and Identification via Object Reflectance Using a Hyperspectral Video Camera......Page 204
1 Introduction......Page 205
2 The Hyperspectral Video Camera......Page 206
3 Estimating Object Reflectance......Page 207
4.1 Framework of Particle Filter......Page 211
4.2 Appearance Model......Page 213
4.3 Adaptive Velocity......Page 214
5.1 Sequential Recognition......Page 215
7 Conclusion......Page 221
References......Page 222
Moving Object Detection and Tracking in Forward Looking Infra-Red Aerial Imagery......Page 223
1 Introduction......Page 224
1.1 Ego-Motion Compensation......Page 225
1.2 Regions of Interest Detection......Page 226
2 Related Work......Page 227
3.1 Motion Compensation......Page 229
3.2 Object Detection......Page 237
3.3 Tracking......Page 243
4 Discussion......Page 247
5 Conclusion......Page 251
References......Page 253