Search and Find
Service
Human Recognition at a Distance in Video
of: Bir Bhanu, Ju Han
Springer-Verlag, 2010
ISBN: 9780857291240 , 253 Pages
Format: PDF, Read online
Copy protection: DRM
Preface
5
Contents
8
List of Figures
13
List of Tables
21
Introduction to Gait-Based Individual Recognition at a Distance
24
Introduction
25
Gait-Based Human Recognition
26
Face-Based Human Recognition
26
Key Ideas Described in the Book
27
Organization of the Book
29
Gait-Based Individual Recognition at a Distance
32
Gait Representations in Video
33
Human Motion Analysis and Representations
33
Human Activity and Individual Recognition by Gait
34
Human Recognition by Gait
35
Model-Based Approaches
35
Model-Free Approaches
35
Human Activity Recognition
37
Model-Based Approaches
37
Model-Free Approaches
37
Gait Energy Image (GEI) Representation
37
Motivation
38
Representation Construction
38
Relationship with MEI and MHI
38
Representation Justification
39
Framework for GEI-Based Recognition
41
Silhouette Extraction and Processing
41
Feature Extraction
42
Summary
44
Model-Free Gait-Based Human Recognition in Video
45
Statistical Feature Fusion for Human Recognition by Gait
45
Real and Synthetic Gait Templates
46
Human Recognition
48
Experimental Results
50
Data and Parameters
50
Performance Evaluation
52
Human Recognition Based on Environmental Context
53
Walking Surface Type Detection
54
Classifier Design
57
Probabilistic Classifier Combination
58
Experimental Results
59
View-Insensitive Human Recognition by Gait
60
View-Insensitive Gait Templates
60
Human Recognition
62
Experimental Results
63
Human Repetitive Activity Recognition in Thermal Imagery
65
Object Detection in Thermal Infrared Imagery
66
Human Repetitive Activity Representation and Recognition
67
Experimental Results
68
Human Recognition Under Different Carrying Conditions
70
Technical Approach
70
Gait Energy Image (GEI)
70
Feature Extraction
71
Co-evolutionary Genetic Programming
72
Majority Voting
73
Experimental Results
73
Data
73
Experiments
74
Classifier Performance Comparison
74
Summary
75
Discrimination Analysis for Model-Based Gait Recognition
77
Predicting Human Recognition Performance
77
Algorithm Dependent Prediction and Performance Bounds
78
Body Part Length Distribution
78
Algorithm Dependent Performance Prediction
80
Upper Bound on PCR
81
Experimental Results
82
Summary
83
Model-Based Human Recognition-2D and 3D Gait
85
2D Gait Recognition (3D Model, 2D Data)
85
3D Human Modeling
86
Human Kinematic Model
86
Human Model Parameter Selection
87
Camera Model and Coordinate Transformation
88
World Coordinate to Camera Coordinate
89
Camera Coordinate to Ideal Image Coordinate
89
Ideal Image Coordinate to Actual Image Coordinate
89
Actual Image Coordinate to Computer Image Coordinate
90
Human Recognition from Single Non-calibrated Camera
90
Silhouette Preprocessing
90
Matching Between 3D Model and 2D Silhouette
91
Human Model Parameter Estimation
91
Stationary Parameter Estimation
91
Kinematic Parameter Estimation
92
Recognition Based on Kinematic and Stationary Features
93
Kinematic and Stationary Feature Classifier
93
Classifier Combination Strategies
93
Performance Evaluation on Monocular Image Sequences
94
Performance of Stationary Feature Classifier
94
Performance of Kinematic Feature Classifier
95
Performance with Classifier Combination
96
Human Recognition from Multiple Calibrated Cameras
96
Human Model Parameter Selection
96
Matching Between 3D Human Model and Multiple 2D Silhouettes
97
Human Model Parameter Initialization and Estimation
97
Performance Evaluation on Data from Multiple Cameras
98
Gait Recognition in 3D
100
Individual Recognition by Gait in 3D
100
Related Work
101
Technical Approach
103
3D Human Body Data
103
3D Human Body Model
104
Model Fitting
105
Body Axes
105
Torso
106
Arms and Legs
107
Head and Neck
108
Gait Reconstruction
108
Feature Matching
108
Experimental Results
109
Gait Reconstruction
109
Training and Testing Data
110
Gait Recognition
112
Summary
114
Fusion of Color/Infrared Video for Human Detection
115
Related Work
117
Hierarchical Image Registration and Fusion Approach
119
Image Transformation Model
120
Preliminary Human Silhouette Extraction and Correspondence Initialization
121
Automatic Image Registration
122
Model Parameter Selection
122
Parameter Estimation Based on Hierarchical Genetic Algorithm
124
Sensor Fusion
127
Registration of EO/IR Sequences with Multiple Objects
128
Experimental Results
128
Image Registration Results
129
Sensor Fusion Results
132
Summary
133
Face Recognition at a Distance in Video
135
Super-Resolution of Facial Images in Video at a Distance
136
Closed-Loop Super-Resolution of Face Images in Video
137
Related Work
137
Technical Approach
138
Bilinear Basis Images Computation
139
Pose and Illumination Estimation
139
Super-Resolution Algorithm
139
Experimental Results
141
Synthetic Data
141
Real Video
142
Super-Resolution of Facial Images with Expression Changes in Video
143
Related Work
144
Technical Approach
145
Tracking of Facial Regions
146
Local Deformation
147
Free Form Deformation Formulation
147
Cost Function
148
Resolution Aware Local Deformation
148
Deform Local Motion on High Resolution Data
149
Super-Resolution Methodology Requires Sub-pixel Registration
150
Super-Resolution Algorithm
151
A Match Measure for Warping Errors
151
Experimental Results
151
Data and Parameters
151
Results of Resolution Aware FFD
152
Super-Resolution Results-Global Registration vs. Global + RAIFFD Local Deformation
152
Quantification of Performance
153
Proposed Approach with Two Different SR Algorithms
155
Constructing Enhanced Side Face Images from Video
156
Enhanced Side Face Image (ESFI) Construction
158
Technical Approach
158
Acquiring Moving Head of a Person in Video
158
Side Face Image Alignment
158
Elastic Registration Method
158
Match Statistic
160
Resolution Enhancement Algorithm
162
The Imaging Model
162
Algorithm for Resolution Enhancement
163
Side Face Normalization
163
Summary
167
Evaluating Quality of Super-Resolved Face Images
168
Image Quality Indices
168
Integrated Image Quality Index
169
Gray Scale Based Quality (Qg)
171
Structure Based Quality (Qe)
172
Similarity Between Input Images (Qi)
173
Integrated Quality Measure (Qint)
174
Experimental Results for Face Recognition in Video
174
Experiment 1: Influence of Pose Variation on the Super-Resolved Face Image
175
Experiment 2: Influence of Lighting Variation on the Super-Resolved Face Image
177
Experiment 3: Influence of Facial Expression Variation on the Super-Resolved Face Image
178
Experiment 4: Influence of the Number of Images Used for Constructing the Super-Resolved Face Image for Face Recognition
179
Discussion
182
Summary
183
Integrated Face and Gait for Human Recognition at a Distance in Video
184
Integrating Face Profile and Gait at a Distance
185
Introduction
185
Technical Approach
187
High-Resolution Image Construction for Face Profile
187
The Imaging Model
188
The Super Resolution Algorithm
189
Face Profile Representation and Matching
191
Face Profile Extraction
192
Curvature-Based Fiducial Extraction
193
Profile Matching Using Dynamic Time Warping
194
Gait Recognition
196
Integrating Face Profile and Gait for Recognition at a Distance
197
Experimental Results
197
Face Profile-Based Recognition
197
Static Face Database
197
Experimental Results
198
Integrating Face Profile With Gait
199
Video Data
199
Experimental Results
199
Summary
202
Match Score Level Fusion of Face and Gait at a Distance
203
Introduction
204
Related Work
205
Technical Approach
206
Enhanced Side Face Image Construction
207
Gait Energy Image Construction
208
Human Recognition Using ESFI and GEI
208
Feature Learning Using PCA and MDA Combined Method
208
Recognition by Integrating ESFI and GEI
209
Experimental Results and Performance Analysis
211
Experiments and Parameters
211
Experiment 1
212
Experiment 2
216
Experiment 3
218
Performance Analysis
219
Discussion on Experiments
219
Performance Characterization Statistic Q
222
Summary
224
Feature Level Fusion of Face and Gait at a Distance
226
Introduction
226
Technical Approach
229
Human Identification Using ESFI and GEI
231
Feature Learning Using PCA
231
Synthetic Feature Generation and Classification
232
The Related Fusion Schemes
233
Fusion at the Match Score Level
234
Fusion at the Feature Level
235
Experimental Results and Comparisons
235
Experiments and Parameters
235
Experiment 1
239
Experiment 2
241
Discussion on Experiments
247
Summary
249
Conclusions for Integrated Gait and Face for Human Recognition at a Distance in Video
250
Conclusions and Future Work
251
Summary
251
Gait-Based Human Recognition at a Distance
251
Video-Based Human Recognition at a Distance
252
Fusion of Face and Gait for Human Recognition at Distance
253
Future Research Directions
254
References
256
Index
266
All prices incl. VAT