Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010126625 | TK7882.B56 N49 2006 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
Human Identification Based on Gait is the first book to address gait as a biometric. Biometrics is now in a unique position where it affects most people's lives. This is especially true of "gait", which is one of the most recent biometrics. Recognizing people by the way they walk and run implies analyzing movement which, in turn, implies analyzing sequences of images, thus requiring memory and computational performance that became available only recently. Human Identification Based on Gait introduces developments from distinguished researchers within this relatively new area of biometrics. This book clearly establishes how human gait is biometric.
Human Identification Based on Gait is structured to meet the needs of professionals in industry, as well as advanced-level students in computer science.
Table of Contents
Preface | p. vii |
1 Introduction | p. 1 |
1.1 Biometrics and Gait | p. 1 |
1.2 Contexts | p. 2 |
1.2.1 Immigration and Homeland Security | p. 2 |
1.2.2 Surveillance | p. 2 |
1.2.3 Human ID at a Distance (HiD) Program | p. 3 |
1.3 Book Structure | p. 3 |
2 Subjects Allied to Gait | p. 5 |
2.1 Overview | p. 5 |
2.2 Literature | p. 5 |
2.3 Medicine and Biomechanics | p. 6 |
2.3.1 Basic Gait Analysis | p. 6 |
2.3.2 Variation in Gait Covariate Factors | p. 10 |
2.4 Psychology | p. 12 |
2.5 Computer Vision-Based Human Motion Analysis | p. 13 |
2.6 Other Subjects Allied to Gait | p. 15 |
3 Gait Databases | p. 17 |
3.1 Early Databases | p. 17 |
3.1.1 UCSD Gait Data | p. 17 |
3.1.2 Early Soton Gait Data | p. 18 |
3.2 Current Databases | p. 20 |
3.2.1 Overall Design Considerations | p. 20 |
3.2.2 NIST/USF Database | p. 21 |
3.2.3 Soton Database | p. 22 |
Overview | p. 22 |
Laboratory Layout | p. 24 |
Outdoor Data Design Issues | p. 27 |
Acquisition Set-up Procedure | p. 29 |
Filming Issues | p. 29 |
Recording Procedure | p. 30 |
Ancillary Data | p. 31 |
3.2.4 CASIA Database | p. 32 |
3.2.5 UMD Database | p. 33 |
4 Early Recognition Approaches | p. 35 |
4.1 Initial Objectives and Constraints | p. 35 |
4.2 Silhouette Based | p. 35 |
4.3 Model Based | p. 39 |
5 Silhouette-Based Approaches | p. 45 |
5.1 Overview | p. 45 |
5.2 Extending Shape Description to Moving Shapes | p. 48 |
5.2.1 Area Masks | p. 49 |
5.2.2 Gait Symmetry | p. 51 |
5.2.3 Velocity Moments | p. 53 |
5.2.4 Results | p. 54 |
Recognition by Area Masks | p. 55 |
Recognition by Symmetry | p. 58 |
Recognition by Velocity Moments | p. 61 |
5.2.5 Potency of Measurements of Silhouette | p. 63 |
5.3 Procrustes and Spatiotemporal Silhouette Analysis | p. 65 |
5.3.1 Automatic Gait Recognition Based on Procrustes Shape Analysis | p. 65 |
5.3.2 Silhouette Detection and Representation for Procrustes Analysis | p. 66 |
Silhouette Extraction | p. 66 |
Representation of Silhouette Shapes | p. 68 |
5.3.3 Procrustes Gait Feature Extraction and Classification | p. 69 |
Procrustes Shape Analysis | p. 69 |
Gait Signature Extraction | p. 69 |
Similarity Measure and Classifier | p. 70 |
5.3.4 Spatiotemporal Silhouette Analysis Based Gait Recognition | p. 70 |
Spatiotemporal Feature Extraction | p. 72 |
Feature Extraction and Classification | p. 73 |
5.3.5 Experimental Results and Analysis | p. 77 |
Procrustes Shape Analysis | p. 77 |
Spatiotemporal Silhouette Analysis | p. 82 |
5.4 Modeling, Matching, Shape and Kinematics | p. 89 |
5.4.1 HMM Based Gait Recognition | p. 89 |
Gait Recognition Framework | p. 90 |
Direct Approach | p. 91 |
Indirect Approach | p. 93 |
5.4.2 DTW Based Gait Recognition | p. 94 |
Gait Recognition Framework | p. 96 |
5.4.3 Shape and Kinematics | p. 97 |
Shape Analysis | p. 97 |
Dynamical Models | p. 98 |
5.4.4 Results | p. 100 |
HMM Based Gait Recognition | p. 100 |
DTW Based Gait Recognition | p. 102 |
Shape and Kinematics | p. 104 |
6 Model-Based Approaches | p. 107 |
6.1 Overview | p. 107 |
6.2 Planar Human Modeling | p. 109 |
6.2.1 Modeling Walking and Running | p. 109 |
6.2.2 Model-Based Extraction and Description | p. 111 |
6.3 Kinematics-based People Tracking and Recognition in 3D Space | p. 114 |
6.3.1 Model-based People Tracking using Condensation | p. 114 |
Human Body Model | p. 115 |
Learning Motion Model and Motion Constraints | p. 117 |
Experiments and Discussions | p. 125 |
6.4 Other Approaches | p. 131 |
6.4.1 Structure by Body Parameters | p. 132 |
6.4.2 Structural Model-based Recognition | p. 132 |
7 Further Gait Developments | p. 135 |
7.1 View Invariant Gait Recognition | p. 135 |
7.1.1 Overview of the Algorithm | p. 136 |
7.1.2 Optical flow based SfM approach | p. 137 |
7.1.3 Homography based approach | p. 138 |
7.1.4 Experimental Results | p. 138 |
7.2 Gait Biometric Fusion | p. 141 |
7.3 Fusion of Static and Dynamic Body Biometrics for Gait Recognition | p. 144 |
7.3.1 Overview of Approach | p. 144 |
7.3.2 Classifiers and Fusion Rules | p. 145 |
7.3.3 Experimental Results and Analysis | p. 146 |
8 Future Challenges | p. 151 |
References | p. 157 |
Literature | p. 157 |
Medicine and Biomechanics | p. 157 |
Covariate factors | p. 158 |
Psychology | p. 159 |
Computer Vision-Based Analysis of Human Motion | p. 160 |
Databases | p. 161 |
Early work | p. 162 |
Current approaches | p. 163 |
Further Analysis | p. 166 |
Other Related Work | p. 169 |
General | p. 169 |
9 Appendices | p. 171 |
Appendix 9.1 Southampton Data Acquisition Forms | p. 171 |
Appendix 9.1.1 Laboratory Set-up Forms | p. 171 |
Appendix 9.1.2 Camera Set-up Forms | p. 175 |
Appendix 9.1.3 Session Coordinator's Instructions | p. 180 |
Appendix 9.1.4 Subject Information Form | p. 182 |
Index | p. 185 |