Koschan / Pollefeys / Abidi 3D Imaging for Safety and Security

2007
ISBN: 978-1-4020-6182-0
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 35, 310 Seiten

Reihe: Computational Imaging and Vision

This book presents the thoroughly revised versions of lectures given by leading researchers during the Workshop on Advanced 3D Imaging for Safety and Security in conjunction with the International Conference on Computer Vision and Pattern Recognition CVPR 2005, held in San Diego, CA, USA in June 2005. It covers the current state of the art in 3D imaging for safety and security.

Autoren/Hrsg.

Koschan, Andreas

Pollefeys, Marc

Abidi, Mongi

Inhaltsverzeichnis

1;Contents;6
2;Contributing Authors;8
3;Preface;14
4;Part I Biometrics;17
4.1;Chapter 1 3D ASSISTED FACE RECOGNITION: A SURVEY;18
4.1.1;1. INTRODUCTION;18
4.1.2;2. 3D SENSING FOR FACIAL BIOMETRICS;20
4.1.3;3. 3D FACE MODELS;25
4.1.4;4. FACE REGISTRATION;26
4.1.5;5. USE OF 3D IN RECOGNITION;33
4.1.6;6. SUMMARY AND CONCLUSIONS;34
4.1.7;ACKNOWLEDGMENTS;35
4.1.8;REFERENCES;35
4.2;Chapter 2 A SURVEY ON 3D MODELING OF HUMAN FACES FOR FACE RECOGNITION;40
4.2.1;1. INTRODUCTION;40
4.2.2;2. DATA ACQUISITION AND REPRESENTATION;42
4.2.3;3. ACTIVE MODELING TECHNIQUES;46
4.2.4;4. PASSIVE MODELING TECHNIQUES;51
4.2.5;5. RECONSTRUCTION QUALITY AND COMPARISONS;66
4.2.6;6. USE OF 3D FACE MODELS IN FACE RECOGNITION;68
4.2.7;7. FUTURE TRENDS;70
4.2.8;8. CONCLUSION;72
4.2.9;ACKNOWLEDGEMENT;74
4.2.10;REFERENCES;74
4.3;Chapter 3 AUTOMATIC 3D FACE REGISTRATION WITHOUT INITIALIZATION;84
4.3.1;1. INTRODUCTION;84
4.3.2;2. RELATED WORK;86
4.3.3;3. GAUSSIAN FIELDS FOR 3D FACE REGISTRATION;89
4.3.4;4. EXPERIMENTAL ANALYSIS;93
4.3.5;5. CONCLUSIONS;106
4.3.6;6. ACKNOWLEDGEMENTS;106
4.3.7;REFERENCES;106
4.4;Chapter 4 A GENETIC ALGORITHM BASED APPROACH FOR 3D FACE RECOGNITION;110
4.4.1;1. INTRODUCTION;111
4.4.2;2. FRAMEWORK OF THE SYSTEM;112
4.4.3;3. 3D FACIAL MODEL CREATION;113
4.4.4;4. 3D FACIAL MODEL LABELING;115
4.4.5;5. GOOD FEATURE SELECTION USING A GA-BASED APPROACH;120
4.4.6;6. FACE MODEL MATCHING;123
4.4.7;7. EXPERIMENTS AND ANALYSIS;127
4.4.8;8. CONCLUSIONS AND FUTURE WORK;131
4.4.9;ACKNOWLEDGEMENT;132
4.4.10;REFERENCES;132
4.5;Chapter 5 STORY OF CINDERELLA;134
4.5.1;1. INTRODUCTION;134
4.5.2;2. UBIQUITOUS ISOMETRIES;135
4.5.3;3. FLAT EMBEDDING AND CANONICAL FORMS;137
4.5.4;4. SPHERICAL CANONICAL FORMS;138
4.5.5;5. GENERALIZED MULTIDIMENSIONAL SCALING;139
4.5.6;6. COMPARISON OF PHOTOMETRIC PROPERTIES;142
4.5.7;7. CONCLUSIONS;144
4.5.8;REFERENCES;145
4.6;Chapter 6 HUMAN EAR DETECTION FROM 3D SIDE FACE RANGE IMAGES;148
4.6.1;1. INTRODUCTION;148
4.6.2;2. RELATED WORK, MOTIVATION AND CONTRIBUTIONS OF THE CHAPTER;150
4.6.3;3. TEMPLATE MATCHING BASED EAR DETECTION;152
4.6.4;4. SHAPE MODEL BASED EAR DETECTION;157
4.6.5;5. EXPERIMENTAL RESULTS;161
4.6.6;6. CONCLUSIONS;168
4.6.7;REFERENCES;169
5;Part II Safety and Security Applications;172
5.1;Chapter 7 SYNTHETIC APERTURE FOCUSING USING DENSE CAMERA ARRAYS;174
5.1.1;1. INTRODUCTION;174
5.1.2;2. REFOCUSING WITH HOMOLOGIES;177
5.1.3;3. REAL-TIME SYNTHETIC FOCUS;181
5.1.4;4. CONCLUSIONS;184
5.1.5;ACKNOWLEDGEMENTS;185
5.1.6;REFERENCES;185
5.1.7;APPENDIX A;186
5.2;Chapter 8 DYNAMIC PUSHBROOM STEREO VISION;188
5.2.1;1. INTRODUCTION;188
5.2.2;2. DYNAMIC PUSHBROOM STEREO GEOMETRY;191
5.2.3;3. GAMMA-RAY LINEAR PUSHBROOM STEREO;196
5.2.4;4. DYNAMIC STEREO MOSAICS FROM VIDEO;202
5.2.5;5. CONCLUSIONS AND DISCUSSIONS;211
5.2.6;ACKNOWLEDGEMENTS;213
5.2.7;REFERENCES;213
5.3;Chapter 9 3D MODELING OF INDOOR ENVIRONMENTS;216
5.3.1;1. INTRODUCTION;217
5.3.2;2. TECHNIQUES FOR MODELING 3D SCENES;218
5.3.3;3. OVERVIEW;220
5.3.4;4. HARDWARE PLATFORM AND SENSORS;222
5.3.5;5. BUILDING THE 2D MAP BY SCAN MATCHING;224
5.3.6;6. GENERATION OF GEOMETRY;227
5.3.7;7. GENERATION OF TEXTURES;227
5.3.8;8. ACQUISITION OF ADDITIONAL 3D GEOMETRY USING STEREO;230
5.3.9;9. RESULTS AND CONCLUSION;236
5.3.10;ACKNOWLEDGMENTS;237
5.3.11;REFERENCES;237
5.4;Chapter 10 3D SITE MODELLING AND VERIFICATION;240
5.4.1;1. INTRODUCTION;240
5.4.2;2. TASK COMPLEXITY;241
5.4.3;3. SYSTEM DESCRIPTION;241
5.4.4;4. DATA COLLECTION;243
5.4.5;5. REFERENCE MODEL CONSTRUCTION;251
5.4.6;6. VERIFICATION;252
5.4.7;7. EXPERIMENTS AND RESULTS;255
5.4.8;8. CONCLUSIONS;261
5.4.9;REFERENCES;262
5.5;Chapter 11 UNDER VEHICLE INSPECTION WITH 3D IMAGING;264
5.5.1;1. INTRODUCTION;265
5.5.2;2. THE “SENSOR BRICK” ARCHITECTURE FOR ROBOTIC UNDER VEHICLE INSPECTION;269
5.5.3;3. 3D IMAGING AND VISUALIZATION FOR UNDER VEHICLE INSPECTION;273
5.5.4;4. AUTOMATION FOR THREAT DETECTION;281
5.5.5;5. CONCLUSIONS AND FUTURE DIRECTIONS;290
5.5.6;ACKNOWLEDGEMENTS;291
5.5.7;REFERENCES;291
6;Colour Plate Section;294
7;Index;322

Leseproben

Chapter 2 A SURVEY ON 3D MODELING OF HUMAN FACES FOR FACE RECOGNITION (P. 25)

S. Huq, B. Abidi, S. G. Kong, and M. Abidi
Imaging, Robotics, and Intelligent Systems, The University of Tennessee, Knoxville,
TN 37996-2100, USA.
Abstract:

In its quest for more reliability and higher recognition rates the face recognition community has been focusing more and more on 3D based recognition. Depth information adds another dimension to facial features and provides ways to minimize the effects of pose and illumination variations for achieving greater recognition accuracy. This chapter reviews, therefore, the major techniques for 3D face modeling, the first step in any 3D assisted face recognition system.

The reviewed techniques are laser range scans, 3D from structured light projection, stereo vision, morphing, shape from motion, shape from space carving, and shape from shading. Concepts, accuracy, feasibility, and limitations of these techniques and their effectiveness for 3D face recognition are discussed.

Key words:

3D face reconstruction, face recognition, laser range scanner, structured light, stereo vision, morphing, shape from shading, shape from motion.

1. INTRODUCTION

Biometrics-based techniques such as fingerprint and iris matching often require physical contact or cooperation of the user. Face recognition offers a reliable means for personal identification without requiring much of the participant’s cooperation.

Despite the success in various applications, recognizing human faces in an uncontrolled environment has remained largely unsolved. The appearance of a face, an inherently three-dimensional (3D) object, projected onto a two-dimensional Face recognition has become one of the most active research fields in (2D) space is sensitive to the variations in pose and illumination.

Even, face variations of the same person created by pose and illumination changes could become larger than variations between individuals1. Face recognition techniques assisted with 3D facial models promise to overcome the difficulties and limitations associated with face recognition in 2D space.

In addition to being an important additional feature in recognition, depth plays a crucial role in mitigating variations caused by pose and illumination. In the acquisition of facial images using cameras deployed for surveillance or access control, people move freely with their faces appearing at any angle.

In this case, a smart face recognition system should be able to reproduce the same 2D rendering of the face as in the database for an accurate comparison. Once modeled in 3D, faces can accurately be back projected at any angle for matching.

The major goal of this chapter is to present a comprehensive review of the current technologies for modeling 3D human faces. Several related topics such as (1) the use of 3D face images in face recognition, (2) existing 3D face databases (publicly available), and (3) future trends of 3D face modeling and recognition have also been covered.

3D face modeling techniques can be divided into two classes - active and passive - depending on the imaging modalities and reconstruction methods.