In the areas of image processing and computer vision, there is a particular need for software that can, given an unfocused or motion-blurred image, infer the three-dimensional shape of a scene. This book describes the analytical processes that go into designing such software, delineates the options open to programmers, and presents original algorithms. Written for readers with interests in image processing and computer vision and with backgrounds in engineering, science or mathematics, this highly practical text/reference is accessible to advanced students or those with a degree that includes basic linear algebra and calculus courses.
Author(s): Paolo Favaro, Stefano Soatto
Edition: 1st Edition.
Year: 2006
Language: English
Pages: 262
Tags: Информатика и вычислительная техника;Обработка медиа-данных;Обработка изображений;
Cover......Page 1
3-D Shape
Estimation and
Image Restoration......Page 3
ISBN-10: 1846281768......Page 4
Preface......Page 6
Organizational chart......Page 8
Contents......Page 9
1
Introduction......Page 14
2
Basic models of image formation......Page 27
3
Some analysis: When can 3-D shape be
reconstructed from blurred images?......Page 50
4
Least-squares shape from defocus......Page 63
5
Enforcing positivity: Shape from
defocus and image restoration by
minimizing I-divergence......Page 82
6
Defocus via diffusion: Modeling and
reconstruction......Page 100
7
Dealing with motion: Unifying defocus
and motion blur......Page 119
8
Dealing with multiple moving objects......Page 133
9
Dealing with occlusions......Page 160
10
Final remarks......Page 172
Appendix A
Concepts of radiometry......Page 174
Appendix B
Basic primer on functional optimization......Page 181
Appendix C
Proofs......Page 203
Appendix D
Calibration of defocused images......Page 210
Appendix E
MATLAB implementation of some
algorithms......Page 215
Appendix F
Regularization......Page 245
References......Page 252
Index......Page 260
