Muutke küpsiste eelistusi

3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur 2007 ed. [Kõva köide]

,
  • Formaat: Hardback, 249 pages, kõrgus x laius: 235x155 mm, kaal: 565 g, XIV, 249 p., 1 Hardback
  • Ilmumisaeg: 29-Dec-2006
  • Kirjastus: Springer London Ltd
  • ISBN-10: 1846281768
  • ISBN-13: 9781846281761
Teised raamatud teemal:
  • Kõva köide
  • Hind: 48,66 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 57,25 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur 2007 ed.Suurem pilt
  • Formaat: Hardback, 249 pages, kõrgus x laius: 235x155 mm, kaal: 565 g, XIV, 249 p., 1 Hardback
  • Ilmumisaeg: 29-Dec-2006
  • Kirjastus: Springer London Ltd
  • ISBN-10: 1846281768
  • ISBN-13: 9781846281761
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781846281761.html
Märksõnad:
Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer thr- dimensional information. For instance, if the scene contains objects made with homogeneous material, such as marble, variations in image intensity can be - sociated with variations in shape, and hence the shading in the image can be exploited to infer the shape of the scene (shape from shading). Similarly, if the scene contains (statistically) regular structures, variations in image intensity can be used to infer shape (shape from textures). Shading, texture, cast shadows, - cluding boundaries are all cues that can be exploited to infer spatial properties of the scene from a single image, when the underlying assumptions are sat- ?ed. In addition, one can obtain spatial cues from multiple images of the same scene taken with changing conditions. For instance, changes in the image due to a moving light source are used in photometric stereo, changes in the image due to changes in the position of the cameras are used in stereo, structure from motion, and motion blur. Finally, changes in the image due to changes in the geometry of the camera are used in shape from defocus. In this book, we will concentrate on the latter two approaches, motion blur and defocus, which are referred to collectively as accommodation cues.

Arvustused

"This book presents a framework for estimating three-dimensional (3D) shapes from defocused and motion-blurred images. The book systematically describes various problems involved in estimating 3D shapes, and provides solutions to these problems The book is well-written, and is equipped with Matlab code that implements the estimators presented in the chapters I recommend this book to engineers in image processing and computer vision. Readers will learn state-of-the-art methods for shape restoration." (Hsun-Hsien Chang, ACM Computing Reviews, Vol. 49 (9), September 2008)

Preface vii
1 Introduction
1
1.1 The sense of vision
1
1.1.1 Stereo
4
1.1.2 Structure from motion
5
1.1.3 Photometric stereo and other techniques based on controlled light
5
1.1.4 Shape from shading
6
1.1.5 Shape from texture
6
1.1.6 Shape from silhouettes
6
1.1.7 Shape from defocus
6
1.1.8 Motion blur
7
1.1.9 On the relative importance and integration of visual cues
7
1.1.10 Visual inference in applications
8
1.2 Preview of coming attractions
9
1.2.1 Estimating 3-D geometry and photometry with a finite aperture
9
1.2.2 Testing the power and limits of models for accommodation cues
10
1.2.3 Formulating the problem as optimal inference
11
1.2.4 Choice of optimization criteria, and the design of optimal algorithms
12
1.2.5 Variational approach to modeling and inference from accommodation cues
12
2 Basic models of image formation
14
2.1 The simplest imaging model
14
2.1.1 The thin lens
14
2.1.2 Equifocal imaging model
16
2.1.3 Sensor noise and modeling errors
18
2.1.4 Imaging models and linear operators
19
2.2 Imaging occlusion-free objects
20
2.2.1 Image formation nuisances and artifacts
22
2.3 Dealing with occlusions
23
2.4 Modeling defocus as a diffusion process
26
2.4.1 Equifocal imaging as isotropic diffusion
28
2.4.2 Nonequifocal imaging model
29
2.5 Modeling motion blur
30
2.5.1 Motion blur as temporal averaging
30
2.5.2 Modeling defocus and motion blur simultaneously
34
2.6 Summary
35
3 Some analysis: When can 3-D shape be reconstructed from blurred images?
37
3.1 The problem of shape from defocus
38
3.2 Observability of shape
39
3.3 The role of radiance
41
3.3.1 Harmonic components
42
3.3.2 Band-limited radiances and degree of resolution
42
3.4 Joint observability of shape and radiance
46
3.5 Regularization
46
3.6 On the choice of objective function in shape from defocus
47
3.7 Summary
49
4 Least-squares shape from defocus
50
4.1 Least-squares minimization
50
4.2 A solution based on orthogonal projectors
53
4.2.1 Regularization via truncation of singular values
53
4.2.2 Learning the orthogonal projectors from images
55
4.3 Depth-map estimation algorithm
58
4.4 Examples
60
4.4.1 Explicit kernel model
60
4.4.2 Learning the kernel model
61
4.5 Summary
65
5 Enforcing positivity: Shape from defocus and image restoration by minimizing I-divergence
69
5.1 Information-divergence
70
5.2 Alternating minimization
71
5.3 Implementation
76
5.4 Examples
76
5.4.1 Examples with synthetic images
76
5.4.2 Examples with real images
78
5.5 Summary
79
6 Defocus via diffusion: Modeling and reconstruction
87
6.1 Blurring via diffusion
88
6.2 Relative blur and diffusion
89
6.3 Extension to space-varying relative diffusion
90
6.4 Enforcing forward diffusion
91
6.5 Depth-map estimation algorithm
92
6.5.1 Minimization of the cost functional
94
6.6 On the extension to multiple images
95
6.7 Examples
96
6.7.1 Examples with synthetic images
97
6.7.2 Examples with real images
99
6.8 Summary
99
7 Dealing with motion: Unifying defocus and motion blur
106
7.1 Modeling motion blur and defocus in one go
107
7.2 Well-posedness of the diffusion model
109
7.3 Estimating Radiance, Depth, and Motion
110
7.3.1 Cost Functional Minimization
111
7.4 Examples
113
7.4.1 Synthetic Data
114
7.4.2 Real Images
117
7.5 Summary
118
8 Dealing with multiple moving objects
120
8.1 Handling multiple moving objects
121
8.2 A closer look at camera exposure
124
8.3 Relative motion blur
125
8.3.1 Minimization algorithm
126
8.4 Dealing with changes in motion
127
8.4.1 Matching motion blur along different directions
129
8.4.2 A look back at the original problem
131
8.4.3 Minimization algorithm
132
8.5 Image restoration
135
8.5.1 Minimization algorithm
137
8.6 Examples
138
8.6.1 Synthetic data
138
8.6.2 Real data
141
8.7 Summary
146
9 Dealing with occlusions
147
9.1 Inferring shape and radiance of occluded surfaces
148
9.2 Detecting occlusions
150
9.3 Implementation of the algorithm
151
9.4 Examples
152
9.4.1 Examples on a synthetic scene
152
9.4.2 Examples on real images
154
9.5 Summary
157
10 Final remarks 159
A Concepts of radiometry 161
A.1 Radiance, irradiance, and the pinhole model
161
A.1.1 Foreshortening and solid angle
161
A.1.2 Radiance and irradiance
162
A.1.3 Bidirectional reflectance distribution function
163
A.1.4 Lambertian surfaces
163
A.1.5 Image intensity for a Lambertian surface and a pinhole lens model
164
A.2 Derivation of the imaging model for a thin lens
164
B Basic primer on functional optimization 168
B.1 Basics of the calculus of variations
169
B.1.1 Functional derivative
170
B.1.2 Euler–Lagrange equations
171
B.2 Detailed computation of the gradients
172
B.2.1 Computation of the gradients in
Chapter 6
172
B.2.2 Computation of the gradients in
Chapter 7
174
B.2.3 Computation of the gradients in
Chapter 8
176
B.2.4 Computation of the gradients in
Chapter 9
185
C Proofs 190
C.1 Proof of Proposition 3.2
190
C.2 Proof of Proposition 3.5
191
C.3 Proof of Proposition 4.1
192
C.4 Proof of Proposition 5.1
194
C.5 Proof of Proposition 7.1
195
D Calibration of defocused images 197
D.1 Zooming and registration artifacts
197
D.2 Telecentric optics
200
E MATLAB® implementation of some algorithms 202
E.1 Least-squares solution (Chapter 4)
202
E.2 I-divergence solution (Chapter 5)
212
E.3 Shape from defocus via diffusion (Chapter 6)
221
E.4 Initialization: A fast approximate method
229
F Regularization 232
F.1 Inverse problems
232
F.2 Ill-posed problems
234
F.3 Regularization
235
F.3.1 Tikhonov regularization
237
F.3.2 Truncated SVD
238
References 239
Index 247