Readings in Computer Vision (eBook)

Front Cover 1
Readings in Computer Vision: Issues, Problems, Principles, and Paradigms 4
Copyright Page 5
Table of Contents 6
Acknowledgments 12
Introduction 16
Acknowledgments 17
IMAGE ANALYSIS: PROBLEMS, PROGRESS AND PROSPECTS 18
1. INTRODUCTION 18
2. AN IMAGE ANALYSIS PARADIGM 18
3. FEATURE EXTRACTION 20
4. TEXTURE ANALYSIS 20
5. SURFACE ORIENTATION ESTIMATION 21
6. IMAGE MATCHING 22
7. RANGE ESTIMATION 22
8. SEGMENTATION 23
9. OBJECT REPRESENTATION 24
10. MODEL MATCHING 25
11. CONCLUDING REMARKS 25
REFERENCES 26
CHAPTER 1. RECOVERING SCENE GEOMETRY 28
A Stochastic Approach to Stereo Vision 36
Epipolar-Plane Image Analysis: A Technique for Analyzing Motion Sequences 41
Preface-The Changing Shape of Computer Vision 52
Understanding Image Intensities 60
A computer algorithm for reconstructing a scene from two projections 76
Practical real-time imaging stereo matcher 78
Detection of Binocular Disparities 88
Hierarchical Warp Stereo 95
Stereo Integral Equation 102
Recovering the Camera Parameters from a Transformation Matrix 108
One-Eyed Stereo: A General Approach to Modeling 3-D Scene Geometry 116
An Algebraic Approach to Shape-from-Image Problems 128
Analysis of Visual Motion by Biological and Computer Systems 147
An Image Flow Paradigm 160
CHAPTER 2. IMAGE PARTITIONING AND PERCEPTUAL ORGANIZATION 184
Extracting Straight Lines 195
A Computational Approach to Edge Detection 199
Linear Delineation 219
Perceptual Organization and Curve Partitioning 225
Digital Stereo Edges from Zero Crossing of Second Directional Derivatives 231
Parts of Recognition 242
Textons, The Fundamental Elements in Preattentive Vision and Perception of Textures 258
Mapping Image Properties into Shape Constraints: Skewed Symmetry, Aiffne-Transformable Patterns, and the Shape-from-Texture Paradigm 272
Analyzing Oriented Patterns 283
Capturing the Local Structure of Image Discontinuities in Two Dimensions 292
Segmentation and Aggregation: An Approach to Figure-Ground Phenomena 297
Color Constancy: A Method for Recovering Surface Spectral Reflectance 308
Visual Routines 313
Scale-Space Filtering 344
Early Orientation Selection: Tangent Fields and the Dimensionality of Their Support 348
CHAPTER 3. RECOGNITION AND LABELING OF SCENE OBJECTS 364
3DPO: A Three-Dimensional Part Orientation System 370
Model-Based Three-Dimensional Interpretations of Two-Dimensional Images 375
Special Purpose Automatic Programming for 3D Model-Based Vision 386
Model-Based Recognition and Localization from Sparse Range or Tactile Data 397
Rule-Based Interpretation of Aerial Imagery 430
CHAPTER 4. RELATIONAL DESCRIPTION 446
Visual Map Making for a Mobile Robot 453
A Heuristic Program to Solve Geometric-Analogy Problems 459
Problem-Solving with Diagrammatic Representations 471
The 3D MOSAIC Scene Understanding System: Incremental Reconstruction of 3D Scenes for Complex Images 486
Terrain Models for an Autonomous Land Vehicle 498
Experiments in Using a Theorem Prover to Prove and Develop Geometrical Theorems in Computer Vision 507
Knowledge Organization and Its Role in Representation and Interpretation for Time-Varying Data: The ALVEN System 513
CHAPTER 5. VISION SYSTEM ARCHITECTURES AND COMPUTATIONAL PARADIGMS 530
A Learning Algorithm for Boltzmann Machines 537
Parameter Nets 549
Image Processing by Simulated Annealing 566
Preface to S. Geman and D. Geman, "Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images" 577
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images 579
On the Foundations of Relaxation Labeling Processes 600
Optimization by Simulated Annealing 621
Visual Information Processing: Artificial Intelligence and the Sensorium of Sight 631
Computational Vision and Regularization Theory 653
CHAPTER 6. REPRESENTATIONS AND TRANSFORMATIONS 660
Geometry for Construction and Display 667
Global and Local Deformations of Solid Primitives 676
The Laplacian Pyramid as a Compact Image Code 686
Perceptual Organization and the Representation of Natural Form 695
Codon Constraints on Closed 2D Shapes 715
CHAPTER 7. MATCHING, MODEL FITTING, DEDUCTION, AND INFORMATION INTEGRATION 724
Generalizing the Hough Transform to Detect Arbitrary Shapes 729
Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography 741
Detection of Roads and Linear Structures in Low-Resolution Aerial Imagery Using a Multisource Knowledge Integration Technique 756
Representations Based on Zero-crossings in Scale-Space 768
Signal Matching Through Scale Space 774
APPENDIX A: KEY IDEAS, ASSUMPTIONS, AND OPEN ISSUES IN COMPUTER VISION 780
APPENDIX B: PARALLEL COMPUTER ARCHITECTURES FOR COMPUTER VISION 783
Glossary 788
Bibliography 795
Index 810