智能视感学 英文版【2025|PDF|Epub|mobi|kindle电子书版本百度云盘下载】

智能视感学 英文版PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

Base article1

Chapter1 Introduction1

1.1 Overview1

1.1.1 Concept about the Visual Perception1

1.1.2 The Development of Visual Perception Technology2

1.1.3 Classification of Visual Perception System4

1.2 A Visual Perception Hardware-base6

1.2.1 Image Sensing6

1.2.2 Image Acquisition22

1.2.3 PC Hardware Requirements for VPS27

Exercises31

Chapter2 Foundations of Image Processing32

2.1 Basic Processing Methods for Gray Image32

2.1.1 Spatial Domain Enhancement Algorithm32

2.1.2 Frequency Domain Enhancement Algorithm43

2.2 Edge Detection of Gray Image50

2.2.1 Threshold Edge Detection51

2.2.2 Gradient-based Edge Detection53

2.2.3 Laplacian Operator56

2.2.4 Canny Edge Operator58

2.2.5 Mathematical Morphological Method63

2.2.6 Brief Description of Other Algorithms66

2.3 Binarization Processing and Segmentation of Image67

2.3.1 General Description67

2.3.2 Histogram-based Valley-point Threshold Image Binarization68

2.3.3 OTSU Algorithm68

2.3.4 Minimum Error Method of Image Segmentation70

2.4 Color Image Enhancement71

2.4.1 Color Space and Its Transformation71

2.4.2 Histogram Equalization of Color Levels in Color Image74

2.5 Color Image Edge Detection76

2.5.1 Color Image Edge Detection Based on Gradient Extreme Value76

2.5.2 Practical Method for Color Image Edge Detection79

Exercises80

Chapter3 Mathematical Model of the Camera83

3.1 Geometric Transformations of Image Space83

3.1.1 Homogeneous Coordinates84

3.1.2 Orthogonal Transformation and Rigid Body Transformation84

3.1.3 Similarity Transformation and Affine Transformation85

3.1.4 Perspective Transformation86

3.2 Image Coordinate System and Its Transformation88

3.2.1 Image Coordinate System88

3.2.2 Image Coordinate Transformation90

3.3 Common Method of Calibration Camera Parameters94

3.3.1 Step Calibration Method95

3.3.2 Calibration Algorithm Based on More than One Free Plane97

3.3.3 Non-linear Distortion Parameter Calibration Method99

Exercises101

Chapter4 Visual Perception Identification Algorithms104

4.1 Image Feature Extraction and Identification Algorithm105

4.1.1 Decision Theory Approach105

4.1.2 Statistical Classification Method112

4.1.3 Feature Classification Discretion Similarity about the Image Recognition Process114

4.2 Principal Component Analysis116

4.2.1 Principal Component Analysis Principle116

4.2.2 Kernel Principal Component Analysis118

4.2.3 PCA-based Image Recognition122

4.3 Support Vector Machines125

4.3.1 Main Contents of Statistical Learning Theory126

4.3.2 Classification-Support Vector Machine130

4.3.3 Solution to the Nonlinear Regression Problem136

4.3.4 Algorithm of Support Vector Machine139

4.3.5 Image Characteristics Identification Based on SVM145

4.4 Moment Invariants and Normalized Moments of Inertia146

4.4.1 Moment Theory147

4.4.2 Normalized Moment of Inertia149

4.5 Template Matching and Similarity157

4.5.1 Spatial Domain Description of Template Matching157

4.5.2 Frequency Domain Description of Template Matching162

4.6 Object Recognition Based on Color Feature171

4.6.1 Image Colorimetric Processing171

4.6.2 Construction of Color-Pool173

4.6.3 Object Recognition Based on Color175

4.7 Image Fuzzy Recognition Method176

4.7.1 Fuzzy Content Feature and Fuzzy Similarity Degree176

4.7.2 Extraction of Fuzzy Structure178

4.7.3 Fuzzy Synthesis Decision-making of Image Matching183

Exercises188

Chapter5 Detection Principle of Visual Perception191

5.1 Single View Geometry and Detection Principle of Monocular Visual Perception191

5.1.1 Single Vision Coordinate System191

5.1.2 Basic Algorithm for Single Vision Detection192

5.1.3 Engineering Technology Based on Single View Geometry192

5.2 Detection Principle of Binocular Visual Perception195

5.2.1 Two-view Geometry and Detection of Binocular Perception196

5.2.2 Epipolar Geometry Principle200

5.2.3 Determination Method of Spatial Coordinates204

5.2.4 Camera Calibration in Binocular Visual Perception System207

5.3 Theoretical Basis for Multiple Visual Perception Detection217

5.3.1 Tensor Geometry Principle218

5.3.2 Geometric Properties of Three Visual Tensor221

5.3.3 Operation of Three-visual Tensor226

5.3.4 Constraint Matching Feature Points of Three-visual Tensor228

5.3.5 Three-visual Tensor Restrict the Three Visual Restraint Feature Line’s Matching231

Exercises236

Application article238

Chapter6 Practical Technology of Intelligent Visual Perception238

6.1 Automatic Monitoring System and Method of Load Limitation of The Bridge238

6.1.1 The Basic Composition of The System239

6.1.2 System Algorithm241

6.2 Intelligent Identification System for Billet Number244

6.2.1 System Control Program245

6.2.2 Recognition Algorithm245

6.3 Verification of Banknotes-Sorting Based on Image Information251

6.3.1 Preprocessing of the Banknotes Image252

6.3.2 Distinction Between Old and New Banknotes252

6.3.3 Distinction of the Denomination and Direction of the Banknotes253

6.3.4 Banknotes Fineness Detection255

6.4 Intelligent Collision Avoidance Technology of Vehicle258

6.4.1 Basic Hardware Configuration258

6.4.2 Road Obstacle Recognition Algorithm259

6.4.3 Smart Algorithm of Anti-collision to Pedestrians262

6.5 Intelligent Visual Perception Control of Traffic Lights267

6.5.1 Overview267

6.5.2 The Core Algorithm of Intelligent Visual Perception Control of Traffic Lights267

Exercises272

Appendix275

Ⅰ Least Square and Common Algorithms in Visual Perception Detection275

Ⅰ.1 Basic Idea of the Algorithm275

Ⅰ.2 Common Least Square Algorithms in Visual Perception Detection276

Ⅰ.2.1 Least Square of Linear System of Equations276

Ⅰ.2.2 Least Square Solution of Nonlinear Homogeneous System of Equations278

Ⅱ Theory and Method of BAYES Decision281

Ⅱ.1 Introduction281

Ⅱ.2 BAYES Classification Decision Mode281

Ⅱ.2.1 BAYES Classification of Minimum Error Rate281

Ⅱ.2.2 BAYES Classification Decision of Minimum Risk283

Ⅲ Statistical Learning and VC-dimension Theorem285

Ⅲ.1 Bounding Theory and VC-dimension Principle285

Ⅲ.2 Generalized Capability Bounding286

Ⅲ.3 Structural Risk Minimization Principle of Induction287

Ⅳ Optimality Conditions on Constrained Nonlinear Programming Problem288

Ⅳ.1 Kuhn-Tucker Condition288

Ⅳ.1.1 Gordon Lemma288

Ⅳ.1.2 Fritz John Theorem288

Ⅳ.1.3 Proof of the Kuhn-Tucker Condition289

Ⅳ.2 Karush-Kuhn-Tucker Condition291

Subject Index293

References300