智能视感学

Foreword

Preface

Base article

Chapter 1 Introduction

1.1 Overview

1.1.1 Concept about the Visual Perception

1.1.2 The Development of Visual Perception Technology

1.1.3 Classification of Visual Perception System

1.2 A Visual Perception Hardware-base

1.2.1 iImage Se ing

1.2.2 Image Acquisition

1.2.3 PC Hardware Requirements for VPS

Exercises

Chapter 2 Foundatio of Image Processing

2.1 Basic Processing Methods for Gray Image

2.1.1 Spatial Domain Enhancement Algorithm

2.1.2 Frequency Domain Enhancement Algorithm

2.2 Edge Detection of Gray Image

2.2.1 Threshold Edge Detection

2.2.2 Gradient-based Edge Detection

2.Z.3 Laplacian Operator

2.2.4 Canny Edge Operator

2.2.5 Mathematical Morphological Method

2.2.6 Brief Description of Other Algorithms

2.3 Binarization Processing and Segmentation of Image

2.3.1 General Description

2.3.2 Histogram-based Valley-point Threshold Image Binarization

2.3.3 OTSU Algorithm

2.3.4 Minimum Error Method of Image Segmentation

2.4 Color Image Enhancement

2.4.1 Color Space and Its Tra formation

2.4.2 Histogram Equalization of Color Levels in Color Image

2.5 Color Image Edge Detection

2.5.1 Color Image Edge Detection Based on Gradient Extreme Value

2.5.2 Practical Method for Color Image Edge Detection

Exercises

Chapter 3 Mathematical Model of the Camera

3.1 Geometric Tra formatio of Image Space

3.1.1 Homogeneous Coordinates

3.1.2 Orthogonal Tra formation and Rigid Body Tra formation

3.1.3 Similarity Tra formation and Affine Tra formation

3.1.4 Pe pective Tra formation

3.2 Image Coordinate System and Its Tra formation

3.2.1 Image Coordinate System

3.2.2 Image Coordinate Tra formation

3.3 Common Method of Calibration Camera Paramete

3.3.1 Step Calibration Method

3.3.2 Calibration Algorithm Based on More than One Free Plane

3.3.3 Non-linear Distortion Parameter Calibration Method

Exercises

Chapter 4 Visual Perception Identification Algorithms

4.1 Image Feature Extraction and Identification Algorithm

4.1.1 Decision Theory Approach

4.1.2 Statistical Classification Method

4.1.3 Feature Classification Discretion Similarity about the Image Recognition Process

4.2 Principal Component Analysis

4.2.1 Principal Component Analysis Principle

4.2.2 Kernel Principal Component Analysis

4.2.3 PCA-based Image Recognition

4.3 Support Vector Machines

4.3.1 Main Contents of Statistical Learning Theory

4.3.2 Classification-Support Vector Machine ~

4.3.3 Solution to the Nonlinear Regression Problem

4.3.4 Algorithm of Support Vector Machine

4.3.5 Image Characteristics Identification Based on SVM

4.4 Moment Invariants and Normalized Moments of Inertia

4.4.1 Moment Theory

4.4.2 Normalized Moment of Inertia

4.5 Template Matching and Similarity

4.5.1 Spatial Domain Description of Template Matching

4.5.2 Frequency Domain Description of Template Matching

4.6 Object Recognition Based on Color Feature

4.6.1 Image Colorimetric Processing

4.6.2 Co truction of Color-Pool

4.6.3 Object Recognition Based on Color

4.7 Image Fuzzy Recognition Method

4.7.1 Fuzzy Content Feature and Fuzzy Similarity Degree

4.7.2 Extraction of Fuzzy Structure

4.7.3 Fuzzy Synthesis Decision-making of Image Matching

Exercises

Chapter 5 Detection Principle of Visual Perception

5.1 Single View Geometry and Detection Principle of Monocular Visual Perception

5.1.1 Single Vision Coordinate System

5.1.2 Basic Algorithm for Single Vision Detection

5.1.3 Engineering Technology Based on Single View Geometry

5.2 Detection Principle of Binocular Visual Perception

5.2.1 Two-view Geometry and Detection of Binocular Perception

5.2.2 Epipolar Geometry Principle

5.2.3 Determination Method of Spatial Coordinates

5.2.4 Camera Calibration in Binocular Visual Perception System

5.3 Theoretical Basis for Multiple Visual Perception Detection

5.3.1 Te or Geometry Principle

5.3.2 Geometric Properties of Three Visual Te or

5.3.3 Operation of Three-visual Te or

5.3.4 Co traint Matching Feature Points of Three-visual Te or

5.3.5 Three-visual Te or Restrict the Three Visual Restraint Feature Line' s Matching

Exercises

Application article

Chapter 6 Practical Technology of Intelligent Visual Perception

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

6.1.1 The Basic Composition of The System

6.1.2 System Algorithm

6.2 Intelligent Identification System for Billet Number

6.2.1 System Control Program

6.2.2 Recognition Algorithm

6.3 Verification of Banknotes-Sorting Based on Image Information

6.3.1 Preprocessing of the Banknotes Image

6.3.2 Distinction Between Old and New Banknotes

6.3.3 Distinction of the Denomination and Direction of the Banknotes

6.3.4 Banknotes Fineness Detection

6.4 Intelligent Collision Avoidance Technology of Vehicle

6.4.1 Basic Hardware Configuration

6.4.2 Road Obstacle Recognition Algorithm

6.4.3 Smart Algorithm of Anti-collision to Pedestria

6.5 Intelligent Visual Perception Control of Traffic Lights

6.5.1 Overview

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

Exercises

Appendix

Least Square and Common Algorithms in Visual Perception Detection

I.1 Basic Idea of the Algorithm

I.2 Common Least Square Algorithms in Visual Perception Detection

I.2.1 Least Square of Linear System of Equatio

I.2.2 Least Square Solution of Nonlinear Homogeneous System of Equatio Theory and Method of BAYES Decision

II.1 Introduction

II.2 BAYES Classification Decision Mode

II.2.1 BAYES Classification of Minimum Error Rate

II.2.2 BAYES Classification Decision of Minimum Risk

III Statistical Learning and VC-dime ion Theorem

III.1 Bounding Theory and VC-dime ion Principle

III.2 Generalized Capability Bounding

III.3 Structural Risk Minimization Principle of Induction

IV Optimality Conditio on Co trained Nonlinear Programming Problem

IV.1 Kuhn-Tucker Condition

IV.1.1 Gordon Lemma

IV.1.2 Fritz John Theorem

IV.1.3 Proof of the Kuhn-Tucker Condition

IV.2 Karush-Kuhn-Tucker Condition

Subject Index

References

《智能视感学（英文版）》从计算机视感及其信号处理的基本概念与基础理论出发，阐述了基于图像信息的识别、理解与检测技术原理与方法。《智能视感学（英文版）》根据作者多年来从事智能视感理论与技术研究的成果，结合研究性本科与研究生教学特点编撰而成。全书分为基础篇与应用篇两大部分，其中，基础篇系统地介绍了智能视感的基本原理、方法、关键技术及其算法；应用篇则由配合主要基础理论和方法的应用技术实例所组成。全书遵循理论知识与实用技术的紧密结合、数学方法与实用效果的相互映证等编写原则。《智能视感学（英文版）》涉及的教学内容主要包括：图像处理基础、摄像机数学模型、视感识别与检测原理、智能视感实用技术等。《智能视感学（英文版）》可以作为检测与控制、自动化、计算机、机器人及人工智能等专业的高年级本科生和研究生的教材，也可作为专业技术人员的参考工具书。