Atjaunināt sīkdatņu piekrišanu

E-grāmata: Selection of Image Understanding Techniques: From Fundamentals to Research Front [Taylor & Francis e-book]

  • Formāts: 330 pages, 43 Tables, black and white; 133 Line drawings, black and white; 31 Halftones, black and white; 164 Illustrations, black and white
  • Izdošanas datums: 31-Jan-2023
  • Izdevniecība: CRC Press
  • ISBN-13: 9781003362388
Citas grāmatas par šo tēmu:
  • Taylor & Francis e-book
  • Cena: 177,87 €*
  • * this price gives unlimited concurrent access for unlimited time
  • Standarta cena: 254,10 €
  • Ietaupiet 30%
Selection of Image Understanding Techniques: From Fundamentals to Research FrontPalielināt
  • Formāts: 330 pages, 43 Tables, black and white; 133 Line drawings, black and white; 31 Halftones, black and white; 164 Illustrations, black and white
  • Izdošanas datums: 31-Jan-2023
  • Izdevniecība: CRC Press
  • ISBN-13: 9781003362388
Citas grāmatas par šo tēmu:
Taylor & Francis e-booksMore info about Taylor & Francis e-books
Rokasgrāmatas mājas lapa: https://www.taylorfrancis.com/books/9781003362388
"This book offers a comprehensive introduction to seven commonly used image understanding techniques in modern information technology. Readers of various levels can find suitable techniques to solve their practical problems and discover the latest development in these specific domains. The techniques covered include camera model and calibration, stereo vision, generalized matching, scene analysis and semantic interpretation, multi-sensor image information fusion, content-based visual information retrieval, and understanding spatial-temporal behavior. The book provides aspects from the essential concepts overview and basic principles to detailed introduction, explanation of the current methods and their practical techniques. It also presents discussions on the research trends and latest results in conjunction with new development of technical methods. This is an excellent read for those who do not have a subject background in image technology but need to use these techniques to complete specific tasks. These essential information will also be useful for their further study in the relevant fields"--

This book offers a comprehensive introduction to seven commonly used image understanding techniques in modern information technology. Readers of various levels can find suitable techniques to solve their practical problems and discover the latest development in these specific domains.

The techniques covered include camera model and calibration, stereo vision, generalized matching, scene analysis and semantic interpretation, multi-sensor image information fusion, content-based visual information retrieval, and understanding spatial-temporal behavior. The book provides aspects from the essential concepts overview and basic principles to detailed introduction, explanation of the current methods and their practical techniques. It also presents discussions on the research trends and latest results in conjunction with new development of technical methods.

This is an excellent read for those who do not have a subject background in image technology but need to use these techniques to complete specific tasks. These essential information will also be useful for their further study in the relevant fields.



This book offers a comprehensive introduction to seven commonly used image understanding techniques in modern information technology. Readers of various levels can find suitable techniques to solve their practical problems and discover the latest development in these specific domains.

Preface xvii
Chapter 1 Introduction
1(34)
1.1 Image Engineering And Its Development
2(7)
1.1.1 Basic Concepts and Overall Framework
2(2)
1.1.2 Review of the Development of Image Technology
4(1)
1.1.2.1 A Closed Survey Series of Image Technology
4(1)
1.1.2.2 Image Engineering Survey Series in Progress
4(5)
1.2 Image Understanding And Related Disciplines
9(6)
1.2.1 Image Understanding
9(1)
1.2.2 Computer Vision
10(1)
1.2.2.1 Research Methods
10(1)
1.2.2.2 Realization of Engineering Methods
11(1)
1.2.2.3 Research Objectives
11(1)
1.2.2.4 The Relationship between Image Understanding and Computer Vision
12(1)
1.2.3 Other Related Disciplines
13(1)
1.2.3.1 Artificial Intelligence
13(1)
1.2.3.2 Machine Learning and Deep Learning
13(1)
1.2.3.3 Machine Vision/Robot Vision
14(1)
1.2.3.4 Pattern Recognition
14(1)
1.2.3.5 Computer Graphics
14(1)
1.3 The Theoretical Framework Of Image Understanding
15(14)
1.3.1 Marr's Theory of Visual Computation
15(1)
1.3.1.1 Vision is a Complex Information Processing Process
15(1)
1.3.1.2 Three Key Elements of Visual Information Processing
16(2)
1.3.1.3 Three-Level Internal Representation of Visual Information
18(2)
1.3.1.4 Visual Information Understanding is Organized in the Form of Functional Modules
20(1)
1.3.1.5 The Formal Representation of Computational Theory Must Take Constraints into Account
21(1)
1.3.2 Improvements to Marrs Theoretical Framework
22(2)
1.3.3 Discussion on Marr's Reconstruction Theory
24(1)
1.3.3.1 Problems Related to Reconstruction Theory
24(1)
1.3.3.2 Representation Without Reconstruction
25(2)
1.3.4 Research on the New Theoretical Framework
27(1)
1.3.4.1 Knowledge-Based Theoretical Framework
27(1)
1.3.4.2 Active Vision Theory Framework
28(1)
1.4 Characteristics Of This Book
29(6)
1.4.1 Writing Motivation
29(2)
1.4.2 Material Selection and Contents
31(1)
1.4.3 Structure and Arrangement
32(1)
References
33(2)
Chapter 2 Camera Model and Calibration
35(42)
2.1 Linear Camera Model
36(11)
2.1.1 Imaging Transformation
36(1)
2.1.1.1 Various Coordinate Systems
36(1)
2.1.1.2 Imaging Model
36(1)
2.1.1.3 Perspective Transformation
37(1)
2.1.1.4 Telecentric Imaging and Supercentric Imaging
38(2)
2.1.1.5 Homogeneous Coordinates
40(1)
2.1.1.6 Inverse Perspective Transformation
41(1)
2.1.2 Approximate Projection Modes
42(1)
2.1.2.1 Orthogonal Projection
42(1)
2.1.2.2 Weak Perspective Projection
43(1)
2.1.2.3 Parallel Perspective Projection
44(1)
2.1.2.4 Comparison of Various Approximate Modes and Perspective Projection
45(1)
2.1.3 A General Camera Model
45(2)
2.2 Nonlinear Camera Model
47(5)
2.2.1 Type of Distortion
48(1)
2.2.1.1 Radial Distortion
48(1)
2.2.1.2 Tangential Distortion
49(1)
2.2.1.3 Eccentric Distortion
50(1)
2.2.7.4 Thin Prism Distortion
50(1)
2.2.2 A Complete Imaging Model
50(2)
2.3 Camera Calibration
52(5)
2.3.1 Basic Calibration Procedure
52(1)
2.3.2 Camera Internal and External Parameters
53(1)
2.3.2.1 External Parameters
54(1)
2.3.2.2 Internal Parameters
54(1)
2.3.2.3 Another Description of Internal and External Parameters
55(1)
2.3.3 Nonlinear Camera Calibration
56(1)
2.3.4 Classification of Calibration Methods
57(1)
2.4 Traditional Calibration Methods
57(6)
2.4.1 Basic Steps and Parameters
59(1)
2.4.2 Two-Stage Calibration Method
59(3)
2.4.3 Precision Improvement
62(1)
2.5 Self-Calibration Methods
63(3)
2.5.1 Basic Idea
63(1)
2.5.2 A Practical Method
64(2)
2.6 Some Recent Developments And Further Research
66(11)
2.6.1 Calibration of Structured Light Active Vision System
66(1)
2.6.1.1 Projector Model and Calibration
67(1)
2.6.1.2 Pattern Separation
68(1)
2.6.1.3 Calculation of Homography Matrix
69(2)
2.6.1.4 Calculation of Calibration Parameters
71(2)
2.6.2 Online Camera External Parameter Calibration
73(1)
2.6.2.1 Lane Line Detection and Data Screening
74(1)
2.6.2.2 Optimizing Reprojection Error
75(1)
References
76(1)
Chapter 3 Stereo Vision
77(40)
3.1 Depth Imaging And Depth Image
78(3)
3.1.1 Depth Image and Grayscale Image
78(1)
3.1.2 Intrinsic Image and Non-Intrinsic Image
79(1)
3.1.3 Depth Imaging Modes
79(2)
3.2 Binocular Imaging Modes
81(7)
3.2.1 Binocular Horizontal Mode
81(1)
3.2.1.1 Parallax and Depth
81(2)
3.2.1.2 Angular Scanning Imaging
83(1)
3.2.2 Binocular Convergence Horizontal Mode
84(1)
3.2.2.1 Parallax and Depth
84(1)
3.2.2.2 Image Rectification
85(2)
3.2.3 Binocular Axial Mode
87(1)
3.3 Binocular Stereo Matching Based On Region
88(10)
3.3.1 Template Matching
88(1)
3.3.1.1 Basic Method
89(2)
3.3.1.2 Using Geometric Hashing
91(1)
3.3.2 Stereo Matching
92(1)
3.3.2.1 Epipolar Line Constraint
93(2)
3.3.2.2 Essential Matrix and Fundamental Matrix
95(2)
3.3.2.3 Calculation of Optical Properties
97(1)
3.4 Binocular Stereo Matching Based On Features
98(12)
3.4.1 Basic Steps
98(1)
3.4.1.1 Matching Using Edge Points
98(1)
3.4.1.2 Matching Using Zero-Crossing Points
99(1)
3.4.1.3 Feature Point Depth
100(1)
3.4.1.4 Sparse Matching Points
101(1)
3.4.2 Scale-Invariant Feature Transformation
101(3)
3.4.3 Speed-Up Robust Feature
104(1)
3.4.3.1 Determine the Point of Interest Based on the Hessian Matrix
104(1)
3.4.3.2 Scale Space Representation
105(2)
3.4.3.3 Description and Matching of Points of Interest
107(3)
3.5 Some Recent Developments And Further Research
110(7)
3.5.1 Biocular and Stereopsis
110(1)
3.5.1.1 Biocular and Binocular
110(1)
3.5.1.2 From Monocular to Binocular
111(1)
3.5.2 Stereo Matching Methods Based on Deep Learning
112(1)
3.5.2.1 Methods Using Image Pyramid Networks
112(1)
3.5.2.2 Methods Using Siamese Networks
113(1)
3.5.2.3 Methods Using Generative Adversarial Networks
113(1)
3.5.3 Matching Based on Feature Cascade CNN
114(1)
References
115(2)
Chapter 4 Generalized Matching
117(38)
4.1 Matching Overview
118(6)
4.1.1 Matching Strategies and Categories
118(2)
4.1.2 Matching and Registration
120(1)
4.1.2.1 Registration Technology
120(1)
4.1.2.2 Inertia-Equivalent Ellipse Matching
121(2)
4.1.3 Matching Evaluation
123(1)
4.2 Object Matching
124(6)
4.2.1 Matching Metrics
124(1)
4.2.1.1 Hausdorff Distance
125(1)
4.2.1.2 Structural Matching Metrics
126(1)
4.2.2 Corresponding Point Matching
127(2)
4.2.3 String Matching
129(1)
4.2.4 Shape Matrix Matching
129(1)
4.3 Dynamic Pattern Matching
130(4)
4.3.1 Matching Process
131(1)
4.3.2 Absolute Pattern and Relative Pattern
131(3)
4.4 Relationship Matching
134(5)
4.4.1 Objects and Relational Representations
135(2)
4.4.2 Connection Relationship Matching
137(1)
4.4.3 Matching Process
138(1)
4.5 Graph Isomorphism Matching
139(6)
4.5.1 Introduction to Graph Theory
139(1)
4.5.1.1 Basic Definitions
139(1)
4.5.1.2 Geometric Representation of Graphs
140(1)
4.5.1.3 Subgraphs
141(1)
4.5.2 Graph Isomorphism and Matching
142(1)
4.5.2.1 Identity and Isomorphism of Graphs
142(1)
4.5.2.2 Judgment for Isomorphism
143(2)
4.6 Some Recent Developments And Further Research
145(10)
4.6.1 Image Registration and Matching
145(1)
4.6.1.1 Heterogeneous Remote Sensing Image Registration Based on Feature Matching
145(1)
4.6.1.2 Image Matching Based on Spatial Relation Reasoning
146(2)
4.6.2 Multimodal Image Matching
148(1)
4.6.2.1 Region-Based Techniques
148(1)
4.6.2.2 Feature-Based Techniques
149(2)
References
151(4)
Chapter 5 Scene Analysis and Semantic Interpretation
155(40)
5.1 Overview Of Scene Understanding
155(3)
5.1.1 Scenario Analysis
156(1)
5.1.2 Scene Awareness Hierarchy
156(2)
5.1.3 Scene Semantic Interpretation
158(1)
5.2 Fuzzy Inference
158(5)
5.2.1 Fuzzy Sets and Fuzzy Operations
159(1)
5.2.2 Fuzzy Inference Methods
160(1)
5.2.2.7 Basic Model
160(1)
5.2.2.2 Fuzzy Combination
161(2)
5.2.2.3 Defuzzification
163(1)
5.3 Predicate Logical System
163(8)
5.3.1 Predicate Calculus Rules
164(2)
5.3.2 Inference by Theorem Proving
166(5)
5.4 SCENE OBJECT LABELING
171(3)
5.4.1 Labeling Methods and Key Elements
171(1)
5.4.2 Discrete Relaxation Labeling
172(1)
5.4.3 Probabilistic Relaxation Labels
173(1)
5.5 Scene Classification
174(11)
5.5.1 Bag of Words/Bag-of-Features Models
175(2)
5.5.2 pLSA Model
177(1)
5.5.2.1 Model Description
178(1)
5.5.2.2 Model Calculation
179(1)
5.5.2.3 Model Application Example
180(2)
5.5.3 LDA Model
182(1)
5.5.3.7 Basic LDA Model
182(2)
5.5.3.2 SLDA Model
184(1)
5.6 Some Recent Developments And Further Research
185(10)
5.6.1 Interpretation of Remote Sensing Images
185(1)
5.6.1.1 Classification of Remote Sensing Image Interpretation Methods
185(2)
5.6.1.2 Knowledge Graph for Remote Sensing Image Interpretation
187(1)
5.6.2 Hybrid Enhanced Visual Cognition
188(1)
5.6.2.1 From Computer Vision Perception to Computer Vision Cognition
189(1)
5.6.2.2 Hybrid Enhanced Visual Cognition Related Technologies
190(2)
References
192(3)
Chapter 6 Multi-Sensor Image Information Fusion
195(48)
6.1 Overview Of Information Fusion
195(4)
6.1.1 Multi-Sensor Information Fusion
196(1)
6.1.2 Information Fusion Level
197(1)
6.1.3 Active Vision and Active Fusion
198(1)
6.2 Image Fusion
199(8)
6.2.1 Main Steps of Image Fusion
199(1)
6.2.1.1 Image Preprocessing
199(1)
6.2.1.2 Image Registration
199(1)
6.2.1.3 Image Information Fusion
200(1)
6.2.2 Three Levels of Image Fusion
201(2)
6.2.3 Evaluation of Image Fusion Effect
203(1)
6.2.3.1 Subjective Evaluation
203(1)
6.2.3.2 Objective Evaluation Based on Statistical Characteristics
204(1)
6.2.3.3 Objective Evaluation Based on the Amount of Information
205(2)
6.2.3.4 Evaluation According to the Purpose of Fusion
207(1)
6.3 Pixel-Level Fusion Methods
207(15)
6.3.1 Basic Fusion Methods
207(1)
6.3.1.1 Weighted Average Fusion Method
208(1)
6.3.1.2 Pyramid Fusion Method
208(1)
6.3.1.3 Wavelet Transform Fusion Method
209(1)
6.3.1.4 HSI Transform Fusion Method
209(1)
6.3.1.5 PCA Transform Fusion Method
210(1)
6.3.2 Combining Various Fusion Methods
210(1)
6.3.2.1 Problems with a Single-Type Fusion Method
210(1)
6.3.2.2 Fusion by Combining HSI Transform and Wavelet Transform
211(1)
6.3.2.3 Fusion by Combining PCA Transform and Wavelet Transform
212(1)
6.3.2.4 Performance of Combined Fusions
213(1)
6.3.3 The Optimal Number of Decomposition Layers for Wavelet Fusion
214(2)
6.3.4 Image Fusion Based on Compressed Sensing
216(2)
6.3.5 Examples of Pixel-Level Fusion
218(1)
6.3.5.1 Fusion of Different Exposure Images
218(1)
6.3.5.2 Fusion of Different Focus Images
218(1)
6.3.5.3 Fusion of Remote Sensing Images
219(1)
6.3.5.4 Fusion of Visible Light Image and Infrared Image
219(1)
6.3.5.5 Fusion of Visible Light Image and Millimeter-Wave Radar Image
220(1)
6.3.5.6 Fusion of CT Image and PET Image
220(1)
6.3.5.7 Fusion of Dual-Energy Transmission Image and Compton Backscatter Image
221(1)
6.4 Feature-Level And Decision-Level Fusion Methods
222(4)
6.4.1 Bayesian Method
222(2)
6.4.2 Evidential Reasoning Method
224(2)
6.5 Rough Set Theory In Decision-Level Fusion
226(4)
6.5.1 Rough Set Definition
227(1)
6.5.2 Rough Set Description
228(2)
6.5.3 Fusion Based on Rough Sets
230(1)
6.6 Some Recent Developments And Further Research
230(13)
6.6.1 Spatial-Spectral Feature Extraction of Hyperspectral Images
230(1)
6.6.1.1 Traditional Spatial-Spectral Feature Extraction Methods
231(1)
6.6.1.2 Deep Learning-Based Methods of Extracting Spatial-Spectral Features
232(1)
6.6.2 Multi-Source Remote Sensing Image Fusion
233(1)
6.6.2.1 Nine Multi-Source Remote Sensing Data Sources
233(3)
6.6.2.2 Multi-Source Remote Sensing Image Fusion Literatures
236(1)
6.6.2.3 Spatial-Spectral Fusion of Remote Sensing Images
237(1)
6.6.2.4 Fusion with Deep Recurrent Residual Networks
237(3)
References
240(3)
Chapter 7 Content-Based Visual Information Retrieval
243(40)
7.1 Principles Of Image And Video Retrieval
243(5)
7.1.1 Content-Based Retrieval
244(1)
7.1.2 Achieving and Retrieval Flowchart
244(2)
7.1.3 Multi-Level Content Representation
246(2)
7.2 Matching And Retrieval Of Visual Features
248(8)
7.2.1 Color Feature Matching
248(1)
7.2.1.1 Histogram Intersection Method
249(1)
7.2.1.2 Distance Method
249(1)
7.2.1.3 Central Moment Method
249(1)
7.2.1.4 Reference Color Table Method
249(1)
7.2.2 Texture Feature Calculation
250(2)
7.2.3 Multi-Scale Shape Features
252(1)
7.2.4 Retrieval with Composite Features
253(1)
7.2.4.1 Combination of Color and Texture Features
254(2)
7.2.4.2 Combining Color, SIFT and CNN Features
256(1)
7.3 Video Retrieval Based On Motion Features
256(3)
7.3.1 Global Motion Features
257(1)
7.3.2 Local Motion Features
258(1)
7.4 Video Program Retrieval
259(9)
7.4.1 News Video Structuring
260(1)
7.4.1.1 Features of News Video
260(1)
7.4.1.2 Main Speaker Close-up Shot Detection
260(2)
7.4.1.3 Clustering of Main Speaker Close-up Shots
262(1)
7.4.1.4 Announcer Shot Extraction
263(1)
7.4.2 Video Ranking of Sports Games
264(1)
7.4.2.1 Features of Sports Video
264(1)
7.4.2.2 Structure of Table Tennis Competition Program
265(1)
7.4.2.3 Object Detection and Tracking
266(1)
7.4.2.4 Make the Brilliance Ranking
267(1)
7.5 Semantic Classification Retrieval
268(5)
7.5.1 Image Classification Based on Visual Keywords
269(1)
7.5.7.2 Feature Selection
269(1)
7.5.1.2 Image Classification
270(1)
7.5.2 High-Level Semantics and Atmosphere
270(1)
7.5.2.1 Five Atmospheric Semantics
271(1)
7.5.2.2 Classification of Atmosphere
272(1)
7.6 Some Recent Developments And Further Research
273(10)
7.6.1 Deep Learning Based Cross-Modal Retrieval
273(3)
7.6.2 Hashing in Image Retrieval
276(1)
7.6.2.1 Supervised Hashing
276(1)
7.6.2.2 Asymmetric Supervised Deep Discrete Hashing
277(1)
7.6.2.3 Hashing in Cross-Modal Image Retrieval
277(3)
References
280(3)
Chapter 8 Understanding Spatial-Temporal Behavior
283(42)
8.1 Spatial-Temporal Technology
284(1)
8.2 Spatial-Temporal Points Of Interest
285(4)
8.2.1 Detection of Spatial Points of Interest
286(1)
8.2.2 Detection of Spatial-Temporal Points of Interest
287(2)
8.3 Dynamic Trajectory Learning And Analysis
289(4)
8.3.1 Overall Process
289(1)
8.3.2 Automatic Scene Modeling
289(1)
8.3.2.1 Object Tracking
290(1)
8.3.2.2 Interest Point Detection
290(1)
8.3.2.3 Activity Path Learning
291(1)
8.3.3 Automated Activity Analysis
291(2)
8.4 Action Classification And Recognition
293(6)
8.4.1 Action Classification
294(1)
8.4.1.1 Direct Classification
294(1)
8.4.1.2 Time-State Model
294(1)
8.4.1.3 Action Detection
294(2)
8.4.2 Action Recognition
296(1)
8.4.2.1 Holistic Recognition
296(1)
8.4.2.2 Pose Modeling
296(1)
8.4.2.3 Active Reconstruction
297(1)
8.4.2.4 Interactive Activities
297(1)
8.4.2.5 Group Activities
298(1)
8.4.2.6 Scene Interpretation
298(1)
8.5 Activity And Behavior Modeling
299(11)
8.5.1 Action Modeling
300(1)
8.5.1.1 Non-Parametric Modeling Methods
300(1)
8.5.1.2 3-D Modeling Methods
301(2)
8.5.1.3 Parametric Time-Series Modeling Methods
303(2)
8.5.2 Activity Modeling and Recognition
305(1)
8.5.2.1 Graph Model
305(2)
8.5.2.2 Synthesis Methods
307(2)
8.5.2.3 Knowledge- and Logic-Based Methods
309(1)
8.6 Joint Modeling Of Actor And Action
310(6)
8.6.1 Single-Label Actor-Action Recognition
311(1)
8.6.2 Multi-Label Actor-Action Recognition
312(1)
8.6.3 Actor-Action Semantic Segmentation
313(3)
8.7 Some Recent Developments And Further Research
316(9)
8.7.1 Behavior Recognition Using Joints
316(1)
8.7.1.1 Using CNN as Backbone
317(1)
8.7.1.2 Using RNN as Backbone
317(1)
8.7.1.3 Using GCN as Backbone
318(1)
8.7.1.4 Using Hybrid Network as Backbone
318(1)
8.7.2 Detection of Video Anomalous Events
318(1)
8.7.2.1 Detection with Convolutional Auto-Encoder Block Learning
319(2)
8.7.2.2 Detection Using One-Class Neural Network
321(1)
References
322(3)
Index 325
Yu-Jin Zhang is a tenured professor of image engineering at Tsinghua University, Beijing, China. He earned his PhD in Applied Science from the State University of Ličge, Ličge, Belgium. He was a post-doc fellow of Delft University of Technology, Delft, the Netherlands. He is also a CSIG and SPIE fellow. Dr. Zhang has published 50 books and more than 500 research papers.
Permanent link: https://www.kriso.lv/db/9781003362388_pe.html
Keywords: