Favorskaya / Jain Computer Vision in Control Systems-3

Aerial and Satellite Image Processing
1. Auflage 2018
ISBN: 978-3-319-67516-9
Verlag: Springer Nature Switzerland
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 135, 343 Seiten

Reihe: Intelligent Systems Reference Library

The research book is a continuation of the authors’ previous works, which are focused on recent advances in computer vision methodologies and technical solutions using conventional and intelligent paradigms.

The book gathers selected contributions addressing aerial and satellite image processing and related fields. Topics covered include novel tensor and wave models, a new comparative morphology scheme, warping compensation in video stabilization, image deblurring based on physical processes of blur impacts, and a rapid and robust core structural verification algorithm for feature extraction in images and videos, among others. All chapters focus on practical implementations.

Given the tremendous interest among researchers in the development and applications of computer vision paradigms in the field of business, engineering, medicine, security and aviation, this book offers a timely guide.

Autoren/Hrsg.

Favorskaya, Margarita N.

Jain, Lakhmi C.

Inhaltsverzeichnis

1;Preface;6
2;Contents;7
3;About the Editors;12
4;1 Theoretical and Practical Solutions in Remote Sensing;14
4.1;Abstract;14
4.2;1.1 Introduction;14
4.3;1.2 Chapters Included in the Book;15
4.4;1.3 Conclusions;20
4.5;References;20
5;2 Multidimensional Image Models and Processing;23
5.1;Abstract;23
5.2;2.1 Introduction;24
5.3;2.2 Mathematical Models of Images;26
5.3.1;2.2.1 Random Fields;26
5.3.2;2.2.2 Tensor Models of Random Fields;27
5.3.3;2.2.3 Autoregressive Models of Random Fields;30
5.3.4;2.2.4 Wave Models of Random Fields;37
5.3.5;2.2.5 Random Fields on Surfaces;40
5.4;2.3 Image Filtering;44
5.4.1;2.3.1 Efficiency of Optimal Image Filtering;45
5.4.2;2.3.2 Tensor Kalman Filter;47
5.5;2.4 Anomalies Detection in Noisy Background;49
5.5.1;2.4.1 Optimal Algorithms for Signal Detection;50
5.5.2;2.4.2 Efficiency of Anomaly Detection;54
5.6;2.5 Image Alignment;57
5.6.1;2.5.1 Tensor Shift Filtering;57
5.6.2;2.5.2 Random Field Alignment of Images with Interframe Geometric Transformation;59
5.6.3;2.5.3 Alignment of Two Frames of Gaussian Random Field;60
5.6.4;2.5.4 Method of Fixed Point at Frame Alignment;63
5.7;2.6 Adaptive Algorithms of Image Processing;67
5.7.1;2.6.1 Pseudo-Gradient Adaptive Algorithms;68
5.7.2;2.6.2 Pseudo-Gradient Adaptive Prediction Algorithms;71
5.7.3;2.6.3 Pseudo-Gradient Algorithms of Image Alignment;73
5.8;2.7 Conclusions;74
5.9;Acknowledgements;75
5.10;References;75
6;3 Vision-Based Change Detection Using Comparative Morphology;77
6.1;Abstract;77
6.2;3.1 Introduction;78
6.3;3.2 Related Works;79
6.4;3.3 Methodology;81
6.4.1;3.3.1 Comparative Morphology as a Generalized Scheme of Morphological Image Analysis;82
6.4.2;3.3.2 Comparative Filtering as a Generalization of Morphological Filtering;84
6.4.3;3.3.3 Comparative Filters Based on Guided Contrasting;86
6.4.4;3.3.4 Manifold Learning, Diffusion Maps and Shape Matching;88
6.4.5;3.3.5 Generalized Diffusion Morphology and Comparative Filters Based on Diffusion Operators;91
6.4.6;3.3.6 Image and Shape Matching Based on Diffusion Morphology;94
6.4.7;3.3.7 Change Detection Pipeline Based on Comparative Filtering;96
6.5;3.4 Experiments;98
6.5.1;3.4.1 Qualitative Change Detection Experiments;98
6.5.2;3.4.2 Quantitative Change Detection Experiments;99
6.6;3.5 Conclusions;103
6.7;Acknowledgements;103
6.8;References;104
7;4 Methods of Filtering and Texture Segmentation of Multicomponent Images;109
7.1;Abstract;109
7.2;4.1 Introduction;110
7.3;4.2 Method for Nonlinear Multidimensional Filtering of Images;111
7.3.1;4.2.1 Mathematical Model of Multispectral Images;112
7.3.2;4.2.2 Nonlinear Multidimensional Filtering;114
7.4;4.3 Method of Texture Segmentation;122
7.5;4.4 Conclusions;128
7.6;References;129
8;5 Extraction and Selection of Objects in Digital Images by the Use of Straight Edges Segments;131
8.1;Abstract;131
8.2;5.1 Introduction;132
8.3;5.2 Related Works;133
8.4;5.3 Problem Statement and Method of Solution;136
8.4.1;5.3.1 Problem Statement and Tasks;136
8.4.2;5.3.2 Image Processing Structure;136
8.4.3;5.3.3 Advanced Algorithm of Straight Edge Segments Extraction;138
8.4.4;5.3.4 Lines Grouping Algorithms for Object Description and Selection;141
8.5;5.4 Modelling of Straight Edge Segments Extraction;143
8.6;5.5 Modelling of Segment Grouping and Object Detection, Selection and Localization;146
8.7;5.6 Experimental Results for Aerial, Satellite and Radar Images;149
8.8;5.7 Conclusions;155
8.9;Acknowledgements;157
8.10;References;157
9;6 Automated Decision Making in Road Traffic Monitoring by On-board Unmanned Aerial Vehicle System;160
9.1;Abstract;160
9.2;6.1 Introduction;161
9.3;6.2 Algorithm for Classification of Road Traffic Situation;163
9.4;6.3 Alphabet Forming for Description of Situation Class;164
9.5;6.4 Detection of Scene Objects;166
9.6;6.5 Forming Observed Scene Descriptions;170
9.7;6.6 Decision Making Procedure;174
9.8;6.7 Use of Statistical Criteria for Decision Making;175
9.9;6.8 Use of Functional Criteria Model;178
9.10;6.9 Examples;181
9.11;6.10 Conclusions;184
9.12;References;184
10;7 Warping Techniques in Video Stabilization;187
10.1;Abstract;187
10.2;7.1 Introduction;187
10.3;7.2 Development of Warping Techniques;189
10.4;7.3 Related Works;191
10.4.1;7.3.1 Overview of Warping Techniques in 2D Stabilization;191
10.4.2;7.3.2 Overview of Warping Techniques in 3D Stabilization;193
10.4.3;7.3.3 Overview of Inpainting Methods for Boundary Completion;197
10.5;7.4 Scene Classification;199
10.5.1;7.4.1 Extraction of Key Frames;199
10.5.2;7.4.2 Estimation of Scene Depth;201
10.6;7.5 3D Warping During Stabilization;202
10.6.1;7.5.1 Extraction of Structure from Motion;203
10.6.2;7.5.2 3D Camera Trajectory Building;205
10.6.3;7.5.3 Warping in Scenes with Small Depth;206
10.6.4;7.5.4 Warping Using Geometrical Primitives;207
10.6.5;7.5.5 Local 3D Warping in Scenes with Large Depth;210
10.7;7.6 Warping During Video Inpainting;213
10.8;7.7 Experimental Results;218
10.9;7.8 Conclusions;221
10.10;Acknowledgements;222
10.11;References;222
11;8 Image Deblurring Based on Physical Processes of Blur Impacts;226
11.1;Abstract;226
11.2;8.1 Introduction;227
11.3;8.2 Overview of Blur and Deblurring Methods;228
11.4;8.3 Model of Linear Blur Formation;237
11.4.1;8.3.1 Discrete-Analog Representation of Illumination;237
11.4.2;8.3.2 Small Linear Blur;239
11.4.3;8.3.3 Large Linear Blur;246
11.5;8.4 Non-linear Blur;250
11.6;8.5 Conclusions;257
11.7;References;257
12;9 Core Algorithm for Structural Verification of Keypoint Matches;260
12.1;Abstract;260
12.2;9.1 Introduction;261
12.3;9.2 Overview of Keypoint-Based Methods;262
12.4;9.3 Notation;264
12.5;9.4 Training Datasets;268
12.6;9.5 Algorithms of Primary Outlier Elimination;269
12.6.1;9.5.1 Nearest Neighbour Ratio Test;269
12.6.2;9.5.2 Crosscheck;270
12.6.3;9.5.3 Exclusion of Ambiguous Matches;270
12.6.4;9.5.4 Comparison and Conclusion;272
12.7;9.6 Geometrical Verification of Matches;273
12.7.1;9.6.1 Hough Clustering of Keypoint Matches;273
12.7.2;9.6.2 Verification of Cluster Hypotheses;278
12.8;9.7 Confidence Estimation;282
12.9;9.8 Application for Practical Tasks;284
12.9.1;9.8.1 Matching of Images of 3D Scenes;285
12.9.2;9.8.2 Image Retrieval Using Bag of Words;286
12.9.3;9.8.3 Registration of Aerospace Images;289
12.10;9.9 Conclusions;292
12.11;Acknowledgements;292
12.12;References;292
13;10 Strip-Invariants of Double-Sided Matrix Transformation of Images;296
13.1;Abstract;296
13.2;10.1 Introduction;297
13.3;10.2 Double-Sided Matrix Transformation of Images;298
13.4;10.3 Invariant Images (Problem Statement);301
13.5;10.4 Analysis of Strip-Invariant Images;307
13.5.1;10.4.1 Existence Criteria of Strip-Invariant Images for Case m = n, A = B;307
13.5.2;10.4.2 Renunciation of Matrices Equality Condition A = B;316
13.5.3;10.4.3 Abandonment of Conditions of Symmetry and Orthogonality of Matrices A and B;319
13.6;10.5 Getting Invariant Images Using Eigenvectors of Matrices;321
13.7;10.6 Synthesis of Matrices by Given Invariant Images;325
13.8;10.7 Conclusions;327
13.9;References;327
14;11 The Fibonacci Numeral System for Computer Vision;329
14.1;Abstract;329
14.2;11.1 Introduction;330
14.3;11.2 Fibonacci Numbers;333
14.4;11.3 Fibonacci Numbers and Fibonacci Codes;334
14.5;11.4 Minimal and Maximum Representation Forms for Fibonacci Numbers;336
14.5.1;11.4.1 Estimate of the Noise Immunity of the Fibonacci Codes in Their Minimal Form;337
14.5.2;11.4.2 Noise-Proof Fibonacci Counting;343
14.6;11.5 Decoding the Fibonacci Combinations in the Minimal Representation Form;346
14.7;11.6 Conclusions and Future Research;350
14.8;Acknowledgements;351
14.9;References;351