Classification Methods for Remotely Sensed Data

Classification Methods for Remotely Sensed Data

The new edition of the bestselling Classification Methods for Remotely Sensed Data covers current state-of-the-art machine learning algorithms and developments in the analysis of remotely sensed data, and presents new AI-based analysis tools and metrics together with ongoing debates on accuracy asse...

Descripción completa

Detalles Bibliográficos
Otros Autores: Kavzoglu, Taskin, author (author), Tso, Brandt, author, Mather, Paul M., author
Formato: Libro electrónico
Idioma:Inglés
Publicado: Boca Raton, FL : CRC Press [2025]
Edición:Third edition
Materias:
Remote sensing.
Pattern recognition systems.
Ver en Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009869097406719
Tabla de Contenidos:
  • Cover
  • Half Title
  • Title Page
  • Copyright Page
  • Dedication
  • Table of Contents
  • Preface to the Third Edition
  • Preface to the Second Edition
  • Preface to the First Edition
  • Acknowledgments
  • Authors
  • Chapter 1 Fundamentals of Remote Sensing
  • 1.1 Introduction to Remote Sensing
  • 1.1.1 Atmospheric Interactions
  • 1.1.2 Reflectance Properties of Surface Materials
  • 1.1.3 Spatial, Spectral, and Radiometric Resolution
  • 1.1.4 Scale Issues in Remote Sensing
  • 1.2 Optical Remote Sensing Systems
  • 1.3 Atmospheric Correction
  • 1.3.1 Dark Object Subtraction
  • 1.3.2 Modeling Techniques
  • 1.3.2.1 Modeling the Atmospheric Effect
  • 1.3.2.2 Steps in Atmospheric Correction
  • 1.4 Correction for Topographic Effects
  • 1.5 Remote Sensing in the Microwave Region
  • 1.6 Radar Fundamentals
  • 1.6.1 SLAR Image Resolution
  • 1.6.2 Geometric Effects on Radar Images
  • 1.6.3 Factors Affecting Radar Backscatter
  • 1.6.3.1 Surface Roughness
  • 1.6.3.2 Surface Conductivity
  • 1.6.3.3 Parameters of the Radar Equation
  • 1.7 Imaging Radar Polarimetry
  • 1.7.1 Radar Polarization State
  • 1.7.2 Polarization Synthesis
  • 1.7.3 Polarization Signatures
  • 1.8 Radar Speckle Suppression
  • 1.8.1 Multilook Processing
  • 1.8.2 Filters for Speckle Suppression
  • References
  • Chapter 2 Pattern Recognition Principles
  • 2.1 A Terminological Introduction
  • 2.2 Taxonomy of Classification Techniques
  • 2.3 Fundamental Pattern Recognition Techniques
  • 2.3.1 Unsupervised Methods
  • 2.3.1.1 The k-Means Algorithm
  • 2.3.1.2 Fuzzy C-Means Clustering
  • 2.3.2 Supervised Methods
  • 2.3.2.1 Parallelepiped Method
  • 2.3.2.2 Minimum Distance Classifier
  • 2.3.2.3 Maximum Likelihood Classifier
  • 2.3.2.4 Fuzzy Maximum Likelihood Classifier
  • 2.4 Spectral Unmixing
  • 2.5 Ensemble Classifiers
  • 2.6 Incorporation of Ancillary Information.
  • 2.6.1 Use of Texture and Context
  • 2.6.2 Using Ancillary Multisource Data
  • 2.7 Epilogue
  • References
  • Chapter 3 Dimensionality Reduction: Feature Extraction and Selection
  • 3.1 Feature Extraction
  • 3.1.1 Principal Component Analysis
  • 3.1.2 Minimum/Maximum Autocorrelation Factors
  • 3.1.3 Maximum Noise Fraction (MNF) Transformation
  • 3.1.4 Independent Component Analysis
  • 3.1.5 Projection Pursuit
  • 3.2 Feature Selection
  • 3.2.1 Greedy Search Methods
  • 3.2.2 Simulated Annealing
  • 3.2.3 Separability Indices
  • 3.2.4 Filter-Based Methods
  • 3.2.4.1 Correlation-Based Feature Selection
  • 3.2.4.2 Information Gain
  • 3.2.4.3 Gini Impurity Index
  • 3.2.4.4 Minimum Redundancy-Maximum Relevance
  • 3.2.4.5 Chi-Square Test
  • 3.2.4.6 Relief-F
  • 3.2.4.7 Symmetric Uncertainty
  • 3.2.4.8 Fisher's Test
  • 3.2.4.9 OneR
  • 3.2.5 Wrappers
  • 3.2.5.1 Genetic Algorithm
  • 3.2.5.2 Particle Swarm Optimization
  • 3.2.5.3 Feature Selection with SVMs
  • 3.2.6 Embedded Methods
  • 3.2.6.1 K-Nearest Neighbor-Based Feature Selection
  • 3.2.6.2 Feature Selection with Ensemble Learners
  • 3.2.6.3 Hilbert-Schmidt Independence Criterion with Lasso
  • 3.3 Concluding Remarks
  • References
  • Chapter 4 Multisource Image Fusion and Classification
  • 4.1 Image Fusion
  • 4.1.1 Image Fusion Methods
  • 4.1.1.1 PCA-Based Image Fusion
  • 4.1.1.2 IHS-Based Image Fusion
  • 4.1.1.3 Brovey Transform
  • 4.1.1.4 Gram-Schmidt Transform
  • 4.1.1.5 Wavelet Transform
  • 4.1.1.6 Deep Learning for Image Fusion
  • 4.1.2 Assessment of Fused Image Quality
  • 4.1.3 Performance Evaluation of Fusion Methods
  • 4.2 Multisource Classification Using the Stacked-Vector Method
  • 4.3 The Extension of Bayesian Classification Theory
  • 4.3.1 An Overview
  • 4.3.1.1 Feature Extraction
  • 4.3.1.2 Probability or Evidence Generation
  • 4.3.1.3 Multisource Consensus.
  • 4.3.2 Bayesian Multisource Classification Mechanism
  • 4.3.3 A Refined Multisource Bayesian Model
  • 4.3.4 Multisource Classification Using the MRF
  • 4.3.5 Assumption of Inter-Source Independence
  • 4.4 Evidential Reasoning
  • 4.4.1 Concept Development
  • 4.4.2 Belief Function and Belief Interval
  • 4.4.3 Evidence Combination
  • 4.4.4 Decision Rules for Evidential Reasoning
  • 4.5 Dealing with Source Reliability
  • 4.5.1 Using Classification Accuracy
  • 4.5.2 Use of Class Separability
  • 4.5.3 Data Information Class Correspondence Matrix
  • 4.6 Concluding Remarks and Future Trends
  • References
  • Chapter 5 Support Vector Machines
  • 5.1 Linear Classification
  • 5.1.1 The Separable Case
  • 5.1.2 The Nonseparable Case
  • 5.2 Nonlinear Classification and Kernel Functions
  • 5.2.1 Nonlinear SVMs
  • 5.2.2 Kernel Functions
  • 5.3 Parameter Determination
  • 5.3.1 t-Fold Cross-Validations
  • 5.3.2 Bound on Leave-One-Out Error
  • 5.3.3 Grid Search
  • 5.3.4 Gradient Descent Method
  • 5.4 Multiclass Classification
  • 5.4.1 One-Against-One, One-Against-Others, and DAG
  • 5.4.2 Multiclass SVMs
  • 5.4.2.1 Vapnik's Approach
  • 5.4.2.2 Methodology of Crammer and Singer
  • 5.5 Relevance Vector Machines
  • 5.6 Twin Support Vector Machines
  • 5.7 Deep Support Vector Machines
  • 5.8 Concluding Remarks
  • References
  • Chapter 6 Decision Trees
  • 6.1 ID3, C4.5, and SEE5.0 Decision Trees
  • 6.1.1 ID3
  • 6.1.2 C4.5
  • 6.1.3 SEE5.0 (C5.0)
  • 6.2 CHAID
  • 6.3 CART
  • 6.4 QUEST
  • 6.4.1 Split Point Selection
  • 6.4.2 Attribute Selection
  • 6.5 Tree Induction from Artic fi ial Neural Networks
  • 6.6 Pruning Decision Trees
  • 6.6.1 Reduced Error Pruning
  • 6.6.2 Pessimistic Error Pruning
  • 6.6.3 Error-Based Pruning
  • 6.6.4 Cost Complexity Pruning
  • 6.6.5 Minimal Error Pruning
  • 6.7 Ensemble Methods
  • 6.7.1 Boosting
  • 6.7.2 Random Forest
  • 6.7.3 Rotation Forest.
  • 6.7.4 Canonical Correlation Forest
  • 6.7.5 Extreme Gradient Boosting
  • 6.7.6 Light Gradient Boosting Machines
  • 6.7.7 Gradient Boosting Machines
  • 6.7.8 Categorical Boosting
  • 6.7.9 Natural Gradient Boosting
  • 6.8 Concluding Remarks
  • References
  • Chapter 7 Deep Learning
  • 7.1 Fundamentals
  • 7.1.1 Stochastic Gradient Descent
  • 7.1.2 Backpropagation
  • 7.1.3 Regularization
  • 7.1.3.1 Weight Decay
  • 7.1.3.2 Dropout
  • 7.1.3.3 Data Augmentation
  • 7.1.3.4 Early Stopping
  • 7.1.4 Activation Functions
  • 7.1.5 Loss Functions
  • 7.2 Neural Network Architectures
  • 7.2.1 Multilayer Perceptron
  • 7.2.2 Convolutional Neural Networks
  • 7.2.2.1 Convolutional Layers
  • 7.2.2.2 Pooling Layers
  • 7.2.2.3 Fully Connected Layers
  • 7.2.2.4 Receptive Field and Feature Map
  • 7.2.2.5 Training CNNs
  • 7.2.2.6 Data Structures in CNNs
  • 7.2.2.7 Evolving Trends in CNN Design
  • 7.2.3 Recurrent Neural Networks
  • 7.2.3.1 Long- and Short-Term Memory
  • 7.2.3.2 Gated Recurrent Unit
  • 7.2.4 Vision Transformers
  • 7.2.5 Deep Multilayer Perceptron
  • 7.2.6 Generative Adversarial Networks
  • 7.2.7 Deep Autoencoders
  • 7.2.7.1 Undercomplete Autoencoders
  • 7.2.7.2 Regularized Autoencoders
  • 7.2.7.3 Sparse Autoencoders
  • 7.2.7.4 Denoising Autoencoders
  • 7.2.7.5 Variational Autoencoders
  • 7.3 Learning Paradigms
  • 7.3.1 Transfer Learning
  • 7.3.2 Semi-Supervised Learning
  • 7.3.3 Reinforcement Learning
  • 7.3.4 Active Learning
  • 7.3.5 Multitask Learning
  • 7.4 Application of DL in Remote Sensing
  • 7.4.1 Semantic Segmentation
  • 7.4.2 Object Detection
  • 7.4.3 Scene Classification
  • 7.4.4 Change Detection
  • 7.5 Concluding Remarks
  • References
  • Chapter 8 Object-B ased Image Analysis
  • 8.1 Clustering-Based Segmentation
  • 8.1.1 Mean-Shift Algorithm
  • 8.1.2 Superpixel Segmentation
  • 8.2 Thresholding-Based Segmentation
  • 8.3 Edge-Based Segmentation.
  • 8.4 Watershed Segmentation
  • 8.5 Region-Based Segmentation
  • 8.5.1 Region Splitting and Merging
  • 8.5.2 Region Growing
  • 8.5.3 Multiresolution Segmentation
  • 8.6 Hybrid Segmentation
  • 8.7 Evaluation of Segmentation Quality
  • 8.7.1 Supervised Approach
  • 8.7.2 Unsupervised Approach
  • 8.7.2.1 Estimation of the Scale Parameter
  • 8.7.2.2 Global Score
  • 8.7.2.3 Overall Goodness F-Measure
  • 8.8 Concluding Remarks
  • References
  • Chapter 9 Hyperparameter Optimization
  • 9.1 What Is Hyperparameter Optimization?
  • 9.2 Hyperparameter Optimization Techniques
  • 9.2.1 Model-Free Algorithms
  • 9.2.1.1 Trial-and-Error (Manual Testing)
  • 9.2.1.2 Grid Search
  • 9.2.1.3 Random Search
  • 9.2.2 Gradient-Based Optimization
  • 9.2.3 Bayesian Optimization
  • 9.2.4 Multifidelity Optimization
  • 9.2.4.1 Successive Halving
  • 9.2.4.2 Hyperband
  • 9.2.5 Metaheuristic Algorithms
  • 9.2.5.1 Genetic Algorithm
  • 9.2.5.2 Particle Swarm Optimization
  • 9.3 Challenges in Hyperparameter Optimization
  • 9.4 Concluding Remarks
  • References
  • Chapter 10 Accuracy Assessment and Model Explainability
  • 10.1 Accuracy Assessment
  • 10.1.1 Sampling Scheme and Spatial Autocorrelation
  • 10.1.2 Sample Size, Scale, and Spatial Variability
  • 10.1.3 Adequacy of Training and Testing Data
  • 10.1.4 Conventional Accuracy Analysis
  • 10.1.5 Accuracy Analysis for Machine Learning
  • 10.1.6 Fuzzy Accuracy Assessment
  • 10.1.7 Object-Based Accuracy Assessment
  • 10.2 Comparison of Thematic Maps
  • 10.2.1 McNemar's Test
  • 10.2.2 z-Test
  • 10.2.3 Wilcoxon Signed-Ranks Test
  • 10.2.4 5×2-Cross-Validation t-Test
  • 10.2.5 Friedman Test
  • 10.3 Explainability Methods
  • 10.3.1 SHapley Additive exPlanations
  • 10.3.2 Partial Dependence Plot
  • 10.3.3 Pairwise Interaction Importance
  • 10.3.4 Permutation-Based Feature Importance.
  • 10.3.5 Local Interpretable Model-Agnostic Explanations (LIME).

Ejemplares similares