高光谱图像处理技术 英文PDF电子书下载

1 Basic Theory and Main Processing Techniques of Hyperspectral Remote Sensing 1

1.1 Basic Theory of Hyperspectral Remote Sensing 1

1.1.1 Theory of Remote Electromagnetic Wave 1

1.1.2 Interaction of Solar Radiation and Materials 2

1.1.3 Imaging Spectrometer and Spectral Imaging Modes 3

1.1.4 Imaging Characteristics of HSI 7

1.2 Classification Technique of HSI 8

1.2.1 Supervised Classifications and Unsupervised Classifications 8

1.2.2 Parameter Classifications and Nonparameter Classifications 11

1.2.3 Crisp Classifications and Fuzzy Classifications 13

1.2.4 Other Classification Methods 13

1.3 Endmember Extraction Technique of HSI 14

1.4 Spectral Unmixing Technique of HSI 17

1.4.1 Nonlinear Model 18

1.4.2 Linear Model 19

1.4.3 Multi-endmember Mode of Linear Model 23

1.5 Sub-pixel Mapping Technique of HSI 24

1.5.1 Spatial Correlation-Based Sub-pixel Mapping 26

1.5.2 Spatial Geostatistics-Based Sub-pixel Mapping 28

1.5.3 Neural Network-Based Sub-pixel Mapping 29

1.5.4 Pixel-Swapping Strategy-Based Sub-pixel Mapping 30

1.6 Super Resolution Technique of HSI 32

1.7 Anomaly Detection Technique of HSI 35

1.8 Dimensionality Reduction and Compression Technique for HSI 38

1.8.1 Dimensionality Reduction：Band Selection and Feature Extraction 38

1.8.2 Compression：Lossy Compression and Lossless Compression 42

References 44

2 Classification Technique for HSI 45

2.1 Typical Classification Methods 45

2.2 Typical Assessment Criterions 48

2.3 SVM-Based Classification Method 50

2.3.1 Theory Foundation 50

2.3.2 Classification Principle 52

2.3.3 Construction of Multi-class Classifier with the Simplest Structure 60

2.3.4 Least Squares SVM and Its SMO Optimization Algorithm 63

2.3.5 Triply Weighted Classification Method 66

2.4 Performance Assessment for SVM-Based Classification 70

2.4.1 Performance Assessment for Original SVM-Based Classification 72

2.4.2 Performance Assessment for Multi-class Classifier with the Simplest Structure 73

2.4.3 Performance Assessment for Triply Weighted Classification 74

2.5 Chapter Conclusions 76

References 77

3 Endmember Extraction Technique of HSI 79

3.1 Endmember Extraction Method：N-FINDR 79

3.1.1 Introduction of Related Theory 79

3.1.2 N-FINDR Algorithm 82

3.2 Distance Measure-Based Fast N-FINDR Algorithm 84

3.2.1 Substituting Distance Measure for Volume One 84

3.2.2 PPI Concept-Based Pixel Indexing 86

3.2.3 Complexity Analysis and Efficiency Assessment 87

3.3 Linear LSSVM-Based Distance Calculation 87

3.4 Robust Method in Endmember Extraction 89

3.4.1 In the Pre-processing Stage：Obtaining of Robust Covariance Matrix 89

3.4.2 In Endmember Extraction Stage：Deletion of Outliers 92

3.5 Performance Assessment 92

3.5.1 Distance Measure-Based N-FINDR Fast Algorithm 92

3.5.2 Robustness Assessment 94

3.6 Two Applications of Fast N-FINDR Algorithm 98

3.6.1 Construction of New Solving Algorithm for LSMM 98

3.6.2 Construction of Fast and Unsupervised Band Selection Algorithm 99

3.7 Chapter Conclusions 103

References 103

4 Spectral Unmixing Technique of HSI 105

4.1 LSMM-Based LSMA Method 105

4.2 Two New Solving Methods for Full Constrained LSMA 108

4.2.1 Parameter Substitution Method in Iteration Solving Method 108

4.2.2 Geometric Solving Method 109

4.3 The Principle of LSVM-Based Spectral Unmixing 114

4.3.1 Equality Proof of LSVM and LSMM for Spectral Unmixing 114

4.3.2 The Unique Superiority of LSVM-Based Unmixing 116

4.4 Spatial-Spectral Information-Based Unmixing Method 117

4.5 SVM-Based Spectral Unmixing Model with Unmixing Residue Constraints 118

4.5.1 Original LSSVM-Based Spectral Unmixing 119

4.5.2 Construction of Spectral Unmixing Model Based on Unmixing Residue Constrained LSSVM and Derivation of Its Closed form Solution 121

4.5.3 Substituting Multiple Endmembers for Single One in the New Model 124

4.6 Performance Assessment 125

4.6.1 Performance Assessment for Original SVM-Based Spectral Unmixing 125

4.6.2 Assessment on Robust Weighted SVM-Based Unmixing 127

4.6.3 Assessment on Spatial-Spectral Unmixing Method 129

4.6.4 Performance Assessment on New SVM Unmixing Model with Unmixing Residue Constraints 131

4.7 Fuzzy Method of Accuracy Assessment of Spectral Unmixing 135

4.7.1 Fuzzy Method of Accuracy Assessment 135

4.7.2 Application of Fuzzy Method of Accuracy Assessment in Experiments 138

4.8 Chapter Conclusions 144

References 144

5 Subpixel Mapping Technique of HSI 147

5.1 Subpixel Mapping for a Land Class with Linear Features Using a Least Square Support Vector Machine（LSSVM） 149

5.1.1 Subpixel Mapping Based on the Least Square Support Vector Machine（LSSVM） 150

5.1.2 Artificially Synthesized Training Samples 152

5.2 Spatial Attraction-Based Subpixel Mapping（SPSAM） 154

5.2.1 Subpixel Mapping Based on the Modified Subpixel/Pixel Spatial Attraction Model（MSPSAM） 154

5.2.2 Subpixel Mapping Based on the Mixed Spatial Attraction Model（MSAM） 158

5.3 Subpixel Mapping Using Markov Random Field with Subpixel Shifted Remote Sensing Images 163

5.3.1 Markov Random Field-Based Subpixel Mapping 163

5.3.2 Markov Random Field-Based Subpixel Mapping with Subpixel Shifted Remote-Sensing Images 167

5.4 Accuracy Assessment 170

5.4.1 Subpixel Mapping for Land Class with Linear Features Using the Least Squares Support Vector Machine（LSSVM） 170

5.4.2 MSPSAM and MSAM 173

5.4.3 MRF-Based Subpixel Mapping with Subpixel Shifted Remote-Sensing Images 178

5.5 Chapter Conclusions 183

References 184

6 Super-Resolution Technique of HSI 187

6.1 POCS Algorithm-Based Super-Resolution Recovery 187

6.1.1 Basic Theory of POCS 187

6.1.2 POCS Algorithm-Based Super-Resolution Recovery 189

6.2 MAP Algorithm-Based Super-Resolution Recovery 193

6.2.1 Basic Theory of MAP 193

6.2.2 MAP Algorithm-Based Super-Resolution Recovery 197

6.3 Resolution Enhancement Method for Single Band 199

6.3.1 Construction of Geometric Dual Model and Interpolation Method 200

6.3.2 Mixed Interpolation Method 203

6.4 Performance Assessment 206

6.4.1 POCS and MAP-Based Super-Resolution Methods 206

6.4.2 Dual Interpolation Method 209

6.5 Chapter Conclusions 215

References 216

7 Anomaly Detection Technique of HSI 217

7.1 Kernel Detection Algorithm Based on the Theory of the Morphology 217

7.1.1 Band Selection Based on Morphology 218

7.1.2 Kernel RX Algorithm Based on Morphology 221

7.2 Adaptive Kernel Anomaly Detection Algorithm 224

7.2.1 The Method of Support Vector Data Description 225

7.2.2 Adaptive Kernel Anomaly Detection Algorithm 228

7.3 Construction of Spectral Similarity Measurement Kemel in Kernel Anomaly Detection 232

7.3.1 The Limitations of Gaussian Radial Basis Kernel 233

7.3.2 Spectral Similarity Measurement Kernel Function 234

7.4 Performance Assessment 238

7.4.1 Effect Testing of Morphology-Based Kernel Detection Algorithm 238

7.4.2 Effect Testing of Adaptive Kernel Anomaly Detection Algorithm 241

7.4.3 Effect Testing of Spectral Similarity Measurement Kernel-Based Anomaly Detection Algorithm 244

7.5 Introduction of Other Anomaly Detection Algorithms 249

7.5.1 Spatial Filtering-Based Kernel RX Anomaly Detection Algorithm 249

7.5.2 Multiple Window Analysis-Based Kernel Detection Algorithm 252

7.6 Summary 255

References 256

8 Dimensionality Reduction and Compression Technique of HSI 257

8.1 Dimensionality Reduction Technique 257

8.1.1 SVM-Based Band Selection 257

8.1.2 Application of Typical Endmember Methods-based Band Selection 262

8.1.3 Simulation Experiments 264

8.2 Compression Technique 266

8.2.1 Vector Quantization-based Compression Algorithm 266

8.2.2 Lifting Scheme-based Compression Algorithm 273

8.3 Chapter Conclusions 279

References 280

9 Introduction of Hyperspectral Remote Sensing Applications 283

9.1 Agriculture 283

9.1.1 Wheat 283

9.1.2 Paddy 285

9.1.3 Soybean 285

9.1.4 Maize 286

9.2 Forest 286

9.2.1 Forest Investigation 286

9.2.2 Forest Biochemical Composition and Forest Health Status 289

9.2.3 Forest Disaster 290

9.2.4 Exotic Species Monitoring 291

9.3 Meadow 291

9.3.1 Biomass Estimation in Meadow 292

9.3.2 Grassland Species Identification 293

9.3.3 Chemical Constituent Estimation 294

9.4 Ocean 295

9.4.1 Basic Research on Ocean Remote Sensing 295

9.4.2 Application Research on Resource and Environment Monitoring of Ocean and Coastal Zone 296

9.4.3 International Development Trend 297

9.5 Geology 298

9.5.1 Mineral Identification 299

9.5.2 Resource Exploration 300

9.6 Environment 304

9.6.1 Atmospheric Pollution Monitoring 304

9.6.2 Soil Erosion Monitoring 305

9.6.3 Water Environment Monitoring 305

9.7 Military Affairs 306

References 308

Appendix 309