1 Basic Theory and Main Processing Techniques of Hyperspectral Remote Sensing
1．1 Basic Theory of Hyperspectral Remote Sensing
1．1．1 Theory of Remote Electromagnetic Wave
1．1．2 Interaction of Solar Radiation and Materials
1．1．3 Imaging Spectrometer and Spectral Imaging Modes
1．1．4 Imaging Characteristics of HSI
1．2 Classification Technique of HSI
1．2．1 Supervised Classifications and Unsupervised
Classifications
1．2．2 Parameter Classifications and Nonparameter
Classifications
1．2．3 Crisp Classifications and Fuzzy Classifications
1．2．4 Other Classification Methods
1．3 Endmember Extraction Technique of HSI
1．4 Spectral Unmixing Technique of HSI
1．4．1 Nonlinear Model
1．4．2 Linear Model
1．4．3 Multi-endmember Mode of Linear Model
1．5 Sub-pixel Mapping Technique of HSI
1．5．1 Spatial Correlation-Based Sub-pixel Mapping
1．5．2 Spatial Geostatistics-Based Sub-pixel Mapping
1．5．3 Neural Network-Based Sub-pixel Mapping
1．5．4 Pixel-Swapping Strategy-Based Sub-pixel Mapping
1．6 Super Resolution Technique of HSI
1．7 Anomaly Detection Technique of HSI
1．8 Dimensionality Reduction and Compression
Technique for HSI
1．8．1 Dimensionality Reduction： Band Selection
and Feature Extraction
1．8．2 Compression： Lossy Compression and Lossless
Compression
References
2 Classification Technique for HSI
2．1 Typical Classification Methods
2．2 Typical Assessment Criterions
2．3 SVM-Based Classification Method
2．3．1 Theory Foundation
2．3．2 Classification Principle
2．3．3 Construction of Multi-class Classifier
with the Simplest Structure
2．3．4 Least Squares SVM and Its SMO Optimization
Algorithm
2．3．5 Triply Weighted Classification Method
2．4 Performance Assessment for SVM-Based Classification
2．4．1 Performance Assessment for Original SVM-Based
Classification
2．4．2 Performance Assessment for Multi-class Classifier
with the Simplest Structure
2．4．3 Performance Assessment for Triply Weighted
Classification
2．5 Chapter Conclusions
References
3 Endmember Extraction Technique of HSI
3．1 Endmember Extraction Method： N-FINDR
3．1．1 Introduction of Related Theory
3．1．2 N-FINDR Algorithm
3．2 Distance Measure-Based Fast N-FINDR Algorithm
3．2．1 Substituting Distance Measure for Volume One
3．2．2 PPI Concept-Based Pixel Indexing
3．2．3 Complexity Analysis and Efficiency Assessment
3．3 Linear LSSVM-Based Distance Calculation
3．4 Robust Method in Endmember Extraction
3．4．1 In the Pre-processing Stage： Obtaining of Robust
Covariance Matrix
3．4．2 In Endmember Extraction Stage： Deletion of Outliers
3．5 Performance Assessment
3．5．1 Distance Measure-Based N-FINDR Fast Algorithm
3．5．2 Robustness Assessment
3．6 Two Applications of Fast N-FINDR Algorithm
3．6．1 Construction of New Solving Algorithm for LSMM
3．6．2 Construction of Fast and Unsupervised Band Selection
Algorithm
3．7 Chapter Conclusions
References
4 Spectral Unmixing Technique of HSI
4．1 LSMM-Based LSMA Method
4．2 Two New Solving Methods for Full Constrained LSMA
4．2．1 Parameter Substitution Method in Iteration
Solving Method
4．2．2 Geometric Solving Method
4．3 The Principle of LSVM-Based Spectral Unmixing
4．3．1 Equality Proof of LSVM and LSMM
for Spectral Unmixing
4．3．2 The Unique Superiority of LSVM-Based Unmixing
4．4 Spatial-Spectral Information-Based Unmixing Method
4．5 SVM-Based Spectral Unmixing Model with Unmixing
Residue Constraints
4．5．1 Original LSSVM-Based Spectral Unmixing
4．5．2 Construction of Spectral Unmixing Model Based
on Unmixing Residue Constrained LSSVM
and Derivation of Its Closed form Solution
4．5．3 Substituting Multiple Endmembers for Single
One in the New Model
4．6 Performance Assessment
4．6．1 Performance Assessment for Original SVM-Based
Spectral Unmixing
4．6．2 Assessment on Robust Weighted SVM-Based
Unmixing
4．6．3 Assessment on Spatial-Spectral Unmixing Method
4．6．4 Performance Assessment on New SVM Unmixing
Model with Unmixing Residue Constraints
4．7 Fuzzy Method of Accuracy Assessment of Spectral Unmixing
4．7．1 Fuzzy Method of Accuracy Assessment
4．7．2 Application of Fuzzy Method of Accuracy
Assessment in Experiments
4．8 Chapter Conclusions
References
5 Subpixel Mapping Technique of HSI
5．1 Subpixel Mapping for a Land Class with Linear Features
Using a Least Square Support Vector Machine （LSSVM）
5．1．1 Subpixel Mapping Based on the Least Square
Support Vector Machine （LSSVM）
5．1．2 Artificially Synthesized Training Samples
5．2 Spatial Attraction-Based Subpixel Mapping （SPSAM）
5．2．1 Subpixel Mapping Based on the Modified
Subpixel/Pixel Spatial Attraction Model （MSPSAM）
5．2．2 Subpixel Mapping Based on the Mixed Spatial
Attraction Model （MSAM）
5．3 Subpixel Mapping Using Markov Random Field
with Subpixel Shifted Remote Sensing Images
5．3．1 Markov Random Field-Based Subpixel Mapping
5．3．2 Markov Random Field-Based Subpixel Mapping
with Subpixel Shifted Remote-Sensing Images
5．4 Accuracy Assessment
5．4．1 Subpixel Mapping for Land Class with Linear
Features Using the Least Squares Support Vector
Machine （LSSVM）
5．4．2 MSPSAM and MSAM
5．4．3 MRF-Based Subpixel Mapping with Subpixel
Shifted Remote-Sensing Images
5．5 Chapter Conclusions
References
6 Super-Resolution Technique of HSI
6．1 POCS Algorithm-Based Super-Resolution Recovery
6．1．1 Basic Theory of POCS
6．1．2 POCS Algorithm-Based Super-Resolution Recovery
6．2 MAP Algorithm-Based Super-Resolution Recovery
6．2．1 Basic Theory of MAP
6．2．2 MAP Algorithm-Based Super-Resolution Recovery
6．3 Resolution Enhancement Method for Single Band
6．3．1 Construction of Geometric Dual Model
and Interpolation Method
6．3．2 Mixed Interpolation Method
6．4 Performance Assessment
6．4．1 POCS and MAP-Based Super-Resolution Methods
6．4．2 Dual Interpolation Method
6．5 Chapter Conclusions
References
7 Anomaly Detection Technique of HSI
7．1 Kernel Detection Algorithm Based on the Theory
of the Morphology
7．1．1 Band Selection Based on Morphology
7．1．2 Kernel RX Algorithm Based on Morphology
7．2 Adaptive Kernel Anomaly Detection Algorithm
7．2．1 The Method of Support Vector Data Description
7．2．2 Adaptive Kernel Anomaly Detection Algorithm
7．3 Construction of Spectral Similarity Measurement Kernel
in Kernel Anomaly Detection
7．3．1 The Limitations of Gaussian Radial Basis Kernel
7．3．2 Spectral Similarity Measurement Kernel Function
7．4 Performance Assessment
7．4．1 Effect Testing of Morphology-Based Kernel
Detection Algorithm
7．4．2 Effect Testing of Adaptive Kernel Anomaly
Detection Algorithm
7．4．3 Effect Testing of Spectral Similarity Measurement
Kernel-Based Anomaly Detection Algorithm
7．5 Introduction of Other Anomaly Detection Algorithms
7．5．1 Spatial Filtering-Based Kernel RX Anomaly Detection
Algorithm
7．5．2 Multiple Window Analysis-Based Kernel Detection
Algorithm
7．6 Summary
References
8 Dimensionafity Reduction and Compression Technique of HSI
8．1 Dimensionality Reduction Technique
8．1．1 SVM-Based Band Selection
8．1．2 Application of Typical Endmember Methods-based
Band Selection
8．1．3 Simulation Experiments
8．2 Compression Technique
8．2．1 Vector Quantization-based Compression Algorithm
8．2．2 Lifting Scheme-based Compression Algorithm
8．3 Chapter Conclusions
References
9 Introduction of Hyperspectral Remote Sensing Applications
9．1 Agriculture
9．1．1 Wheat
9．1．2 Paddy
9．1．3 Soybean
9．1．4 Maize
9．2 Forest
9．2．1 Forest Investigation
9．2．2 Forest Biochemical Composition and Forest
Health Status
9．2．3 Forest Disaster
9．2．4 Exotic Species Monitoring
9．3 Meadow
9．3．1 Biomass Estimation in Meadow
9．3．2 Grassland Species Identification
9．3．3 Chemical Constituent Estimation
9．4 Ocean
9．4．1 Basic Research on Ocean Remote Sensing
9．4．2 Application Research on Rescurce and Environment
Monitoring of Ocean and Coastal Zone
9．4．3 International Development Trend
9．5 Geology
9．5．1 Mineral Identification
9．5．2 Resource Exploration
9．6 Environment
9．6．1 Atmospheric Pollution Monitoring
9，6．2 Soil Erosion Monitoring
9．6．3 Water Environment Monitoring
9．7 Military Affairs
References
Appendix
鄂公网安备 42010302001612号 