Hyperspectral Remote Sensing Fundamentals and Practices

4.5.1.2 Continuum Interpolated Band Ratio (CIBR) -- 4.5.1.3 Three-Band Ratioing (3BR) -- 4.5.1.4 Linear Regression Ratio (LIRR) -- 4.5.1.5 Atmospheric Pre-Corrected Differential Absorption (APAD) -- 4.5.2 Atmospheric Aerosols -- 4.5.2.1 Dark Dense Vegetation (DDV) Technique -- 4.5.2.2 Aerosol Optical Thickness at 550 nm (AOT at 550 nm) -- 4.6 Summary -- References -- Chapter 5: Hyperspectral Data Analysis Techniques -- 5.1 Introduction -- 5.2 Spectral Derivative Analysis -- 5.3 Spectral Similarity Measures -- 5.3.1 Cross-Correlogram Spectral Matching (CCSM) -- 5.3.2 Spectral Angle Matching (SAM) -- 5.3.3 Euclidian Distance (ED) -- 5.3.4 Spectral Information Divergence (SID) -- 5.4 Spectral Absorption Features and Wavelength Position Variables -- 5.4.1 Four-Point Interpolation -- 5.4.2 Polynomial Fitting -- 5.4.3 Lagrangian Technique -- 5.4.4 IG Modeling -- 5.4.5 Linear Extrapolation -- 5.5 Spectral Vegetation Indices -- 5.6 Hyperspectral Transformation and Feature Extraction -- 5.6.1 Principal Components Analysis (PCA) -- 5.6.2 Signal-to-Noise Ratio-Based Image Transforms -- 5.6.2.1 Maximum Noise Fraction (MNF) Transform -- 5.6.2.2 Noise-Adjusted Principal Component Transform -- 5.6.3 Independent Component Analysis -- 5.6.4 Canonical Discriminant Analysis (CDA) -- 5.6.5 Wavelet Transform -- 5.7 Spectral Mixture Analysis (SMA) -- 5.7.1 Traditional Spectral Unmixing Modeling Techniques -- 5.7.2 Artificial Neural Networks Solution to LSM -- 5.7.3 Multiple End-Member Spectral Mixture Analysis (MESMA) -- 5.7.4 Mixture-Tuned Matched Filtering Technique (MTMF) -- 5.7.5 Constrained Energy Minimization (CEM) -- 5.7.6 End-Member Extraction -- 5.7.6.1 Pixel Purity Index (PPI) -- 5.7.6.2 N-Finder -- 5.8 Hyperspectral Image Classifications -- 5.8.1 Segment-Based Multispectral Classifiers -- 5.8.2 Artificial Neural Networks (ANN) -- 5.8.3 Support Vector Machines