Hyperspectral Imaging

1. Front Matter

   Pages i-xvii

   PDF

2. Introduction

   1. Introduction

      • Chein-I Chang

      Pages 1-11

3. Hyperspectral Measures

   1. Front Matter

      Pages 13-13

      PDF

   2. Hyperspectral Measures for Spectral Characterization

      • Chein-I Chang

      Pages 15-35

4. Subpixel Detection

   1. Front Matter

      Pages 37-38

      PDF

   2. Target Abundance-Constrained Subpixel Detection: Partially Constrained Least-Squares Methods

      • Chein-I Chang

      Pages 39-50

   3. Target Signature-Constrained Subpixel Detection: Linearly Constrained Minimum Variance (LCMV)

      • Chein-I Chang

      Pages 51-71

   4. Automatic Subpixel Detection: Unsupervised Subpixel Detection

      • Chein-I Chang

      Pages 73-88

   5. Automatic Subpixel Detection: Anomaly Detection

      • Chein-I Chang

      Pages 89-103

   6. Sensitivity of Subpixel Detection

      • Chein-I Chang

      Pages 105-137

5. Unconstrained Mixed Pixel Classification

   1. Front Matter

      Pages 139-140

      PDF

   2. Unconstrained Mixed Pixel Classification: Least-Squares Subspace Projection

      • Chein-I Chang

      Pages 141-159

   3. A Quantitative Analysis of Mixed-to-Pure Pixel Conversion (MPCV)

      • Chein-I Chang

      Pages 161-178

6. Constrained Mixed Pixel Classification

   1. Front Matter

      Pages 179-180

      PDF

   2. Target Abundance-Constrained Mixed Pixel Classification (TACMPC)

      • Chein-I Chang

      Pages 181-205

   3. Target Signature-Constrained Mixed Pixel Classification (TSCMPC): LCMV Classifiers

      • Chein-I Chang

      Pages 207-227

   4. Target Signature-Constrained Mixed Pixel Classification (TSCMPC): Linearly Constrained Discriminant Analysis (LCDA)

      • Chein-I Chang

      Pages 229-242

7. Automatic Mixed Pixel Classification (AMPC)

   1. Front Matter

      Pages 243-244

      PDF

   2. Automatic Mixed Pixel Classification (AMPC): Unsupervised Mixed Pixel Classification

      • Chein-I Chang

      Pages 245-255

   3. Automatic Mixed Pixel Classificatio (AMPC): Anomaly Classification

      • Chein-I Chang

      Pages 257-275

Hyperspectral Imaging: Techniques for Spectral Detection and Classification is an outgrowth of the research conducted over the years in the Remote Sensing Signal and Image Processing Laboratory (RSSIPL) at the University of Maryland, Baltimore County. It explores applications of statistical signal processing to hyperspectral imaging and further develops non-literal (spectral) techniques for subpixel detection and mixed pixel classification. This text is the first of its kind on the topic and can be considered a recipe book offering various techniques for hyperspectral data exploitation. In particular, some known techniques, such as OSP (Orthogonal Subspace Projection) and CEM (Constrained Energy Minimization) that were previously developed in the RSSIPL, are discussed in great detail. This book is self-contained and can serve as a valuable and useful reference for researchers in academia and practitioners in government and industry.

• classification
• detection
• digital elevation model
• image processing
• imaging
• remote sensing
• signal processing
• remote sensing/photogrammetry
• ecotoxicology

• Remote Sensing Signal and Image Processing Laboratory, University of Maryland, Baltimore County, Baltimore, USA

  Chein-I Chang

Policies and ethics