Chein-I Chang

Remote Sensing Signal and Image Processing Laboratory

University of Maryland, Baltimore County

Baltimore, Maryland


    This book 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 this topic and can be considered as a recipe book that offers 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 length.  This book is self-contained and can serve as a valuable and useful reference for researchers in academia and practitioners in government and industry.



Table of Contents

Chapter 1 -- Introduction (introduction only)

PART I: Hyperspectral Measures

Chapter 2 -- Hyperspectral Measures for Spectral Characterization (introduction only)

PART II: Subpixel Detection

Chapter 3 -- Target Abundance-Constrained Subpixel Detection: Partially Constrained Least-Squares Methods (introduction only)

Chapter 4 -- Target Signature-Constrained Subpixel Detection: Linearly Constrained Minimum Variance (LCMV) (introduction only)

Chapter 5 -- Automatic Subpixel Detection: Unsupervised Subpixel Detection (introduction only)

Chapter 6 -- Automatic Subpixel Detection: Anomaly Detection (introduction only)

Chapter 7 -- Sensitivity of Subpixel Detection (introduction only)

PART III: Unconstrained Mixed Pixel Classification

Chapter 8 -- Unconstrained Mixed Pixel Classification: Least-Squares Subspace Projection (introduction only)

Chapter 9 -- A Quantitative Analysis of Mixed-to-Pure Pixel Conversion (MPCV) (introduction only)

PART IV: Constrained Mixed Pixel Classification

Chapter 10 -- Target Abundance-Constrained Mixed Pixel Classification (TACMPC) (introduction only)

Chapter 11 -- Target Signature-Constrained Mixed Pixel Classification (TSCMPC): LCMV Classifiers (introduction only)

Chapter 12 -- Target Signature-Constrained Mixed Pixel Classification (TSCMPC): Linearly Constrained Discriminant Analysis (LCDA) (introduction only)

PART V: Automatic Mixed Pixel Classification (AMPC)

Chapter 13 -- Automatic Mixed Pixel Classification (AMPC): Unsupervised Mixed pixel Classification (introduction only)

Chapter 14 -- Automatic Mixed Pixel Classification (AMPC): Anomaly Classification (introduction only)

Chapter 15 -- Automatic Mixed Pixel Classification (AMPC): Linear Spectral Random Mixture Analysis (LSRMA) (introduction only)

Chapter 16 -- Automatic Mixed Pixel Classification (AMPC): Projection Pursuit (introduction only)

Chapter 17 -- Estimation for Virtual Dimensionality of Hyperspectral Imagery (introduction only)

Chapter 18 -- Conclusions and Further Techniques (introduction only)