Hyperspectral Data Processing: Algorithm Design and Analysis

Hyperspectral Data Processing: Algorithm Design and Analysis

Released April 2013
Publisher(s): Wiley-Interscience
ISBN: 9780471690566

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Hyperspectral Data Processing: Algorithm Design and Analysis is a culmination of the research conducted in the Remote Sensing Signal and Image Processing Laboratory (RSSIPL) at the University of Maryland, Baltimore County. Specifically, it treats hyperspectral image processing and hyperspectral signal processing as separate subjects in two different categories. Most materials covered in this book can be used in conjunction with the author's first book, Hyperspectral Imaging: Techniques for Spectral Detection and Classification, without much overlap.

Many results in this book are either new or have not been explored, presented, or published in the public domain. These include various aspects of endmember extraction, unsupervised linear spectral mixture analysis, hyperspectral information compression, hyperspectral signal coding and characterization, as well as applications to conceal target detection, multispectral imaging, and magnetic resonance imaging. Hyperspectral Data Processing contains eight major sections:

  • Part I: provides fundamentals of hyperspectral data processing

  • Part II: offers various algorithm designs for endmember extraction

  • Part III: derives theory for supervised linear spectral mixture analysis

  • Part IV: designs unsupervised methods for hyperspectral image analysis

  • Part V: explores new concepts on hyperspectral information compression

  • Parts VI & VII: develops techniques for hyperspectral signal coding and characterization

  • Part VIII: presents applications in multispectral imaging and magnetic resonance imaging

    • Hyperspectral Data Processing compiles an algorithm compendium with MATLAB codes in an appendix to help readers implement many important algorithms developed in this book and write their own program codes without relying on software packages.

    Hyperspectral Data Processing is a valuable reference for those who have been involved with hyperspectral imaging and its techniques, as well those who are new to the subject.

    Table of contents

    1. Cover
    2. Title Page
    3. Copyright
    4. Dedication
    5. Preface
    6. Chapter 1: Overview and Introduction
      1. 1.1 Overview
      2. 1.2 Issues of Multispectral and Hyperspectral Imageries
      3. 1.3 Divergence of Hyperspectral Imagery from Multispectral Imagery
      4. 1.4 Scope of This Book
      5. 1.5 Book's Organization
      6. 1.6 Laboratory Data to be Used in This Book
      7. 1.7 Real Hyperspectral Images to be Used in this Book
      8. 1.8 Notations and Terminologies to be Used in this Book
    7. I: Preliminaries
      1. Chapter 2: Fundamentals of Subsample and Mixed Sample Analyses
        1. 2.1 Introduction
        2. 2.2 Subsample Analysis
        3. 2.3 Mixed Sample Analysis
        4. 2.4 Kernel-Based Classification
        5. 2.5 Conclusions
      2. Chapter 3: Three-Dimensional Receiver Operating Characteristics (3D ROC) Analysis
        1. 3.1 Introduction
        2. 3.2 Neyman–Pearson Detection Problem Formulation
        3. 3.3 ROC Analysis
        4. 3.4 3D ROC Analysis
        5. 3.5 Real Data-Based ROC Analysis
        6. 3.6 Examples
        7. 3.7 Conclusions
      3. Chapter 4: Design of Synthetic Image Experiments
        1. 4.1 Introduction
        2. 4.2 Simulation of Targets of Interest
        3. 4.3 Six Scenarios of Synthetic Images
        4. 4.4 Applications
        5. 4.5 Conclusions
      4. Chapter 5: Virtual Dimensionality of Hyperspectral Data
        1. 5.1 Introduction
        2. 5.2 Reinterpretation of VD
        3. 5.3 VD Determined by Data Characterization-Driven Criteria
        4. 5.4 VD Determined by Data Representation-Driven Criteria
        5. 5.5 Synthetic Image Experiments
        6. 5.6 VD Estimated for Real Hyperspectral Images
        7. 5.7 Conclusions
      5. Chapter 6: Data Dimensionality Reduction
        1. 6.1 Introduction
        2. 6.2 Dimensionality Reduction by Second-Order Statistics-Based Component Analysis Transforms
        3. 6.3 Dimensionality Reduction by High-Order Statistics-Based Components Analysis Transforms
        4. 6.4 Dimensionality Reduction by Infinite-Order Statistics-Based Components Analysis Transforms
        5. 6.5 Dimensionality Reduction by Projection Pursuit-Based Components Analysis Transforms
        6. 6.6 Dimensionality Reduction by Feature Extraction-Based Transforms
        7. 6.7 Dimensionality Reduction by Band Selection
        8. 6.8 Constrained Band Selection
        9. 6.9 Conclusions
    8. II: Endmember Extraction
      1. Chapter 7: Simultaneous Endmember Extraction Algorithms (SM-EEAs)
        1. 7.1 Introduction
        2. 7.2 Convex Geometry-Based Endmember Extraction
        3. 7.3 Second-Order Statistics-Based Endmember Extraction
        4. 7.4 Automated Morphological Endmember Extraction (AMEE)
        5. 7.5 Experiments
        6. 7.6 Conclusions
      2. Chapter 8: Sequential Endmember Extraction Algorithms (SQ-EEAs)
        1. 8.1 Introduction
        2. 8.2 Successive N-FINDR (SC N-FINDR)
        3. 8.3 Simplex Growing Algorithm (SGA)
        4. 8.4 Vertex Component Analysis (VCA)
        5. 8.5 Linear Spectral Mixture Analysis-Based SQ-EEAs
        6. 8.6 High-Order Statistics-Based SQ-EEAS
        7. 8.7 Experiments
        8. 8.8 Conclusions
      3. Chapter 9: Initialization-Driven Endmember Extraction Algorithms (ID-EEAs)
        1. 9.1 Introduction
        2. 9.2 Initialization Issues
        3. 9.3 Initialization-Driven EEAs
        4. 9.4 Experiments
        5. 9.5 Conclusions
      4. Chapter 10: Random Endmember Extraction Algorithms (REEAs)
        1. 10.1 Introduction
        2. 10.2 Random PPI (RPPI)
        3. 10.3 Random VCA (RVCA)
        4. 10.4 Random N-FINDR (RN-FINDR)
        5. 10.5 Random SGA (RSGA)
        6. 10.6 Random ICA-Based EEA (RICA-EEA)
        7. 10.7 Synthetic Image Experiments
        8. 10.8 Real Image Experiments
        9. 10.9 Conclusions
      5. Chapter 11: Exploration on Relationships among Endmember Extraction Algorithms
        1. 11.1 Introduction
        2. 11.2 Orthogonal Projection-Based EEAs
        3. 11.3 Comparative Study and Analysis Between SGA and VCA
        4. 11.4 Does an Endmember Set Really Yield Maximum Simplex Volume?
        5. 11.5 Impact of Dimensionality Reduction on EEAs
        6. 11.6 Conclusions
    9. III: Supervised Linear Hyperspectral Mixture Analysis
      1. Chapter 12: Orthogonal Subspace Projection Revisited
        1. 12.1 Introduction
        2. 12.2 Three Perspectives to Derive OSP
        3. 12.3 Gaussian Noise in OSP
        4. 12.4 OSP Implemented with Partial Knowledge
        5. 12.5 OSP Implemented Without Knowledge
        6. 12.6 Conclusions
      2. Chapter 13: Fisher's Linear Spectral Mixture Analysis
        1. 13.1 Introduction
        2. 13.2 Feature Vector-Constrained FLSMA (FVC-FLSMA)
        3. 13.3 Relationship Between FVC-FLSMA and LCMV, TCIMF, and CEM
        4. 13.4 Relationship Between FVC-FLSMA and OSP
        5. 13.5 Relationship Between FVC-FLSMA and LCDA
        6. 13.6 Abundance-Constrained Least Squares FLDA (ACLS-FLDA)
        7. 13.7 Synthetic Image Experiments
        8. 13.8 Real Image Experiments
        9. 13.9 Conclusions
      3. Chapter 14: Weighted Abundance-Constrained Linear Spectral Mixture Analysis
        1. 14.1 Introduction
        2. 14.2 Abundance-Constrained LSMA (AC-LSMA)
        3. 14.3 Weighted Least-Squares Abundance-Constrained LSMA
        4. 14.4 Synthetic Image-Based Computer Simulations
        5. 14.5 Real Image Experiments
        6. 14.6 Conclusions
      4. Chapter 15: Kernel-Based Linear Spectral Mixture Analysis
        1. 15.1 Introduction
        2. 15.2 Kernel-Based LSMA (KLSMA)
        3. 15.3 Synthetic Image Experiments
        4. 15.4 AVIRIS Data Experiments
        5. 15.5 HYDICE Data Experiments
        6. 15.6 Conclusions
    10. IV: Unsupervised Hyperspectral Image Analysis
      1. Chapter 16: Hyperspectral Measures
        1. 16.1 Introduction
        2. 16.2 Signature Vector-Based Hyperspectral Measures for Target Discrimanition and Identification
        3. 16.3 Correlation-Weighted Hyperspectral Measures for Target Discrimanition and Identification
        4. 16.4 Experiments
        5. 16.5 Conclusions
      2. Chapter 17: Unsupervised Linear Hyperspectral Mixture Analysis
        1. 17.1 Introduction
        2. 17.2 Least Squares-Based ULSMA
        3. 17.3 Component Analysis-Based ULSMA
        4. 17.4 Synthetic Image Experiments
        5. 17.5 Real-Image Experiments
        6. 17.6 ULSMA Versus Endmember Extraction
        7. 17.7 Conclusions
      3. Chapter 18: Pixel Extraction and Information
        1. 18.1 Introduction
        2. 18.2 Four Types of Pixels
        3. 18.3 Algorithms Selected to Extract Pixel Information
        4. 18.4 Pixel Information Analysis via Synthetic Images
        5. 18.5 Real Image Experiments
        6. 18.6 Conclusions
    11. V: Hyperspectral Information Compression
      1. Chapter 19: Exploitation-Based Hyperspectral Data Compression
        1. 19.1 Introduction
        2. 19.2 Hyperspectral Information Compression Systems
        3. 19.3 Spectral/Spatial Compression
        4. 19.4 Progressive Spectral/Spatial Compression
        5. 19.5 3D Compression
        6. 19.6 Exploration-Based Applications
        7. 19.7 Experiments
        8. 19.8 Conclusions
      2. Chapter 20: Progressive Spectral Dimensionality Process
        1. 20.1 Introduction
        2. 20.2 Dimensionality Prioritization
        3. 20.3 Representation of Transformed Components for DP
        4. 20.4 Progressive Spectral Dimensionality Process
        5. 20.5 Hyperspectral Compression by PSDP
        6. 20.6 Experiments for PSDP
        7. 20.7 Conclusions
      3. Chapter 21: Progressive Band Dimensionality Process
        1. 21.1 Introduction
        2. 21.2 Band Prioritization
        3. 21.3 Criteria for Band Prioritization
        4. 21.4 Experiments for BP
        5. 21.5 Progressive Band Dimensionality Process
        6. 21.6 Hyperspectral Compresssion by PBDP
        7. 21.7 Experiments for PBDP
        8. 21.8 Conclusions
      4. Chapter 22: Dynamic Dimensionality Allocation
        1. 22.1 Introduction
        2. 22.2 Dynamic Dimensionality Allocaction
        3. 22.3 Signature Discriminatory Probabilties
        4. 22.4 Coding Techniques for Determining DDA
        5. 22.5 Experiments for Dynamic Dimensionality Allocation
        6. 22.6 Conclusions
      5. Chapter 23: Progressive Band Selection
        1. 23.1 Introduction
        2. 23.2 Band De-Corrleation
        3. 23.3 Progressive Band Selection
        4. 23.4 Experiments for Progressive Band Selection
        5. 23.5 Endmember Extraction
        6. 23.6 Land Cover/Use Classification
        7. 23.7 Linear Spectral Mixture Analysis
        8. 23.8 Conclusions
    12. VI: Hyperspectral Signal Coding
      1. Chapter 24: Binary Coding For Spectral Signatures
        1. 24.1 Introduction
        2. 24.2 Binary Coding
        3. 24.3 Spectral Feature-Based Coding
        4. 24.4 Experiments
        5. 24.5 Conclusions
      2. Chapter 25: Vector Coding for Hyperspectral Signatures
        1. 25.1 Introduction
        2. 25.2 Spectral Derivative Feature Coding
        3. 25.3 Spectral Feature Probabilistic Coding
        4. 25.4 Real Image Experiments
        5. 25.5 Conclusions
      3. Chapter 26: Progressive Coding for Spectral Signatures
        1. 26.1 Introduction
        2. 26.2 Multistage Pulse Code Modulation
        3. 26.3 MPCM-Based Progressive Spectral Signature Coding
        4. 26.4 NIST-GAS Data Experiments
        5. 26.5 Real Image Hyperspectral Experiments
        6. 26.6 Conclusions
    13. VII: Hyperspectral Signal Characterization
      1. Chapter 27: Variable-Number Variable-Band Selection for Hyperspectral Signals
        1. 27.1 Introduction
        2. 27.2 Orthogonal Subspace Projection-Based Band Prioritization Criterion
        3. 27.3 Variable-Number Variable-Band Selection
        4. 27.4 Experiments
        5. 27.5 Selection of Reference Signatures
        6. 27.6 Conclusions
      2. Chapter 28: Kalman Filter-Based Estimation for Hyperspectral Signals
        1. 28.1 Introduction
        2. 28.2 Kalman Filter-Based Linear Unmixing
        3. 28.3 Kalman Filter-Based Spectral Characterization Signal-Processing Techniques
        4. 28.4 Computer Simulations Using AVIRIS Data
        5. 28.5 Computer Simulations Using NIST-Gas Data
        6. 28.6 Real Data Experiments
        7. 28.7 Conclusions
      3. Chapter 29: Wavelet Representation for Hyperspectral Signals
        1. 29.1 Introduction
        2. 29.2 Wavelet Analysis
        3. 29.3 Wavelet-Based Signature Characterization Algorithm
        4. 29.4 Synthetic Image-Based Computer Simulations
        5. 29.5 Real Image Experiments
        6. 29.6 Conclusions
    14. VIII: Applications
      1. Chapter 30: Applications of Target Detection
        1. 30.1 Introduction
        2. 30.2 Size Estimation of Subpixel Targets
        3. 30.3 Experiments
        4. 30.4 Concealed Target Detection
        5. 30.5 Computer-Aided Detection and Classification Algorithm for Concealed Targets
        6. 30.6 Experiments for Concealed Target Detection
        7. 30.7 Conclusions
      2. Chapter 31: Nonlinear Dimensionality Expansion to Multispectral Imagery
        1. 31.1 Introduction
        2. 31.2 Band Dimensionality Expansion
        3. 31.3 Hyperspectral Imaging Techniques Expanded by BDE
        4. 31.4 Feature Dimensionality Expansion by Nonlinear Kernels
        5. 31.5 BDE in Conjunction with FDE
        6. 31.6 Multispectral Image Experiments
        7. 31.7 Conclusion
      3. Chapter 32: Multispectral Magnetic Resonance Imaging
        1. 32.1 Introduction
        2. 32.2 Linear Spectral Mixture Analysis for MRI
        3. 32.3 Linear Spectral Random Mixture Analysis for MRI
        4. 32.4 Kernel-Based Linear Spectral Mixture Analysis
        5. 32.5 Synthetic MR Brain Image Experiments
        6. 32.6 Real MR Brain Image Experiments
        7. 32.7 Conclusions
      4. Chapter 33: Conclusions
        1. 33.1 Design Principles for Nonliteral Hyperspectral Imaging Techniques
        2. 33.2 Endemember Extraction
        3. 33.3 Linear Spectral Mixture Analysis
        4. 33.4 Anomaly Detection
        5. 33.5 Support Vector Machines and Kernel-Based Approaches
        6. 33.6 Hyperspectral Compression
        7. 33.7 Hyperspectral Signal Processing
        8. 33.8 Applications
        9. 33.9 Further Topics
    15. Glossary
    16. Appendix: Algorithm Compendium
    17. References
    18. Index

    Product information

    • Title: Hyperspectral Data Processing: Algorithm Design and Analysis
    • Author(s):
    • Release date: April 2013
    • Publisher(s): Wiley-Interscience
    • ISBN: 9780471690566