Hyperspectral Data Exploitation: Theory and Applications »

Chein-I Chang, PHD, is Professor in the Department of Computer Sciences and Electrical Engineering at the University of Maryland, Baltimore County, where he directs the Remote Sensing Signal and Image Processing Laboratory. Dr. Chang is a Fellow of SPIE, the International Society for Optical Engineering, for his achievements in hyperspectral image processing. He is Associate Editor of the IEEE Transactions on Geoscience and Remote Sensing and the author of Hyperspectral Imaging: Techniques for Spectral Detection and Classification.

A Unique Synthesis of Hyperspectral Imaging with Theory and Applications, Written by Pioneers in the Field

The rapid growth of interest in the use of hyperspectral imaging as a powerful remote sensing technique has been accompanied by hundreds of articles published in journals and conference proceedings. With new findings and applications dispersed across numerous sources, this contributed work provides a much-needed synthesis of what is known, what can be expected from current research and development, and what new research is needed.

The book's twenty-five contributors represent some of the field's most important innovators and pioneers from around the world. It begins with an overview written by the editor that discusses the design theory underlying the development of hyperspectral imaging techniques. This overview also provides a brief introduction to each of the book's thirteen chapters, with an emphasis on the interconnections among them. Chapters are organized into three parts: Tutorials, Theory, and Applications.

Among the spectrum of topics covered are imaging systems, data modeling, data representation, band selection and partition, classification, and data compression.

Readers discover a wide range of current and emerging techniques for surface material identification, evaluation, and analysis of materials. Many of the chapters feature case studies that demonstrate applications in defense and homeland security, intelligence, environmental sciences, geology, and agriculture.

Researchers and practitioners throughout the field of remote sensing will find this volume an exceptionally valuable reference that brings together, analyzes, and synthesizes the many research findings and emerging applications in hyperspectral imaging.

Preface.

Contributors.

1. Overview (Chein-I Chang).

I TUTORALS.

2. Hyperspectral Imaging Systems (John P. Kerekes and John R. Schott).

3. Information-Processed Matched Filters for Hyperspectral Target Detection and Classification (Chein-I Chang).

II THEORY.

4. An Optical Real-Time Adaptive Spectral Identification System (ORASIS) (Jeffery H. Bowles and David B. Gillis).

5. Stochastic Mixture Modeling (Michael T. Eismann1 and David W. J. Stein).

6. Unmixing Hyperspectral Data: Independent and Dependent Component Analysis (Jose M.P. Nascimento1 and Jose M.B. Dias).

7. Maximum Volume Transform For Endmember Spectra Determination (Michael E. Winter).

8. Hyperspectral Data Representation (Xiuping Jia and John A. Richards).

9. Optimal Band Selection and Utility Evaluation for Spectral Systems (Sylvia S. Shen).

10. Feature Reduction for Classification Purpose (Sebastiano B. Serpico, Gabriele Moser, and Andrea F. Cattoni).

11. Semi-supervised Support Vector Machines for Classification of Hyperspectral Remote Sensing Images (Lorenzo Bruzzone, Mingmin Chi, and Mattia Marconcini).

III APPLICATIONS.

12. Decision Fusion for Hyperspectral Classification (Mathieu Fauvel, Jocelyn Chanussot, and Jon Atli Benediktsson)

13. Morphological Hyperspectral Image Classification: A Parallel Processing Perspective (Antonio J. Plaza).

14. Three-Dimensional Wavelet-Based Compression of Hyperspectral Imagery (James E. Fowler and Justin T. Rucker).

Index.