Hyperspectral Imaging: Techniques for Spectral Detection and Classification

ISBN-13: 9780306474835 / Angielski / Twarda / 2003 / 370 str.

Chein-I Chang; Chang Chein-I Chang

Opis

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.

Spis treści

1. Introduction. Part I: Hyperspectral Measures. 2. Hyperspectral measures for spectral characterization. Part II: Subpixel Detection. 3. Target abundance-constrained subpixel detection. 4. Target signature-constrained subpixel detection: linearly constrained minimum variance (LCMV). 5. Automatic subpixel detection (unsupervised subpixel detection). 6. Anomaly detection. 7. Sensitivity of subpixel detection. Part III: Unconstrained Mixed Pixel Classification. 8. Unconstrained Mixed Pixel Classification: least squares subspace projection. 9. A quantitative analysis of mixed-to-pure pixel conversion. Part IV: Constrained Mixed Pixel Classification. 10. Target abundance-constrained mixed pixel classification (TACMPC). 11. Target signature-constrained mixed pixel classification (TSCMPC): LCMV multiple target classifiers. 12. Signature-constrained mixed pixel classification (TSCMPC): Linearly constrained discriminant analysis (LCDA). Part V: Automatic Mixed Pixel Classification (AMPC). 13. Automatic mixed pixel classification (AMPC): unsupervised mixed pixel classification. 14. Automatic mixed pixel classification (AMPC): anomaly classification. 15. Automatic mixed pixel classification (AMPC): linear spectral random mixture analysis (LSRMA). 16. Automatic mixed pixel classification (AMPC): projection pursuit. 17. Estimation of virtual dimensionality of hyperspectral imagery. 18. Conclusion and further techniques. Glossary. References. Index.