Hyperspectral Imaging: Techniques for Spectral Detection and ClassificationHyperspectral 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. |
Contents
| 2 | |
HYPERSPECTRAL MEASURES | 13 |
2 | 20 |
AVIRIS Data | 31 |
SUBPIXEL DETECTION | 37 |
UNSUPERVISED SUBPIXEL | 73 |
ANOMALY DETECTION | 89 |
SENSITIVITY OF SUBPIXEL DETECTION | 105 |
CONSTRAINED MIXED PIXEL CLASSIFICATION | 179 |
TARGET SIGNATURECONSTRAINED MIXED PIXEL | 207 |
TARGET SIGNATURECONSTRAINED MIXED PIXEL | 229 |
AUTOMATIC MIXED PIXEL CLASSIFICATION AMPC | 243 |
ANOMALY | 257 |
LINEAR | 277 |
ESTIMATION FOR VIRTUAL DIMENSIONALITY | 319 |
CONCLUSIONS AND FURTHER TECHNIQUES | 335 |
UNCONSTRAINED MIXED PIXEL CLASSIFICATION | 139 |
A QUANTITATIVE ANALYSIS OF MIXEDTOPURE PIXEL | 161 |
Other editions - View all
Hyperspectral Imaging: Techniques for Spectral Detection and ..., Volume 1 Chein-I Chang Limited preview - 2003 |
Hyperspectral Imaging: Techniques for Spectral Detection and Classification Chein-I Chang No preview available - 2011 |
Hyperspectral Imaging: Techniques for Spectral Detection and Classification Chein-I. Chang No preview available - 2003 |
Common terms and phrases
abundance fractions algorithm analysis anomaly detection background signatures blackbrush BRLCMV CEM and TCIMF Chapter cinders classification results components creosote leaves desired target signature detection and classification detection performance Detection results detector dry grass eigenvalues eigenvectors estimated abundance fractions FCLS Figure Gaussian HMMID hyperspectral image image data image pixel vector image scene implemented kurtosis LCDA least-squares LSRMA LXL LXL matched filter methods MFCLS mixed pixel classification mixture model MRXD NCLS no/no noise NSCLS OBSP orthogonal OSP classifiers P₁ panel pixels panels in row pixel detected Pixel Number pixel vector playa posteriori prior red soil Remote Sensing rhyolite ROC curves sagebrush sample covariance matrix SCLS self-information shown in Fig signal sources simulated specified spectral signatures subpixel detection subspace projection Table target detection target information target knowledge target pixels target signature matrix threshold UFCLS UNCLS algorithm unconstrained undesired unsupervised UTGP