Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL

With an ever-increasing availability of aerial and satellite Earth observation data, image analysis has become an essential part of remote sensing. Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL combines theory, algorithms, and computer codes and conveys required proficiency in vector algebra and basic statistics. It covers such topics as basic Fourier transforms, wavelets, principle components, minimum noise fraction transformation, and othorectification. The text also discusses panchromatic sharpening, explores multivariate change detection, examines supervised and unsupervised land cover classification and hyperspectral analysis. With programming examples in IDL and applications that support ENVI, it offers many extensions, such as for data fusion, statistical change detection, clustering and supervised classification with neural networks, all available as downloadable source code. Focusing on pixel-oriented analysis of visual/infrared Earth observation satellite imagery, this book extends the ENVI interface in IDL in order to implement new methods and algorithms of arbitrary sophistication. All of the illustrations and applications in the text are programmed in RSI's ENVI/IDL. The software and source code is available for download at: http://www.crcpress.com/product/isbn/9780849372513 Ideal for undergraduate and graduate student, this book provides exercises and small programming projects at the end of each chapter. A solutions manual is also available.

Table of Contents:
List of Figures Program Listings Images, Arrays, and Matrices Multispectral satellite images Algebra of vectors and matrices Eigenvalues and eigenvectors Vector derivatives Finding minima and maxima Exercises Image Statistics Random variables Random vectors Parameter estimation Hypothesis testing and sample distribution functions Bayes' Theorem and classification Ordinary linear regression Exercises Transformations The discrete Fourier transform The discrete wavelet transform Principal components Maximum noise fraction Spatial correlation Exercises Convolutions, Filters, and Fields The Convolution Theorem Linear filters Wavelets and filter banks Gibbs-Markov random fields Exercises Image Enhancement and Correction Lookup tables and histogram functions High-pass spatial filtering Panchromatic sharpening Topographic correction Image-image registration Exercises Supervised Classification Maximum a posteriori probability Training data and separability Maximum likelihood classification Gaussian kernel classification Neural networks Postprocessing Evaluation and comparison of classification accuracy Hyperspectral analysis Exercises Unsupervised Classification Simple cost functions Algorithms that minimize the simple cost functions Fuzzy maximum likelihood estimation clustering Including spatial information A benchmark The Kohonen self-organizing map Exercises Change Detection Algebraic methods Principal components Postclassification comparison Multivariate alteration detection Decision thresholds and unsupervised classification of changes Radiometric normalization Exercises APPENDIX A: Mathematical Tools Cholesky Decomposition Least Squares Procedures APPENDIX B: Efficient Neural Network Training Algorithms The Hessian Matrix Scaled Conjugate Gradient Training Kalman Filter Training A Neural Network Classifier with Hybrid Training APPENDIX C: ENVI Extensions in IDL Installation Panchromatic Sharpening Topographic Modeling and Registration Supervised Classification Unsupervised Classification Change Detection Mathematical Notation References Index