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

Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL and Python, Third Edition introduces techniques used in the processing of remote sensing digital imagery. It emphasizes the development and implementation of statistically motivated, data-driven techniques. The author achieves this by tightly interweaving theory, algorithms, and computer codes. See What’s New in the Third Edition: Inclusion of extensive code in Python, with a cloud computing example New material on synthetic aperture radar (SAR) data analysis New illustrations in all chapters Extended theoretical development The material is self-contained and illustrated with many programming examples in IDL. The illustrations and applications in the text can be plugged in to the ENVI system in a completely transparent fashion and used immediately both for study and for processing of real imagery. The inclusion of Python-coded versions of the main image analysis algorithms discussed make it accessible to students and teachers without expensive ENVI/IDL licenses. Furthermore, Python platforms can take advantage of new cloud services that essentially provide unlimited computational power. The book covers both multispectral and polarimetric radar image analysis techniques in a way that makes both the differences and parallels clear and emphasizes the importance of choosing appropriate statistical methods. Each chapter concludes with exercises, some of which are small programming projects, intended to illustrate or justify the foregoing development, making this self-contained text ideal for self-study or classroom use.

Images, Arrays, and Matrices Multispectral satellite images Synthetic aperture radar images Algebra of vectors and matrices Eigenvalues and eigenvectors Singular value decomposition Finding minima and maxima Exercises Image Statistics Random variables Parameter estimation Multivariate distributions Bayes’ Theorem, likelihood and classification Hypothesis testing Ordinary linear regression Entropy and information Exercises Transformations The discrete Fourier transform The discrete wavelet transform Principal components Minimum noise fraction Spatial correlation Exercises Filters, Kernels and Fields The Convolution Theorem Linear filters Wavelets and filter banks Kernel methods Gibbs–Markov random fields Exercises Image Enhancement and Correction Lookup tables and histogram functions High-pass spatial filtering and feature extraction Panchromatic sharpening Radiometric correction of polarimetric SAR imagery Topographic correction Image–image registration Exercises Supervised Classification Part Maximizing the a posteriori probability Training data and separability Maximum likelihood classification Gaussian kernel classification Neural networks Support vector machines Exercises Supervised Classification Part Postprocessing Evaluation and comparison of classification accuracy Adaptive boosting Classification of polarimetric SAR imagery Hyperspectral image analysis Exercises Unsupervised Classification Simple cost functions Algorithms that minimize the simple cost functions Gaussian mixture clustering Including spatial information A benchmark The Kohonen self-organizing map Image segmentation Exercises Change Detection Algebraic methods Postclassification comparison Principal components analysis (PCA) Multivariate alteration detection (MAD) Decision thresholds Unsupervised change classification Change detection with polarimetric SAR imagery Radiometric normalization of multispectral imagery Exercises A Mathematical Tools B Efficient Neural Network Training Algorithms C ENVI Extensions in IDL D Python Scripts Mathematical Notation References Index