book

Image Analysis, Classification and Change Detection in Remote Sensing, 4th Edition

Name: Image Analysis, Classification and Change Detection in Remote Sensing, 4th Edition
Author: Morton John Canty
ISBN: 9780429875342

by Morton John Canty

March 2019

Intermediate to advanced

530 pages

12h 13m

English

CRC Press

Read now

Unlock full access

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface to the First Edition
Preface to the Second Edition
Preface to the Third Edition
Preface to the Fourth Edition
Author Biography

1 Images, Arrays, and Matrices
1.1 Multispectral satellite images1.2 Synthetic aperture radar images1.3 Algebra of vectors and matrices1.3.1 Elementary properties1.3.2 Square matrices1.3.3 Singular matrices1.3.4 Symmetric, positive definite matrices1.3.5 Linear dependence and vector spaces1.4 Eigenvalues and eigenvectors1.5 Singular value decomposition1.6 Finding minima and maxima1.7 Exercises
2 Image Statistics
2.1 Random variables2.1.1 Discrete random variables2.1.2 Continuous random variables2.1.3 Random vectors2.1.4 The normal distribution2.1.5 The gamma distribution and its derivatives2.2 Parameter estimation2.2.1 Random samples2.2.2 Sample distributions and interval estimators2.3 Multivariate distributions2.3.1 Vector sample functions and the data matrix2.3.2 Provisional means
2.3.3 Real and complex multivariate sample distributions
2.4 Bayes’ Theorem, likelihood and classification2.5 Hypothesis testing2.6 Ordinary linear regression2.6.1 One independent variable2.6.2 Coefficient of determination (R2)2.6.3 More than one independent variable2.6.4 Regularization, duality and the Gram matrix2.7 Entropy and information2.7.1 Kullback–Leibler divergence2.7.2 Mutual information2.8 Exercises
3 Transformations
3.1 The discrete Fourier transform3.2 The discrete wavelet transform3.2.1 Haar wavelets3.2.2 Image compression3.2.3 Multiresolution analysis
3.3 Principal components
3.3.1 Principal components on the GEE3.3.2 Image compression and reconstruction3.3.3 Primal solution3.3.4 Dual solution3.4 Minimum noise fraction3.4.1 Additive noise3.4.2 Minimum noise fraction via PCA3.5 Spatial correlation3.5.1 Maximum autocorrelation factor3.5.2 Noise estimation3.6 Exercises
4 Filters, Kernels, and Fields
4.1 The Convolution Theorem4.2 Linear filters4.3 Wavelets and filter banks4.3.1 One-dimensional arrays4.3.2 Two-dimensional arrays4.4 Kernel methods4.4.1 Valid kernels4.4.2 Kernel PCA4.5 Gibbs–Markov random fields4.6 Exercises
5 Image Enhancement and Correction
5.1 Lookup tables and histogram functions5.2 High-pass spatial filtering and feature extraction5.2.1 Sobel filter5.2.2 Laplacian-of-Gaussian filter5.2.3 OpenCV and GEE algorithms5.2.4 Invariant moments5.3 Panchromatic sharpening5.3.1 HSV fusion5.3.2 Brovey fusion5.3.3 PCA fusion5.3.4 DWT fusion5.3.5 À trous fusion5.3.6 A quality index5.4 Radiometric correction of polarimetric SAR imagery5.4.1 Speckle statistics5.4.2 Multi-look data
5.4.3 Speckle filtering
5.5 Topographic correction5.5.1 Rotation, scaling and translation5.5.2 Imaging transformations5.5.3 Camera models and RFM approximations5.5.4 Stereo imaging and digital elevation models5.5.5 Slope and aspect5.5.6 Illumination correction5.6 Image–image registration5.6.1 Frequency domain registration5.6.2 Feature matching5.6.3 Re-sampling with ground control points5.7 Exercises
6 Supervised Classification Part 1
6.1 Maximizing the a posteriori probability6.2 Training data and separability6.3 Maximum likelihood classification6.3.1 Naive Bayes on the GEE6.3.2 Python scripts for supervised classification6.4 Gaussian kernel classification6.5 Neural networks6.5.1 The neural network classifier6.5.2 Cost functions6.5.3 Backpropagation
6.5.4 A deep learning network
6.5.5 Overfitting and generalization6.6 Support vector machines6.6.1 Linearly separable classes6.6.2 Overlapping classes6.6.3 Solution with sequential minimal optimization6.6.4 Multiclass SVMs6.6.5 Kernel substitution6.7 Exercises
7 Supervised Classification Part 2
7.1 Postprocessing7.1.1 Majority filtering7.1.2 Probabilistic label relaxation7.2 Evaluation and comparison of classification accuracy7.2.1 Accuracy assessment7.2.2 Accuracy assessment on the GEE7.2.3 Cross-validation on parallel architectures7.2.4 Model comparison7.3 Adaptive boosting7.4 Classification of polarimetric SAR imagery7.5 Hyperspectral image analysis7.5.1 Spectral mixture modeling7.5.2 Unconstrained linear unmixing7.5.3 Intrinsic end-members and pixel purity7.5.4 Anomaly detection: The RX algorithm7.5.5 Anomaly detection: The kernel RX algorithm7.6 Exercises
8 Unsupervised Classification
8.1 Simple cost functions8.2 Algorithms that minimize the simple cost functions8.2.1 K-means clustering8.2.2 Kernel K-means clustering8.2.3 Extended K-means clustering8.2.4 Agglomerative hierarchical clustering8.2.5 Fuzzy K-means clustering8.3 Gaussian mixture clustering8.3.1 Expectation maximization8.3.2 Simulated annealing8.3.3 Partition density8.3.4 Implementation notes8.4 Including spatial information8.4.1 Multiresolution clustering8.4.2 Spatial clustering8.5 A benchmark8.6 The Kohonen self-organizing map8.7 Image segmentation and the mean shift8.8 Exercises
9 Change Detection
9.1 Naive methods9.2 Principal components analysis (PCA)9.2.1 Iterated PCA9.2.2 Kernel PCA9.3 Multivariate alteration detection (MAD)9.3.1 Canonical correlation analysis (CCA)9.3.2 Orthogonality properties9.3.3 Iteratively re-weighted MAD9.3.4 Scale invariance9.3.5 Correlation with the original observations9.3.6 Regularization9.3.7 Postprocessing9.4 Unsupervised change classification9.5 iMAD on the Google Earth Engine9.6 Change detection with polarimetric SAR imagery9.6.1 Scalar imagery: the gamma distribution9.6.2 Polarimetric imagery: the complex Wishart distribution9.6.3 Python software9.6.4 SAR change detection on the Google Earth Engine9.7 Radiometric normalization of visual/infrared images9.7.1 Scatterplot matching9.7.2 Automatic radiometric normalization9.8 RESTful change detection on the GEE9.9 Exercises
A Mathematical Tools
A.1 Cholesky decompositionA.2 Vector and inner product spacesA.3 Complex numbers, vectors and matricesA.4 Least squares proceduresA.4.1 Recursive linear regressionA.4.2 Orthogonal linear regressionA.5 Proof of Theorem 7.1
B Efficient Neural Network Training Algorithms
B.1 The Hessian matrixB.1.1 The R-operatorB.1.2 Calculating the HessianB.2 Scaled conjugate gradient trainingB.2.1 Conjugate directionsB.2.2 Minimizing a quadratic functionB.2.3 The algorithmB.3 Extended Kalman filter trainingB.3.1 LinearizationB.3.2 The algorithm
C Software
C.1 InstallationC.2 Command line utilitiesC.2.1 gdalC.2.2 earthengineC.2.3 ipclusterC.3 Source codeC.4 Python scriptsC.4.1 adaboost.pyC.4.2 atwt.pyC.4.3 c_corr.pyC.4.4 classify.pyC.4.5 crossvalidate.pyC.4.6 ct.pyC.4.7 dispms.pyC.4.8 dwt.pyC.4.9 eeMad.pyC.4.10 eeSar_seq.pyC.4.11 eeWishart.pyC.4.12 ekmeans.pyC.4.13 em.pyC.4.14 enlml.pyC.4.15 gamma_filter.pyC.4.16 hcl.pyC.4.17 iMad.pyC.4.18 iMadmap.pyC.4.19 kkmeans.pyC.4.20 kmeans.pyC.4.21 kpca.pyC.4.22 krx.pyC.4.23 mcnemar.pyC.4.24 meanshift.pyC.4.25 mmse_filter.pyC.4.26 mnf.pyC.4.27 pca.pyC.4.28 plr.pyC.4.29 radcal.pyC.4.30 readshp.pyC.4.31 registerms.pyC.4.32 registersar.pyC.4.33 rx.pyC.4.34 sar_jseq.pyC.4.35 scatterplot.pyC.4.36 som.pyC.4.37 subset.pyC.5 JavaScript on the GEE Code EditorC.5.1 imad_runC.5.2 omnibus_runC.5.3 omnibus_viewC.5.4 imadC.5.5 omnibusC.5.6 utilities
Mathematical Notation
References
Index

Content preview from Image Analysis, Classification and Change Detection in Remote Sensing, 4th Edition

The output is the same as in Section 1.3.4 apart from small rounding errors:

[[ 407.13229638 442.18038333 -78.32374081]

[ 442.18038333 493.57036037 -120.6419761 ]

[ -78.32374081 -120.6419761 438.95704379]]

2.3.3 Real and complex multivariate sample distributions

For the purposes of interval estimation and hypothesis testing, and also for image classification and change detection, we require not only sample vector estimators, but also their distributions. We concluded, from Theorem 2.3 in Section 2.1.4, that the mean of m normally distributed samples $eq247.jpg$ ,

$eq248.jpg$

is normally distributed with mean μ and variance σ²/m. Similarly, according to Theorem 2.8, (m − 1) S/σ²

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Image Analysis, Classification and Change Detection in Remote Sensing, 3rd Edition

Publisher Resources

ISBN: 9780429875342

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Image Analysis, Classification and Change Detection in Remote Sensing, 4th Edition

by Morton John Canty

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.