Muutke küpsiste eelistusi

Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for Python, Fourth Edition 4th edition [Kõva köide]

(Juelich Research Center, Germany)
  • Formaat: Hardback, 532 pages, kõrgus x laius: 234x156 mm, kaal: 1224 g, 39 Tables, black and white; 153 Illustrations, color
  • Ilmumisaeg: 20-Mar-2019
  • Kirjastus: CRC Press
  • ISBN-10: 1138613223
  • ISBN-13: 9781138613225
Teised raamatud teemal:
  • Kõva köide
  • Hind: 205,75 €*
  • * saadame teile pakkumise kasutatud raamatule, mille hind võib erineda kodulehel olevast hinnast
  • See raamat on trükist otsas, kuid me saadame teile pakkumise kasutatud raamatule.
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Lisa soovinimekirja
Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for Python, Fourth Edition 4th editionSuurem pilt
  • Formaat: Hardback, 532 pages, kõrgus x laius: 234x156 mm, kaal: 1224 g, 39 Tables, black and white; 153 Illustrations, color
  • Ilmumisaeg: 20-Mar-2019
  • Kirjastus: CRC Press
  • ISBN-10: 1138613223
  • ISBN-13: 9781138613225
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781138613225.html
Märksõnad:
Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for Python, Fourth Edition, is focused on the development and implementation of statistically motivated, data-driven techniques for digital image analysis of remotely sensed imagery and it features a tight interweaving of statistical and machine learning theory of algorithms with computer codes. It develops statistical methods for the analysis of optical/infrared and synthetic aperture radar (SAR) imagery, including wavelet transformations, kernel methods for nonlinear classification, as well as an introduction to deep learning in the context of feed forward neural networks.

New in the Fourth Edition:











An in-depth treatment of a recent sequential change detection algorithm for polarimetric SAR image time series.





The accompanying software consists of Python (open source) versions of all of the main image analysis algorithms.





Presents easy, platform-independent software installation methods (Docker containerization).





Utilizes freely accessible imagery via the Google Earth Engine and provides many examples of cloud programming (Google Earth Engine API).





Examines deep learning examples including TensorFlow and a sound introduction to neural networks,

Based on the success and the reputation of the previous editions and compared to other textbooks in the market, Professor Cantys fourth edition differs in the depth and sophistication of the material treated as well as in its consistent use of computer codes to illustrate the methods and algorithms discussed. It is self-contained and illustrated with many programming examples, all of which can be conveniently run in a web browser. Each chapter concludes with exercises complementing or extending the material in the text.

Arvustused

"The book presents a comprehensive exposition of the pixel based image analysis tools needed in a variety of remote sensing applications. It is the fourth edition of a book that first appeared in 2007. This rather rapid transition from one edition to the next is propelled by a parallel development in image analysis theory, in remote sensing platforms and advances in open source tools...The author has managed to encompass the relevant parts of this development in the present edition."

~Knut Conradsen, Technical University of Denmark

Preface to the First Edition xiii
Preface to the Second Edition xv
Preface to the Third Edition xvii
Preface to the Fourth Edition xx
Author Biography xxi
1 Images, Arrays, and Matrices
1(30)
1.1 Multispectral satellite images
4(3)
1.2 Synthetic aperture radar images
7(3)
1.3 Algebra of vectors and matrices
10(7)
1.3.1 Elementary properties
11(2)
1.3.2 Square matrices
13(2)
1.3.3 Singular matrices
15(1)
1.3.4 Symmetric, positive definite matrices
15(1)
1.3.5 Linear dependence and vector spaces
16(1)
1.4 Eigenvalues and eigenvectors
17(2)
1.5 Singular value decomposition
19(2)
1.6 Finding minima and maxima
21(6)
1.7 Exercises
27(4)
2 Image Statistics
31(52)
2.1 Random variables
31(13)
2.1.1 Discrete random variables
32(1)
2.1.2 Continuous random variables
33(3)
2.1.3 Random vectors
36(3)
2.1.4 The normal distribution
39(2)
2.1.5 The gamma distribution and its derivatives
41(3)
2.2 Parameter estimation
44(6)
2.2.1 Random samples
44(3)
2.2.2 Sample distributions and interval estimators
47(3)
2.3 Multivariate distributions
50(7)
2.3.1 Vector sample functions and the data matrix
51(2)
2.3.2 Provisional means
53(2)
2.3.3 Real and complex multivariate sample distributions
55(2)
2.4 Bayes' Theorem, likelihood and classification
57(3)
2.5 Hypothesis testing
60(5)
2.6 Ordinary linear regression
65(8)
2.6.1 One independent variable
65(2)
2.6.2 Coefficient of determination (R2)
67(1)
2.6.3 More than one independent variable
68(4)
2.6.4 Regularization, duality and the Gram matrix
72(1)
2.7 Entropy and information
73(4)
2.7.1 Kullback-Leibler divergence
75(1)
2.7.2 Mutual information
76(1)
2.8 Exercises
77(6)
3 Transformations
83(44)
3.1 The discrete Fourier transform
83(5)
3.2 The discrete wavelet transform
88(15)
3.2.1 Haar wavelets
89(4)
3.2.2 Image compression
93(3)
3.2.3 Multiresolution analysis
96(7)
3.3 Principal components
103(9)
3.3.1 Principal components on the GEE
105(2)
3.3.2 Image compression and reconstruction
107(4)
3.3.3 Primal solution
111(1)
3.3.4 Dual solution
111(1)
3.4 Minimum noise fraction
112(5)
3.4.1 Additive noise
113(3)
3.4.2 Minimum noise fraction via PCA
116(1)
3.5 Spatial correlation
117(6)
3.5.1 Maximum autocorrelation factor
117(2)
3.5.2 Noise estimation
119(4)
3.6 Exercises
123(4)
4 Filters, Kernels, and Fields
127(32)
4.1 The Convolution Theorem
127(5)
4.2 Linear filters
132(3)
4.3 Wavelets and filter banks
135(9)
4.3.1 One-dimensional arrays
136(5)
4.3.2 Two-dimensional arrays
141(3)
4.4 Kernel methods
144(8)
4.4.1 Valid kernels
144(5)
4.4.2 Kernel PCA
149(3)
4.5 Gibbs-Markov random fields
152(4)
4.6 Exercises
156(3)
5 Image Enhancement and Correction
159(72)
5.1 Lookup tables and histogram functions
159(2)
5.2 High-pass spatial filtering and feature extraction
161(16)
5.2.1 Sobel filter
161(3)
5.2.2 Laplacian-of-Gaussian filter
164(2)
5.2.3 OpenCV and GEE algorithms
166(5)
5.2.4 Invariant moments
171(6)
5.3 Panchromatic sharpening
177(8)
5.3.1 HSV fusion
178(1)
5.3.2 Brovey fusion
179(1)
5.3.3 PCA fusion
179(1)
5.3.4 DWT fusion
180(1)
5.3.5 A trous fusion
181(3)
5.3.6 A quality index
184(1)
5.4 Radiometric correction of polarimetric SAR imagery
185(15)
5.4.1 Speckle statistics
185(3)
5.4.2 Multi-look data
188(5)
5.4.3 Speckle filtering
193(7)
5.5 Topographic correction
200(16)
5.5.1 Rotation, scaling and translation
201(1)
5.5.2 Imaging transformations
202(1)
5.5.3 Camera models and RFM approximations
203(2)
5.5.4 Stereo imaging and digital elevation models
205(5)
5.5.5 Slope and aspect
210(1)
5.5.6 Illumination correction
211(5)
5.6 Image--image registration
216(9)
5.6.1 Frequency domain registration
217(2)
5.6.2 Feature matching
219(4)
5.6.3 Re-sampling with ground control points
223(2)
5.7 Exercises
225(6)
6 Supervised Classification Part 1
231(58)
6.1 Maximizing the a posteriori probability
233(1)
6.2 Training data and separability
234(5)
6.3 Maximum likelihood classification
239(6)
6.3.1 Naive Bayes on the GEE
240(1)
6.3.2 Python scripts for supervised classification
241(4)
6.4 Gaussian kernel classification
245(3)
6.5 Neural networks
248(22)
6.5.1 The neural network classifier
253(3)
6.5.2 Cost functions
256(2)
6.5.3 Backpropagation
258(6)
6.5.4 A deep learning network
264(4)
6.5.5 Overfitting and generalization
268(2)
6.6 Support vector machines
270(14)
6.6.1 Linearly separable classes
270(6)
6.6.2 Overlapping classes
276(2)
6.6.3 Solution with sequential minimal optimization
278(1)
6.6.4 Multiclass SVMs
279(1)
6.6.5 Kernel substitution
280(4)
6.7 Exercises
284(5)
7 Supervised Classification Part 2
289(40)
7.1 Postprocessing
289(4)
7.1.1 Majority filtering
290(1)
7.1.2 Probabilistic label relaxation
290(3)
7.2 Evaluation and comparison of classification accuracy
293(13)
7.2.1 Accuracy assessment
293(5)
7.2.2 Accuracy assessment on the GEE
298(1)
7.2.3 Cross-validation on parallel architectures
299(3)
7.2.4 Model comparison
302(4)
7.3 Adaptive boosting
306(6)
7.4 Classification of polarimetric SAR imagery
312(2)
7.5 Hyperspectral image analysis
314(12)
7.5.1 Spectral mixture modeling
314(3)
7.5.2 Unconstrained linear unmixing
317(1)
7.5.3 Intrinsic end-members and pixel purity
318(1)
7.5.4 Anomaly detection: The RX algorithm
319(3)
7.5.5 Anomaly detection: The kernel RX algorithm
322(4)
7.6 Exercises
326(3)
8 Unsupervised Classification
329(46)
8.1 Simple cost functions
330(2)
8.2 Algorithms that minimize the simple cost functions
332(17)
8.2.1 K-means clustering
333(5)
8.2.2 Kernel K-means clustering
338(3)
8.2.3 Extended K-means clustering
341(3)
8.2.4 Agglomerative hierarchical clustering
344(3)
8.2.5 Fuzzy K-means clustering
347(2)
8.3 Gaussian mixture clustering
349(5)
8.3.1 Expectation maximization
350(3)
8.3.2 Simulated annealing
353(1)
8.3.3 Partition density
353(1)
8.3.4 Implementation notes
354(1)
8.4 Including spatial information
354(6)
8.4.1 Multiresolution clustering
354(3)
8.4.2 Spatial clustering
357(3)
8.5 A benchmark
360(2)
8.6 The Kohonen self-organizing map
362(4)
8.7 Image segmentation and the mean shift
366(2)
8.8 Exercises
368(7)
9 Change Detection
375(52)
9.1 Naive methods
376(2)
9.2 Principal components analysis (PCA)
378(6)
9.2.1 Iterated PCA
380(2)
9.2.2 Kernel PCA
382(2)
9.3 Multivariate alteration detection (MAD)
384(13)
9.3.1 Canonical correlation analysis (CCA)
385(3)
9.3.2 Orthogonality properties
388(1)
9.3.3 Iteratively re-weighted MAD
389(2)
9.3.4 Scale invariance
391(1)
9.3.5 Correlation with the original observations
392(2)
9.3.6 Regularization
394(2)
9.3.7 Postprocessing
396(1)
9.4 Unsupervised change classification
397(2)
9.5 iMAD on the Google Earth Engine
399(2)
9.6 Change detection with polarimetric SAR imagery
401(14)
9.6.1 Scalar imagery: the gamma distribution
402(3)
9.6.2 Polarimetric imagery: the complex Wishart distribution
405(4)
9.6.3 Python software
409(4)
9.6.4 SAR change detection on the Google Earth Engine
413(2)
9.7 Radiometric normalization of visual/infrared images
415(7)
9.7.1 Scatterplot matching
416(3)
9.7.2 Automatic radiometric normalization
419(3)
9.8 RESTful change detection on the GEE
422(1)
9.9 Exercises
422(5)
A Mathematical Tools
427(14)
A.1 Cholesky decomposition
427(2)
A.2 Vector and inner product spaces
429(1)
A.3 Complex numbers, vectors and matrices
430(2)
A.4 Least squares procedures
432(5)
A.4.1 Recursive linear regression
432(2)
A.4.2 Orthogonal linear regression
434(3)
A.5 Proof of Theorem 7.1
437(4)
B Efficient Neural Network Training Algorithms
441(22)
B.1 The Hessian matrix
441(6)
B.1.1 The R-operator
442(3)
B.1.2 Calculating the Hessian
445(2)
B.2 Scaled conjugate gradient training
447(8)
B.2.1 Conjugate directions
447(2)
B.2.2 Minimizing a quadratic function
449(2)
B.2.3 The algorithm
451(4)
B.3 Extended Kalman filter training
455(8)
B.3.1 Linearization
456(1)
B.3.2 The algorithm
457(6)
C Software
463(24)
C.1 Installation
463(1)
C.2 Command line utilities
464(1)
C.2.1 gdal
464(1)
C.2.2 earthengine
464(1)
C.2.3 ipcluster
465(1)
C.3 Source code
465(1)
C.4 Python scripts
465(19)
C.4.1 adaboost.py
466(1)
C.4.2 atwt.py
466(1)
C.4.3 c.corr.py
467(1)
C.4.4 classify.py
467(1)
C.4.5 crossvalidate.py
468(1)
C.4.6 ct.py
469(1)
C.4.7 dispms.py
469(1)
C.4.8 dwt.py
470(1)
C.4.9 eeMad.py
470(1)
C.4.10 eeSar_seq.py
471(1)
C.4.11 eeWishart.py
471(1)
C.4.12 ekmeans.py
472(1)
C.4.13 em.py
472(1)
C.4.14 enlml.py
473(1)
C.4.15 gammajilter.py
473(1)
C.4.16 hcl.py
474(1)
C.4.17 iMad.py
474(1)
C.4.18 iMadmap.py
475(1)
C.4.19 kkmeans.py
476(1)
C.4.20 kmeans.py
476(1)
C.4.21 kpca.py
476(1)
C.4.22 krx.py
477(1)
C.4.23 mcnemar.py
477(1)
C.4.24 meanshift.py
477(1)
C.4.25 mmseJilter.py
478(1)
C.4.26 mnf.py
478(1)
C.4.27 pca.py
478(1)
C.4.28 plr.py
479(1)
C.4.29 radcal.py
479(1)
C.4.30 readshp.py
480(1)
C.4.31 registerms.py
480(1)
C.4.32 registersar.py
481(1)
C.4.33 rx.py
482(1)
C.4.34 sar_seq.py
482(1)
C.4.35 scatterplot.py
483(1)
C.4.36 som.py
483(1)
C.4.37 subset.py
484(1)
C.5 JavaScript on the GEE Code Editor
484(3)
C.5.1 imad-run
484(1)
C.5.2 omnibus_run
484(1)
C.5.3 omnibus_view
485(1)
C.5.4 imad
485(1)
C.5.5 Omnibus
485(1)
C.5.6 Utilities
485(2)
Mathematical Notation 487(2)
References 489(12)
Index 501
Morton John Canty is a senior research scientist in the Institute for Bio- and Geosciences at the Juelich Research Center in Germany, now semi-retired. He received his PhD in Nuclear Physics in 1969 at the University of Manitoba, Canada and, after post-doctoral positions in Bonn, Groningen and Marburg, began work in Juelich in 1979. There, his principal interests have been the development of statistical and gametheoretical models for the verification of international treaties and the use of remote sensing data for monitoring global treaty compliance. He has served on numerous advisory bodies to the German federal government and to the International Atomic Energy Agency in Vienna and was a coordinator within the European Network of Excellence on Global Monitoring for Security and Stability, funded by the European Commission. Morton Canty is the author of three monographs in the German language: on the subject of non-linear dynamics (Chaos und Systeme, Vieweg, 1995), neural networks for classification of remote sensing data (Fernerkundung mit neuronalen Netzen, Expert, 1999) and algorithmic game theory (Konfliktl¨osungen mit Mathematica, Springer 2000). The latter text has appeared in a revised English version (Resolving Conflicts withMathematica, Academic Press, 2003). He is co-author of a monograph on mathematical methods for treaty verification (Compliance Quantified, Cambridge University Press, 1996). He has published many papers on the subjects of experimental nuclear physics, nuclear safeguards, applied game theory and remote sensing. He has lectured on nonlinear dynamical growth models and remote sensing digital image analysis to students at both the graduate and undergraduate level at Universities in Bonn, Berlin, Freiberg/Saxony and Rome.