Average Reviews:
(More customer reviews)Don't you just hate it when such a potentially helpful book exists and you can't at least see the table of contents? Well, I provide that below. As for details, I find it a very helpful and very heavily mathematical book. You won't just see the same old stuff on convolution kernels, histogram equalization and matching etc. rehashed with very few technical details and lots of pretty color plates. Be prepared to look at theorems and a few derivations, but the book is practical too. I'd highly recommend it to the professional who is ready for some more advanced material. As for IDL/ENVI, the algorithms are described well enough you don't have to use that as an implementation language. If you don't know ENVI/IDL this is a pretty good tutorial without trying nearly as hard as programming books on that specific subject.
Preface to the Second Edition xi
Preface to the First Edition xiii
1 Images, Arrays, and Matrices 1
1.1 Multispectral Satellite Images 2
1.2 Algebra of Vectors and Matrices 5
1.2.1 Elementary Properties 6
1.2.2 Square Matrices 8
1.2.3 Singular Matrices 10
1.2.4 Symmetric, Positive Definite Matrices 11
1.2.5 Linear Dependence and Vector Spaces 12
1.3 Eigenvalues and Eigenvectors 13
1.4 Singular Value Decomposition 16
1.5 Vector Derivatives 18
1.6 Finding Minima and Maxima 19
1.7 Exercises 25
2 Image Statistics 27
2.1 Random Variables 27
2.1.1 Discrete Random Variables 28
2.1.2 Continuous Random Variables 29
2.1.3 Normal Distribution 32
2.2 Random Vectors 34
2.3 Parameter Estimation 39
2.3.1 Sampling a Distribution 39
2.3.2 Interval Estimation 42
2.3.3 Provisional Means 43
2.4 Hypothesis Testing and Sample Distribution Functions 44
2.4.1 Chi-Square Distribution 48
2.4.2 Student-t Distribution 49
2.4.3 F-Distribution 50
2.5 Conditional Probabilities, Bayes' Theorem, and Classification 51
2.6 Ordinary Linear Regression 55
2.6.1 One Independent Variable 55
2.6.2 More Than One Independent Variable 57
2.6.3 Regularization, Duality, and the Gram Matrix 60
2.7 Entropy and Information 62
2.7.1 Kullback-Leibler Divergence 64
2.7.2 Mutual Information 64
2.8 Exercises 65
3 Transformations 69
3.1 Discrete Fourier Transform 69
3.2 Discrete Wavelet Transform 73
3.2.1 Haar Wavelets 75
3.2.2 Image Compression 79
3.2.3 Multiresolution Analysis 82
3.2.3.1 Dilation Equation and Refinement Coefficients 83
3.2.3.2 Cascade Algorithm 84
3.2.3.3 Mother Wavelet 85
3.2.3.4 Daubechies D4 Scaling Function 87
3.3 PrincipalComponents 89
3.3.1 Primal Solution 91
3.3.2 Dual Solution 91
3.4 Minimum Noise Fraction 93
3.4.1 Additive Noise 93
3.4.2 Minimum Noise Fraction Transformation in ENVI 96
3.5 Spatial Correlation 98
3.5.1 Maximum Autocorrelation Factor 98
3.5.2 Noise Estimation 101
3.6 Exercises 103
4 Filters, Kernels, and Fields 107
4.1 Convolution Theorem 107
4.2 Linear Filters 111
4.3 Wavelets and Filter Banks 113
4.3.1 One-Dimensional Arrays 115
4.3.2 Two-Dimensional Arrays 120
4.4 Kernel Methods 122
4.4.1 Valid Kernels 124
4.4.2 Kernel PCA 127
4.5 Gibbs-Markov Random Fields 130
4.6 Exercises 135
5 Image Enhancement and Correction 139
5.1 Lookup Tables and Histogram Functions 139
5.2 Filtering and Feature Extraction 141
5.2.1 Edge Detection 141
5.2.2 Invariant Moments 145
5.3 Panchromatic Sharpening 150
5.3.1 HSV Fusion 151
5.3.2 Brovey Fusion 152
5.3.3 PCA Fusion 153
5.3.4 DWT Fusion 154
5.3.5 Á Trous Fusion 155
5.3.6 Quality Index 157
5.4 Topographic Correction 159
5.4.1 Rotation, Scaling, and Translation 159
5.4.2 Imaging Transformations 160
5.4.3 Camera Models and RFM Approximations 161
5.4.4 Stereo Imaging and Digital Elevation Models 163
5.4.5 Slope and Aspect 167
5.4.6 Illumination Correction 170
5.5 Image-Image Registration 175
5.5.1 Frequency-Domain Registration 176
5.5.2 Feature Matching 177
5.5.2.1 High-Pass Filtering 178
5.5.2.2 Closed Contours 179
5.5.2.3 Chain Codes and Moments 179
5.5.2.4 Contour Matching 180
5.5.2.5 Consistency Check 180
5.5.2.6 Implementation in IDL 181
5.5.3 Resampling and Warping 182
5.6 Exercises 183
6 Supervised Classification: Part 1 187
6.1 Maximum a Posteriori Probability 188
6.2 Training Data and Separability 189
6.3 Maximum Likelihood Classification 193
6.3.1 ENVI's Maximum Likelihood Classifier 195
6.3.2 Modified Maximum Likelihood Classifier 196
6.4 Gaussian Kernel Classification 198
6.5 Neural Networks 202
6.5.1 Neural Network Classifier 207
6.5.2 Cost Functions 209
6.5.3 Backpropagation 212
6.5.4 Overfitting and Generalization 216
6.6 Support Vector Machines 219
6.6.1 Linearly Separable Classes 220
6.6.1.1 Primal Formulation 221
6.6.1.2 Dual Formulation 222
6.6.1.3 Quadratic Programming and Support Vectors 224
6.6.2 Overlapping Classes 225
6.6.3 Solution with Sequential Minimal Optimization 227
6.6.4 Multiclass SVMs 228
6.6.5 Kernel Substitution 230
6.6.6 Modified SVM Classifier 231
6.7 Exercises 232
7 Supervised Classification: Part 2 237
7.1 Postprocessing 237
7.1.1 Majority Filtering 238
7.1.2 Probabilistic Label Relaxation 238
7.2 Evaluation and Comparison of Classification Accuracy 240
7.2.1 Accuracy Assessment 241
7.2.2 Model Comparison 246
7.3 Adaptive Boosting 250
7.4 Hyperspectral Analysis 257
7.4.1 Spectral Mixture Modeling 259
7.4.2 Unconstrained Linear Unmixing 261
7.4.3 Intrinsic End-Members and Pixel Purity 261
7.5 Exercises 263
8 Unsupervised Classification 267
8.1 Simple Cost Functions 268
8.2 Algorithms That Minimize the Simple Cost Functions 270
8.2.1 K-Means Clustering 271
8.2.2 Kernel K-Means Clustering 271
8.2.3 Extended K-Means Clustering 273
8.2.4 Agglomerative Hierarchical Clustering 278
8.2.5 Fuzzy K-Means Clustering 280
8.3 Gaussian Mixture Clustering 282
8.3.1 Expectation Maximization 283
8.3.2 Simulated Annealing 286
8.3.3 Partition Density 286
8.3.4 Implementation Notes 287
8.4 Including Spatial Information 289
8.4.1 Multiresolution Clustering 289
8.4.2 Spatial Clustering 289
8.5 Benchmark 292
8.6 Kohonen Self-Organizing Map 295
8.7 Image Segmentation 297
8.7.1 Segmenting a Classified Image 299
8.7.2 Object-Based Classification 300
8.7.3 Mean Shift 303
8.8 Exercises 304
9 Change Detection 311
9.1 Algebraic Methods 311
9.2 Postclassification Comparison 313
9.3 Principal Components Analysis 313
9.3.1 Iterated PCA 313
9.3.2 Kernel PCA 314
9.4 Multivariate Alteration Detection 319
9.4.1 Canonical Correlation Analysis 320
9.4.2 Orthogonality Properties 322
9.4.3 Scale Invariance 324
9.4.4 Iteratively Reweighted MAD 325
9.4.5 Correlation with the Original Observations 327
9.4.6 Regularization 328
9.4.7 Postprocessing 330
9.5 Decision Thresholds and Unsupervised Classification of Changes 331
9.6 Radiometric Normalization 336
9.7 Exercises 338
Appendix A Mathematical Tools 343
A.1 Cholesky Decomposition 343
A.2 Vector and Inner Product Spaces 345
A.3 Least Squares Procedures 347
A.3.1 Recursive Linear Regression 347
A.3.2 Orthogonal Linear Regression 350
Appendix B Efficient Neural Network Training Algorithms 355
B.1 Hessian Matrix 355
B.1.1 R-Operator 356
B.l.1.1 Determination of Rv{n} 358
B.l.1.2 Determination of R'{'0} 359
B.l.1.3 Determination of R'{'h] 359
B.1.2 Calculating the Hessian 360
B.2 Scaled Conjugate Gradient Training 360
B.2.1 Conjugate Directions 362
B.2.2 Minimizing a Quadratic Function 363
B.2.3 Algorithm 366
B.3 Kalman Filter Training 368
B.3.1 Linearization 371
B.3.2 Algorithm 372
B.4 A Neural Network Classifier with Hybrid Training 379
Appendix C ENVI Extensions in IDL 381
C.1 Installation 381
C.2 Extensions 382
C.2.1 Kernel Principal Components Analysis 384
C.2.2 Discrete Wavelet Transform Fusion 386
C.2.3 Á Trous Wavelet Transform Fusion 388
C.2.4 Quality Index 389
C.2.5 Calculating Heights of Man-Made Structures in High-Resolution Imagery 390
C.2.6 Illumination Correction 392
C.2.7 Image Registration 393
C.2.8 Maximum Likelihood Classification 394
C.2.9 Gaussian Kernel Classification 396
C.2.10 Neural Network Classification 397
C.2.11 Support Vector Machine Classification 399
C.2.12 Probabilistic Label Relaxation 399
C.2.13 Classifier Evaluation and Comparison 401
C.2.14 Adaptive Boosting a Neural Network Classifier 402
C.2.15 Kernel K-Means Clustering 404
C.2.16 Agglomerative Hierarchical Clustering 405
C.2.17 Fuzzy K-Means Clustering 406
C.2.18 Gaussian Mixture Clustering 407
C.2.19 Kohonen Self-Organizing Map 409
C.2.20 Classified Image Segmentation 410
C.2.21 Mean Shift Segmentation 411
C.2.22 Multivariate Alteration Detection 412
C.2.23 Viewing Changes 415
C.2.24 Radiometric Normalization 416
Appendix D Mathematical Notation 419
References 421
Index 429
Click Here to see more reviews about: Image Analysis, Classification, and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL, Second Edition
Demonstrating the breadth and depth of growth in the field since the publication of the popular first edition, Image Analysis, Classification and Change Detection in Remote Sensing, with Algorithms for ENVI/IDL, Second Edition has been updated and expanded to keep pace with the latest versions of the ENVI software environment. Effectively interweaving theory, algorithms, and computer codes, the text supplies an accessible introduction to the techniques used in the processing of remotely sensedimagery. This significantly expanded edition presents numerous image analysis examples and algorithms, all illustrated in the array-oriented language IDL-allowing readers to plug the illustrations and applications covered in the text directly into the ENVI system-in a completely transparent fashion. Revised chapters on image arrays, linear algebra, and statistics convey the required foundation, while updated chapters detail kernel methods for principal component analysis, kernel-based clustering, and classification with support vector machines. Additions to thisedition include: An introduction to mutual information and entropy Algorithms and code for image segmentation In-depth treatment of ensemble classification (adaptive boosting )Improved IDL code for all ENVI extensions, with routines that can take advantage of the parallel computational power of modern graphics processorsCode that runs on all versions of the ENVI/IDL software environment from ENVI 4.1 up to the present-available on the author's websiteMany new end-of-chapter exercises and programming projects With its numerous programming examples in IDL and many applications supporting ENVI, such as data fusion, statistical change detection, clustering and supervised classification with neural networks-all available as downloadable source code-this self-contained text isidealfor classroom use or self study.
Get 10% OFF
No comments:
Post a Comment