Mathematical Models for Remote Sensing Image Processing : Models and Methods for the Analysis of 2D Satellite and Aerial Images.

By: Moser, GabrieleContributor(s): Zerubia, JosianeMaterial type: TextTextSeries: eBooks on DemandSignals and Communication Technology Ser: Publisher: Cham : Springer, 2017Copyright date: ©2018Description: 1 online resource (446 pages)Content type: text Media type: computer Carrier type: online resourceISBN: 9783319663302Genre/Form: Electronic books.Additional physical formats: Print version:: Mathematical Models for Remote Sensing Image Processing : Models and Methods for the Analysis of 2D Satellite and Aerial ImagesDDC classification: 620 LOC classification: TA1-2040Online resources: Click here to view this ebook.
Contents:
Intro -- Preface -- Contents -- 1 Mathematical Models and Methods for Remote Sensing Image Analysis: An Introduction -- 1.1 Introduction -- 1.2 Basics of Remote Sensing Imagery -- 1.2.1 The Notion of Remote Sensing Image -- 1.2.2 Platforms for Remote Sensing -- 1.2.3 Acquisition of Remote Sensing Images -- 1.2.4 The Notions of Resolution -- 1.3 Mathematical Modeling for Remote Sensing Image Analysis -- 1.3.1 General Comments -- 1.3.2 Mathematical Models for Image Data Representation -- 1.3.3 Probabilistic Modeling and Bayesian Methods to Learn from Image Data -- 1.3.4 Non-Bayesian Methods for Learning from Image Data -- 1.3.5 The Role of Optimization Methods -- 1.4 Structure and Organization of the Book -- References -- 2 Models for Hyperspectral Image Analysis: From Unmixing to Object-Based Classification -- 2.1 Introduction -- 2.2 Unmixing -- 2.2.1 Dimensionality Reduction -- 2.2.2 Endmember Extraction -- 2.2.3 Abundance Estimation -- 2.2.4 Experimental Validation -- 2.3 Classification -- 2.3.1 Supervised Pixelwise Classification -- 2.3.2 Spectral-Spatial Classification -- 2.3.3 Object-Based Classification with Binary Partition Trees -- 2.3.4 Experimental Results -- 2.4 Challenges -- References -- 3 Very High Spatial Resolution Optical Imagery: Tree-Based Methods and Multi-temporal Models for Mining and Analysis -- 3.1 Introduction -- 3.2 Interactive Image Information Mining Based on Hierarchical Data Representation Structure Coupling -- 3.2.1 Introduction -- 3.2.2 Image Content Organization -- 3.2.3 Hierarchical Image Representation Structures -- 3.2.4 Spatial Sampling -- 3.2.5 Efficient Classification by Tree Pruning -- 3.2.6 Experiments and Applications -- 3.3 Mutli-temporal and Multi-angular Optical Image Analysis -- 3.3.1 Introduction -- 3.3.2 Non-physical and Physical Quantities -- 3.3.3 Accounting for Angular Variability.
3.3.4 Experimental Results -- 3.4 Conclusions -- References -- 4 Very-High-Resolution and Interferometric SAR: Markovian and Patch-Based Non-local Mathematical Models -- 4.1 Principles of SAR Imagery -- 4.1.1 Principles of SAR Acquisition -- 4.1.2 From 2D to 4D SAR Imaging -- 4.1.3 Statistics of Speckle in SAR Imagery -- 4.2 Markovian Modeling and Its Applications -- 4.2.1 Markovian Modeling of Images -- 4.2.2 Inference in Markov Random Fields -- 4.2.3 Application to SAR Image Denoising: Joint Regularization and Fusion with Optical Data -- 4.2.4 Application to Phase Unwrapping of Multi-channel Interferometry -- 4.3 Patch-Based Models for SAR Imagery -- 4.3.1 From Local Neighborhoods to Patches -- 4.3.2 Patch-Based Selection for Estimation in Polarimetric or Interferometric SAR -- 4.4 Conclusion -- References -- 5 Polarimetric SAR Modelling: Mellin Kind Statistics and Time-Frequency Analysis -- 5.1 Introduction -- 5.2 Signal Modelling -- 5.3 The Product Model -- 5.4 Radar Polarimetry -- 5.5 Parameter Estimation -- 5.5.1 Covariance Estimation -- 5.5.2 Mellin Kind Statistics -- 5.5.3 Shape Parameter Estimation -- 5.5.4 Estimation of Texture Parameters -- 5.6 Image Classification -- 5.6.1 Supervised Classification -- 5.6.2 Unsupervised Segmentation -- 5.7 Coherent Time-Frequency Characterization of Complex Polarimetric Features -- 5.7.1 Coherent Time-Frequency Decomposition of Polarimetric SAR Images -- 5.7.2 Characterization of Natural Environments with Non-stationary Polarimetric TF SAR Responses -- 5.7.3 TF Polarimetric Characterization of Complex Scenes -- 5.8 Conclusion -- References -- 6 Remote Sensing Data Fusion: Guided Filter-Based Hyperspectral Pansharpening and Graph-Based Feature-Level Fusion -- 6.1 Introduction -- 6.2 Hyperspectral Image Pansharpening -- 6.2.1 Hybrid Method to Fuse Thermal Hyperspectral and Visible Color Images.
6.3 Graph-Based Feature Fusion Model for Multisource Data Classification -- 6.3.1 Graph Fusion of Hyperspectral and LiDAR Data -- 6.3.2 Local Graph Fusion Model for Fusion of Multisource Data -- 6.4 Discussion and Conclusions -- References -- 7 Remote Sensing Data Fusion: Markov Models and Mathematical Morphology for Multisensor, Multiresolution, and Multiscale Image Classification -- 7.1 Multisource Data Fusion for Image Classification -- 7.1.1 Multiscale Feature Extraction -- 7.1.2 Multisensor and Multiresolution Image Classification -- 7.2 Multilevel Feature Extraction Through Mathematical Morphology -- 7.2.1 Introduction to Mathematical Morphology -- 7.2.2 Theoretical Background -- 7.2.3 Multilevel Image Representation -- 7.2.4 Multi-channel and Multi-attribute Representations -- 7.2.5 Automatic Filter Parameter Selection -- 7.2.6 Experimental Study -- 7.3 Hierarchical Markov Models for Multisource Image Classification -- 7.3.1 Bayesian Classification -- 7.3.2 Multitemporal MPM Inference -- 7.3.3 Transition Probabilities -- 7.3.4 Pixelwise Class-Conditional PDFs -- 7.3.5 Experimental Study -- 7.4 Conclusions -- References -- 8 Change Detection in Multitemporal Images Through Single- and Multi-scale Approaches -- 8.1 Introduction -- 8.2 State of the Art -- 8.2.1 Change Detection in Multitemporal Spaceborne Images -- 8.2.2 SAR Change Detection -- 8.2.3 Change Detection Methods for VHR SAR Images -- 8.3 Experimental Results -- 8.3.1 Simulated Data -- 8.3.2 COSMO-SkyMed Images -- 8.4 Concluding Remarks -- References -- 9 Satellite Image Time Series: Mathematical Models for Data Mining and Missing Data Restoration -- 9.1 Introduction -- 9.2 Data Mining Methods for Spatiotemporal Pattern Extraction -- 9.2.1 Objectives and Originality of the Approach -- 9.2.2 Grouped Frequent Sequential Patterns -- 9.2.3 STL-Maps and NMI-Based Scoring of STL-Maps.
9.2.4 Discussion -- 9.3 Reconstruction Methods for Multispectral Images -- 9.3.1 Survey -- 9.3.2 Problem Formulation -- 9.3.3 Linear Contextual Prediction Method -- 9.3.4 Compressive Sensing Reconstruction Strategies -- 9.3.5 Illustration Examples -- 9.3.6 Discussion -- 9.4 Conclusion -- References -- 10 Advances in Kernel Machines for Image Classification and Biophysical Parameter Retrieval -- 10.1 Introduction -- 10.2 Introduction to Kernel Methods -- 10.2.1 Feature Maps and Kernels -- 10.2.2 Positive Definite Kernels and the Kernel Trick -- 10.2.3 Operations with Kernels -- 10.2.4 Kernels Functions -- 10.2.5 Kernel Combinations -- 10.2.6 A Note on the Kernel Metric -- 10.2.7 Support Vector Machine for Classification -- 10.2.8 Gaussian Processes for Regression -- 10.3 Multi-modal Data Classification -- 10.3.1 Multi-source Pixel Classification with Multiple Kernels -- 10.3.2 Making Image Representations More Similar with Manifold Alignment -- 10.3.3 New Challenges -- 10.4 Biophysical Parameter Estimation -- 10.4.1 Covariances in Gaussian Processes -- 10.4.2 Ranking Features Through the Automatic Relevance Determination (ARD) Covariance -- 10.4.3 Uncertainty Intervals -- 10.4.4 New Challenges with GPR -- 10.5 Conclusions -- References.
Tags from this library: No tags from this library for this title. Log in to add tags.

Intro -- Preface -- Contents -- 1 Mathematical Models and Methods for Remote Sensing Image Analysis: An Introduction -- 1.1 Introduction -- 1.2 Basics of Remote Sensing Imagery -- 1.2.1 The Notion of Remote Sensing Image -- 1.2.2 Platforms for Remote Sensing -- 1.2.3 Acquisition of Remote Sensing Images -- 1.2.4 The Notions of Resolution -- 1.3 Mathematical Modeling for Remote Sensing Image Analysis -- 1.3.1 General Comments -- 1.3.2 Mathematical Models for Image Data Representation -- 1.3.3 Probabilistic Modeling and Bayesian Methods to Learn from Image Data -- 1.3.4 Non-Bayesian Methods for Learning from Image Data -- 1.3.5 The Role of Optimization Methods -- 1.4 Structure and Organization of the Book -- References -- 2 Models for Hyperspectral Image Analysis: From Unmixing to Object-Based Classification -- 2.1 Introduction -- 2.2 Unmixing -- 2.2.1 Dimensionality Reduction -- 2.2.2 Endmember Extraction -- 2.2.3 Abundance Estimation -- 2.2.4 Experimental Validation -- 2.3 Classification -- 2.3.1 Supervised Pixelwise Classification -- 2.3.2 Spectral-Spatial Classification -- 2.3.3 Object-Based Classification with Binary Partition Trees -- 2.3.4 Experimental Results -- 2.4 Challenges -- References -- 3 Very High Spatial Resolution Optical Imagery: Tree-Based Methods and Multi-temporal Models for Mining and Analysis -- 3.1 Introduction -- 3.2 Interactive Image Information Mining Based on Hierarchical Data Representation Structure Coupling -- 3.2.1 Introduction -- 3.2.2 Image Content Organization -- 3.2.3 Hierarchical Image Representation Structures -- 3.2.4 Spatial Sampling -- 3.2.5 Efficient Classification by Tree Pruning -- 3.2.6 Experiments and Applications -- 3.3 Mutli-temporal and Multi-angular Optical Image Analysis -- 3.3.1 Introduction -- 3.3.2 Non-physical and Physical Quantities -- 3.3.3 Accounting for Angular Variability.

3.3.4 Experimental Results -- 3.4 Conclusions -- References -- 4 Very-High-Resolution and Interferometric SAR: Markovian and Patch-Based Non-local Mathematical Models -- 4.1 Principles of SAR Imagery -- 4.1.1 Principles of SAR Acquisition -- 4.1.2 From 2D to 4D SAR Imaging -- 4.1.3 Statistics of Speckle in SAR Imagery -- 4.2 Markovian Modeling and Its Applications -- 4.2.1 Markovian Modeling of Images -- 4.2.2 Inference in Markov Random Fields -- 4.2.3 Application to SAR Image Denoising: Joint Regularization and Fusion with Optical Data -- 4.2.4 Application to Phase Unwrapping of Multi-channel Interferometry -- 4.3 Patch-Based Models for SAR Imagery -- 4.3.1 From Local Neighborhoods to Patches -- 4.3.2 Patch-Based Selection for Estimation in Polarimetric or Interferometric SAR -- 4.4 Conclusion -- References -- 5 Polarimetric SAR Modelling: Mellin Kind Statistics and Time-Frequency Analysis -- 5.1 Introduction -- 5.2 Signal Modelling -- 5.3 The Product Model -- 5.4 Radar Polarimetry -- 5.5 Parameter Estimation -- 5.5.1 Covariance Estimation -- 5.5.2 Mellin Kind Statistics -- 5.5.3 Shape Parameter Estimation -- 5.5.4 Estimation of Texture Parameters -- 5.6 Image Classification -- 5.6.1 Supervised Classification -- 5.6.2 Unsupervised Segmentation -- 5.7 Coherent Time-Frequency Characterization of Complex Polarimetric Features -- 5.7.1 Coherent Time-Frequency Decomposition of Polarimetric SAR Images -- 5.7.2 Characterization of Natural Environments with Non-stationary Polarimetric TF SAR Responses -- 5.7.3 TF Polarimetric Characterization of Complex Scenes -- 5.8 Conclusion -- References -- 6 Remote Sensing Data Fusion: Guided Filter-Based Hyperspectral Pansharpening and Graph-Based Feature-Level Fusion -- 6.1 Introduction -- 6.2 Hyperspectral Image Pansharpening -- 6.2.1 Hybrid Method to Fuse Thermal Hyperspectral and Visible Color Images.

6.3 Graph-Based Feature Fusion Model for Multisource Data Classification -- 6.3.1 Graph Fusion of Hyperspectral and LiDAR Data -- 6.3.2 Local Graph Fusion Model for Fusion of Multisource Data -- 6.4 Discussion and Conclusions -- References -- 7 Remote Sensing Data Fusion: Markov Models and Mathematical Morphology for Multisensor, Multiresolution, and Multiscale Image Classification -- 7.1 Multisource Data Fusion for Image Classification -- 7.1.1 Multiscale Feature Extraction -- 7.1.2 Multisensor and Multiresolution Image Classification -- 7.2 Multilevel Feature Extraction Through Mathematical Morphology -- 7.2.1 Introduction to Mathematical Morphology -- 7.2.2 Theoretical Background -- 7.2.3 Multilevel Image Representation -- 7.2.4 Multi-channel and Multi-attribute Representations -- 7.2.5 Automatic Filter Parameter Selection -- 7.2.6 Experimental Study -- 7.3 Hierarchical Markov Models for Multisource Image Classification -- 7.3.1 Bayesian Classification -- 7.3.2 Multitemporal MPM Inference -- 7.3.3 Transition Probabilities -- 7.3.4 Pixelwise Class-Conditional PDFs -- 7.3.5 Experimental Study -- 7.4 Conclusions -- References -- 8 Change Detection in Multitemporal Images Through Single- and Multi-scale Approaches -- 8.1 Introduction -- 8.2 State of the Art -- 8.2.1 Change Detection in Multitemporal Spaceborne Images -- 8.2.2 SAR Change Detection -- 8.2.3 Change Detection Methods for VHR SAR Images -- 8.3 Experimental Results -- 8.3.1 Simulated Data -- 8.3.2 COSMO-SkyMed Images -- 8.4 Concluding Remarks -- References -- 9 Satellite Image Time Series: Mathematical Models for Data Mining and Missing Data Restoration -- 9.1 Introduction -- 9.2 Data Mining Methods for Spatiotemporal Pattern Extraction -- 9.2.1 Objectives and Originality of the Approach -- 9.2.2 Grouped Frequent Sequential Patterns -- 9.2.3 STL-Maps and NMI-Based Scoring of STL-Maps.

9.2.4 Discussion -- 9.3 Reconstruction Methods for Multispectral Images -- 9.3.1 Survey -- 9.3.2 Problem Formulation -- 9.3.3 Linear Contextual Prediction Method -- 9.3.4 Compressive Sensing Reconstruction Strategies -- 9.3.5 Illustration Examples -- 9.3.6 Discussion -- 9.4 Conclusion -- References -- 10 Advances in Kernel Machines for Image Classification and Biophysical Parameter Retrieval -- 10.1 Introduction -- 10.2 Introduction to Kernel Methods -- 10.2.1 Feature Maps and Kernels -- 10.2.2 Positive Definite Kernels and the Kernel Trick -- 10.2.3 Operations with Kernels -- 10.2.4 Kernels Functions -- 10.2.5 Kernel Combinations -- 10.2.6 A Note on the Kernel Metric -- 10.2.7 Support Vector Machine for Classification -- 10.2.8 Gaussian Processes for Regression -- 10.3 Multi-modal Data Classification -- 10.3.1 Multi-source Pixel Classification with Multiple Kernels -- 10.3.2 Making Image Representations More Similar with Manifold Alignment -- 10.3.3 New Challenges -- 10.4 Biophysical Parameter Estimation -- 10.4.1 Covariances in Gaussian Processes -- 10.4.2 Ranking Features Through the Automatic Relevance Determination (ARD) Covariance -- 10.4.3 Uncertainty Intervals -- 10.4.4 New Challenges with GPR -- 10.5 Conclusions -- References.

Description based on publisher supplied metadata and other sources.

There are no comments on this title.

to post a comment.