| |
| |
| Preface | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Introduction and Background | |
| |
| |
| |
| The Beginning of Space Age Remote Sensing | |
| |
| |
| |
| The Fundamental Basis For Remote Sensing | |
| |
| |
| |
| The Systems View And Its Interdisciplinary Nature | |
| |
| |
| |
| The EM Spectrum and How Information Is Conveyed | |
| |
| |
| |
| The Multispectral Concept and Data Representations | |
| |
| |
| |
| Data Analysis and Partitioning Feature Space | |
| |
| |
| |
| The significance of second-order variations | |
| |
| |
| |
| Summary | |
| |
| |
| |
| The Basics for Conventional Multispectral Data | |
| |
| |
| |
| Radiation and Sensor Systems in Remote Sensing | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Radiation Teminology and Units | |
| |
| |
| |
| Planck's Law and Black Body Radiation | |
| |
| |
| |
| Solar Radiation | |
| |
| |
| |
| Atmospheric Effects | |
| |
| |
| |
| Sensor Optics | |
| |
| |
| |
| Describing Surface Reflectance | |
| |
| |
| |
| Radiation Detectors | |
| |
| |
| |
| Sorting Radiation by Wavelength | |
| |
| |
| |
| Multispectral Sensor Systems | |
| |
| |
| |
| The development of multispectral sensor systems | |
| |
| |
| |
| Summary | |
| |
| |
| |
| Pattern Recognition in Remote Sensing | |
| |
| |
| |
| The synoptic view and the volume of data | |
| |
| |
| |
| What is a pattern? | |
| |
| |
| |
| Discriminant Functions | |
| |
| |
| |
| Training the Classifier: An Iterative Approach | |
| |
| |
| |
| Training the Classifier: The Statistical Approach | |
| |
| |
| |
| Discriminant Functions: The Continuous Case | |
| |
| |
| |
| The Gaussian Case | |
| |
| |
| |
| Other Types of Classifiers | |
| |
| |
| |
| Thresholding | |
| |
| |
| |
| On The Characteristics, Value, And Validity Of The Gaussian Assumption | |
| |
| |
| |
| The Hughes Effect | |
| |
| |
| |
| Summary to this point | |
| |
| |
| |
| Evaluating The Classifier: Probability Of Error | |
| |
| |
| |
| Clustering: Unsupervised Analysis | |
| |
| |
| |
| The Nature of Multispectral Data in Feature Space | |
| |
| |
| |
| Analyzing Data: Putting the Pieces Together | |
| |
| |
| |
| An Example Analysis | |
| |
| |
| |
| Additional Details | |
| |
| |
| |
| Training a Classifier | |
| |
| |
| |
| Classifier Training Fundamentals | |
| |
| |
| |
| The Statistics Enhancement Concept | |
| |
| |
| |
| The Statistics Enhancement Implementation | |
| |
| |
| |
| Illustrations Of The Effect Of Statistics Enhancement | |
| |
| |
| |
| Robust Statistics Enhancement | |
| |
| |
| |
| Illustrative Examples Of Robust Expectation Maximation | |
| |
| |
| |
| Some Additional Comments | |
| |
| |
| |
| A Small Sample Covariance Estimation Scheme | |
| |
| |
| |
| Results for Some Examples | |
| |
| |
| |
| Hyperspectral Data Characteristics | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| A Visualization Tool | |
| |
| |
| |
| Accuracy vs. Statistics Order | |
| |
| |
| |
| High-Dimensional Spaces: A Closer Look | |
| |
| |
| |
| Asymptotical first and second order statistics properties | |
| |
| |
| |
| High-dimensional implications for supervised classification | |
| |
| |
| |
| Feature Definition | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Ad Hoc and Deterministic Methods | |
| |
| |
| |
| Feature Selection | |
| |
| |
| |
| Principal Components / Karhunen-Loeve | |
| |
| |
| |
| Discriminant Analysis Feature Extraction (DAFE) | |
| |
| |
| |
| Decision Boundary Feature Extraction (DBFE) | |
| |
| |
| |
| Nonparametric Weighted Feature Extraction (NWFE) | |
| |
| |
| |
| Projection Pursuit | |
| |
| |
| |
| A Data Analysis Paradigm and Examples | |
| |
| |
| |
| A Paradigm for Multispectral and Hyperspectral Data Analysis | |
| |
| |
| |
| Example 1. A Moderate Dimension Example | |
| |
| |
| |
| A Hyperspectral Example Exploring Limits and Limitations | |
| |
| |
| |
| A Hyperspectral Example of Geologic Interest | |
| |
| |
| |
| Hyperspectral Analysis of Urban Data | |
| |
| |
| |
| Analyst Dependence and Other Analysis Factors | |
| |
| |
| |
| Summary and Directions | |
| |
| |
| |
| Hierarchical Decision Tree Classifiers | |
| |
| |
| |
| Use of Spatial Variations | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Use of Texture Measures | |
| |
| |
| |
| Further Evaluations of Texture Measures | |
| |
| |
| |
| A Fresh Look at the Problem | |
| |
| |
| |
| The Sample Classifier Concept | |
| |
| |
| |
| The Per Field Classifier | |
| |
| |
| |
| Finding the Boundaries of Fields | |
| |
| |
| |
| The Design of the ECHO Classifier | |
| |
| |
| |
| Sample Classification | |
| |
| |
| |
| Test of the Algorithm | |
| |
| |
| |
| Noise in Remote Sensing Systems | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Example: The Effects of Noise | |
| |
| |
| |
| A Noise Model | |
| |
| |
| |
| A Further Example of Noise Effects | |
| |
| |
| |
| A Signal and Noise Simulator | |
| |
| |
| |
| Multispectral Image Data Preprocessing | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Radiometric Preprocessing | |
| |
| |
| |
| Geometric Preprocessing | |
| |
| |
| |
| Goniometric Effects | |
| |
| |
| |
| An Outline of Probability Theory | |
| |
| |
| Exercises | |
| |
| |
| Index | |