Remote Sensing Handbook, Volume II: Image Processing, Change Detection, GIS, and Spatial Data Analysis

Volume II of the Six Volume Remote Sensing Handbook , Second Edition, is focused on digital image processing including image classification methods in land cover and land use. It discusses object-based segmentation and pixel-based image processing algorithms, change detection techniques, and image classification for a wide array of applications including land use/land cover, croplands, urban studies, processing hyperspectral remote sensing data, thermal imagery, light detection and ranging (LiDAR), geoprocessing workflows, frontiers of GIScience, and future pathways. This thoroughly revised and updated volume draws on the expertise of a diverse array of leading international authorities in remote sensing and provides an essential resource for researchers at all levels interested in using remote sensing. It integrates discussions of remote sensing principles, data, methods, development, applications, and scientific and social context. Features Provides the most up-to-date comprehensive coverage of digital image processing. Highlights object-based image analysis (OBIA) and pixel-based classification methods and techniques of digital image processing. Demonstrates practical examples of image processing for a myriad of applications such as land use/land cover, croplands, and urban. Establishes image processing using different types of remote sensing data that includes multispectral, radar, LiDAR, thermal, and hyperspectral. Highlights change detection, geoprocessing, and GIScience. This volume is an excellent resource for the entire remote sensing and GIS community. Academics, researchers, undergraduate and graduate students, as well as practitioners, decision makers, and policymakers, will benefit from the expertise of the professionals featured in this book, and their extensive knowledge of new and emerging trends. Cover Half Title Title Copyright Contents Foreword Preface About the Editor List of Contributors Acknowledgments Part I Image Processing Methods and Approaches Chapter 1 Digital Image Processing: A Review of the Fundamental Methods and Techniques 1.1 Introduction 1.2 Image Quality Assessment: Basic Statistics and Histogram Analysis 1.2.1 Histogram 1.3 Image Enhancement 1.4 Image Preprocessing 1.4.1 Radiometric Correction 1.4.2 Geometric Correction 1.5 Principal Component Analysis (PCA) 1.6 Spatial Filtering 1.7 Band Ratioing and Vegetation Indices 1.7.1 Band Ratio 1.7.2 Vegetation Index (VI) 1.7.3 Simple Ratio (SR) 1.7.4 Normalized Difference Vegetation Index (NDVI) 1.7.5 Enhanced Vegetation Index (EVI) 1 and 2 1.7.6 Wide Dynamic Range Vegetation Index (WDRVI) 1.7.7 Three-Band Model (TBM) 1.8 Image Classification 1.9 Future Trends Chapter 2 Image Classification Methods in Land Cover and Land Use 2.1 Introduction 2.1.1 Definitions 2.1.2 Advantages and Limitations of Remote Sensing for Mapmaking 2.2 Image Classification in the Context of Land-Use/Land-Cover Mapping 2.2.1 Historical Perspective 2.2.2 Methods 2.2.3 Uncertainty Assessment 2.3 The Future Chapter 3 Urban Image Classification: Per-Pixel Classifiers, Sub-Pixel Analysis, Object-Based Image Analysis, Geospatial Methods, and Machine Learning Approach 3.1 Introduction 3.2 Remote Sensing Methods for Urban Classification and Interpretation 3.3 Per-Pixel Methods 3.4 Sub-Pixel Methods 3.5 Object-Based Methods 3.6 Geospatial Methods 3.7 Machine Learning Methods 3.8 Concluding Remarks Chapter 4 Hyperspectral Image Processing: Methods and Approaches 4.1 Introduction 4.2 Classification Approaches 4.2.1 Supervised Classification 4.2.2 Spectral–Spatial Classification 4.2.3 Subspace-Based Approaches 4.2.4 Semi-Supervised Classification 4.3 Experimental Comparison 4.4 Conclusions and Future Directions 4.5 Acknowledgments Chapter 5 Collaborative Representation for Hyperspectral Image Classification and Detection 5.1 Introduction 5.2 Collaborative Representation-Based Classification 5.2.1 Collaborative Representation-Based Classifier (CRC) 5.2.2 Collaborative Representation with Tikhonov (CRT) Regularization 5.2.3 Probabilistic CRC (ProCRC) and Probabilistic CRT (ProCRT) 5.2.4 Spatial-Aware CRC (SaCRC) and Spatial-Aware CRT (SaCRT) 5.2.5 SaProCRC and SaProCRT 5.2.6 Representation-Based Classification with Dictionary Partition 5.2.7 Joint Representation-Based Classification 5.2.8 Kernel CRC and CRT 5.2.9 Representation in Feature Spaces 5.3 Collaborative Representation-Based Anomaly Detection 5.4 Experiments 5.4.1 Classification 5.4.2 Anomaly Detection 5.5 Conclusion Chapter 6 Thermal Infrared Remote Sensing: Principles and Theoretical Background 6.1 Introduction 6.2 Principles, Theoretical Background, Important Laws 6.2.1 The Thermal Infrared Domain 6.2.2 Important Laws: Planck 6.2.3 Important Laws: Stefan–Boltzmann 6.2.4 Important Laws: Wien 6.2.5 Important Laws: Kirchhoff and the Role of Emissivity 6.3 Potential of Diurnal and Time Series of Thermal Infrared Remote Sensing Data 6.4 Application Examples of Thermal Infrared Data Analyses 6.5 Ground Data and Validating Thermal Infrared Data 6.6 Discussion and Conclusion Chapter 7 Remote Sensing Image Segmentation: Methods, Approaches, and Advances 7.1 Introduction 7.2 Traditional Segmentation Methods 7.2.1 Spectrally Based Methods 7.2.2 Spatially Based Methods 7.2.3 Graph-Based Method 7.2.4 Hybrid Methods (HMs) 7.3 DL-Based Semantic Segmentation Methods 7.3.1 Algorithms’ Basic 7.3.2 Application Examples 7.3.3 Publicly Available Data for Semantic Segmentation of Remote Sensing Images 7.3.4 Pros and Cons of Semantic Methods 7.4 Segmentation of LiDAR Data 7.5 Segmentation of Hyperspectral Data 7.6 Segmentation Evaluation 7.7 Concluding Remarks Chapter 8 Object-Based Image Analysis: Evolution, History, State of the Art, and Future Vision 8.1 Introduction 8.2 History of OBIA 8.2.1 Intellectual Roots 8.2.2 Needs and Driving Forces 8.2.3 GEOBIA Developments 8.3 OBIA—A Short Summary of the State of the Art 8.3.1 Segmentation Is Part of OBIA—But Not Married to It 8.3.2 Classification 8.3.3 Complex “Geo-Intelligence” Tasks 8.4 Ongoing Developments: Influences of OBIA to Other Fields and Vice Versa 8.4.1 GIScience and Remote Sensing 8.4.2 The Changing Workplace 8.4.3 Who Uses OBIA? 8.5 Concluding Perspectives 8.5.1 New Paradigm: The Need for a Common Nomenclature and Sound Methodologies 8.5.2 Toward a Civilian Geo-Intelligence 8.5.3 Epistemological and Ontological Challenges Chapter 9 Geospatial Data Integration in OBIA—Implications of Accuracy and Validity 9.1 Conditioned Information 9.1.1 OBIA in Support to Geospatial Information Needs 9.1.2 Enriched Information through OBIA 9.2 Object Validity 9.2.1 Color and Form: Elements of Image Understanding 9.2.2 Human versus Machine Vision 9.2.3 Class Modeling 9.2.4 Validity of Object Delineation and Classification 9.2.5 Multiple-Stage Validation 9.3 Object Fate 9.3.1 From Static to Dynamic Change Concepts 9.3.2 Application Scenario 1—Object-Based Information Update 9.3.3 Object Fate Analysis 9.3.4 Object Linking 9.3.5 Application Scenario 2—Rapid Information Extraction 9.4 Conclusions Chapter 10 Image Segmentation Algorithms for Land Categorization 10.1 Introduction 10.2 Spectrally Based Segmentation Approaches 10.2.1 Thresholding-Based Algorithms 10.2.2 Clustering-Based Algorithms 10.2.3 Support Vector Machines 10.3 Spatially Based Segmentation Approaches 10.3.1 Region Growing Algorithms 10.3.2 Texture-Based Algorithms 10.3.3 Morphological Algorithms 10.3.4 Graph-Based Algorithms 10.3.5 MRF-Based Algorithms 10.4 Image Segmentation Quality Evaluation 10.5 Concluding Remarks Chapter 11 LiDAR Data Processing and Applications 11.1 Introduction 11.2 LiDAR Data Quality Assessment and Control 11.2.1 System Components 11.2.2 LiDAR Error Budget 11.2.3 Quality Assessment 11.2.4 Quality Control 11.3 LiDAR Data Management 11.3.1 Storage of LiDAR Point Cloud Data 11.3.2 Organization and Generalization of LiDAR Point Cloud 11.3.3 LiDAR Database 11.4 LiDAR Point Cloud Feature Extraction 11.4.1 Spatial Features in LiDAR Data 11.4.2 Methods for the Extraction of Spatial Features 11.5 3D City Modeling from LiDAR Data 11.5.1 Properties of LiDAR Data in a City Area 11.5.2 Object Reconstruction Strategies 11.5.3 Building Extraction 11.5.4 Road Extraction 11.6 Full-Waveform Airborne LiDAR 11.6.1 Introduction 11.6.2 Waveform Data Analysis 11.6.3 Applications 11.7 DEM and DSM Generation from Airborne LiDAR Data 11.7.1 Introduction 11.7.2 Data Processing for DEM and DSM Generation 11.7.3 DEM Quality Assessment and Control 11.8 Terrestrial/Vehicle-Borne LiDAR Data Processing 11.8.1 Terrestrial LiDAR Data Processing 11.8.2 Object Extraction from Vehicle-Borne LiDAR Data 11.9 Conclusions Part II Change Detection Chapter 12 Forest Clear-Cutting Detection in Subtropical Regions with Time Series Remotely Sensed Data 12.1 Introduction 12.2 Application of Time Series Landsat Images to Forest Clear-Cutting Detection in Fujian Province 12.2.1 Study Area and Datasets 12.2.2 Forest Clear-Cutting Detection Using CCDC 12.2.3 Results 12.2.4 Summary 12.3 Application of Time Series Multi-Sensor Data to Forest Clear-Cutting Detection in Pu’er City 12.3.1 Study Area and Datasets 12.3.2 Forest Clear-Cutting Detection with Deep Learning 12.3.3 Results 12.3.4 Summary 12.4 Discussions 12.4.1 The Role of Time Series Landsat Data in Forest Clear-Cutting Detection 12.4.2 The Role of Time Series Multi-Sensor Data in Forest Clear-Cutting Detection 12.5 Perspectives 12.6 Acknowledgments Part III Integrating Geographic Information Systems (GIS) and Remote Sensing in Spatial Modeling Framework for Decision Support Chapter 13 Geoprocessing, Workflows, and Provenance 13.1 Introduction 13.1.1 Working Definitions 13.2 Historical Context 13.2.1 Digital Provenance in Remote Sensing and Geospatial Workflows 13.2.2 Geospatial Provenance through Version Control 13.2.3 Specifications and International Standards for Implementation of Shared Provence-Aware Remote Sensing Workflows 13.3 Why Provenance in Remote Sensing Workflows 13.3.1 Remote Sensing Questions That Only Provenance Can Answer 13.3.2 Provenance as a Prerequisite for Remote Sensing Stakeholder Requirements 13.3.3 Provenance and Trust in the Remote Sensing Process 13.4 Selected Recent and Proposed Provenance-Aware Systems 13.4.1 General Approaches 13.4.2 Earth System Science Workbench and ES3 13.4.3 MODAPS and OMIDAPS 13.4.4 Karma 13.4.5 Data Quality Provenance System 13.4.6 VisTrails 13.4.7 UV-CDAT 13.4.8 GeoPWProv 13.4.9 GeoWeaver 13.4.10 Code Ocean 13.4.11 KnowWhereGraph 13.5 Conclusions and Research Implications Chapter 14 Toward Democratization of Geographic Information: GIS, Remote Sensing, and GNSS Applications in Everyday Life 14.1 Rethinking Geographic Information and Technologies in the 21st Century 14.2 Toward Democratization of Geo-Information Technologies 14.2.1 Enlightened Phase (20th Century): State Sponsored Geo-Information Technologies 14.2.2 Transition Phase (20th Century): Governance and Scholarship for Society 14.2.3 Contemporary Phase (21st Century): The Vision of Democratization 14.3 Discovering Remote Sensing, GIS, and GNSS Applications in Our Daily Lives 14.3.1 Location-Based Services (LBSs) 14.3.2 Disaster Relief and Emergency Management 14.3.3 Community Building 14.3.4 Participatory Sensing 14.4 Democratization of Geo-Information: Circumscribing Issues and Challenges 14.4.1 Quality of Information and Services 14.4.2 Privacy and Confidentiality 14.4.3 Empowerment and Equity 14.5 Conclusion Chapter 15 Frontiers of GIScience: Evolution, State of the Art, and Future Pathways 15.1 Introduction 15.2 Evolution 15.3 State of the Art 15.3.1 Abstraction 15.3.2 Algorithms 15.3.3 Assimilation 15.4 Future Pathways and Concluding Remarks Chapter 16 Object-Based Regionalization for Policy-Oriented Partitioning of Space 16.1 Mapping Multi-Dimensional Phenomena 16.1.1 Ambitious Policy Targets Require a Systemic View 16.1.2 Approaching Complex Phenomena in a Spatial Focus 16.1.3 Geons—Terminology and Conceptual Background 16.2 Domain-Specific Regionalization 16.2.1 Principles of Regionalization 16.2.2 Integrated Geons 16.2.3 In Depth: Systemic Areal Units 16.3 Case Studies 16.3.1 Socioeconomic Vulnerability to Hazards 16.3.2 Social Vulnerability to Malaria 16.3.3 Landscape Sensitivity to Road Construction 16.3.4 Climate Change Susceptibility (Cumulative CC Impact) 16.4 Conclusion Part IV Summary and Synthesis of Volume II Chapter 17 Summary Chapter, Volume II, Remote Sensing Handbook (Second Edition): Image Processing, Change Detection, GIS, and Spatial Data Analysis 17.1 Digital Image Processing: Methods and Techniques 17.2 Image Classification Methods in Land Cover and Land Use and Cropland Studies 17.3 Urban Image Classification Methods and Approaches 17.4 Hyperspectral Image Processing Methods and Approaches 17.5 Advances in Digital Image Processing with New and Old Generation of Hyperspectral Data 17.6 Thermal Infrared Remote Sensing: Principles and Theoretical Background 17.7 Remote Sensing Image Segmentation: Methods, Approaches, and Advances 17.8 Object-Based Image Analysis (OBIA): Evolution and State of the Art 17.9 Geospatial Data Integration in OBIA and Implications on Accuracy and Validity 17.10 Image Segmentation Algorithms for Land Categorization 17.11 LiDAR Data Processing and Applications 17.12 Change Detection 17.13 Geoprocessing, Workflows, and Provenance 17.14 Toward Democratization of Geographic Information 17.15 GIScience 17.16 Object-Based Regionalization for Policy-Oriented Partitioning of Space 17.17 Synthesis of Chapter 17 of Volume II 17.18 Acknowledgments Index