Object-Based Image Analysis (eBook)

Preface 5
Acknowledgements 8
Contents 9
External Reviewers 15
Section 1 Why object-based image analysis 18
Chapter 1.1 Object-based image analysis for remote sensing applications: modeling reality – dealing with complexity 19
1 Monitoring needs in a dynamic world 20
2 A plurality of solutions – conditioned information and geons 24
3 Class modeling 27
4 Object assessment and evaluation 34
6 Conclusion 40
Acknowledgements 40
References 40
Chapter 1.2 Progressing from object-based to object-oriented image analysis 44
1 Introduction 44
2 Methodology 46
3 Case study – single tree detection 50
4 Discussion 56
5 References 56
Chapter 1.3 An object-based cellular automata model to mitigate scale dependency 58
1 Introduction 59
2 Scale dependency in spatial analysis and modeling 60
3 The Vector-based Geographic Cellular Automata Model (VecGCA) 67
4. Conclusion 80
Acknowledgements 81
References 81
Chapter 1.4 Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline 89
1 Introduction 89
2 What is GEOBIA? A definition 91
3 Why GEOBIA instead of OBIA? 92
4 GEOBIA: A key objective 93
5 Why is GEOBIA? 94
6 GEOBIA SWOT 95
7 GEOBIA Tenets 100
8. Conclusion 101
Acknowledgements 102
References 102
Chapter 1.5 Image objects and geographic objects 104
1 Introduction 104
2 Image-objects 107
3 Geo-objects 111
4 Linking image-objects to geo-objects 117
4.1 Meaningful image-objects 118
4.2. Object-based classification 119
5 Summary 121
Acknowledgements 121
References 121
Section 2 Multiscale representation and object-based classification 124
Chapter 2.1 Using texture to tackle the problem of scale in land-cover classification 125
1 Introduction 125
2 A conceptual model of aerial photo interpretation 127
3 Methodology 130
4 Conclusions and Future Work 142
References 143
Chapter 2.2 Domain-specific class modelling for one-level representation of single trees 145
1 Introduction 146
2 Study Areas and Data sets 147
3 Methodology 149
4 Results and Discussion 155
5 Conclusions 159
References 160
Acknowledgments 163
Chapter 2.3 Object recognition and image segmentation: the Feature Analyst® approach 164
1 Introduction 165
2 Learning Applied to Image Analysis 166
3 Feature Analyst 167
5 Conclusions 175
References 177
Chapter 2.4 A procedure for automatic object-based classification 179
1 Introduction 180
2 Theoretical background 181
3 Towards automation 183
4 Case studies 186
5. CONCLUSION 193
References 194
Chapter 2.5 Change detection using object features 195
1 Introduction 195
2 Methodology 198
3 Case study 204
4. Conclusions and future work 209
References 210
Chapter 2.6 Identifying benefits of pre-processing large area QuickBird imagery for object-based image analysis 212
1 Introduction 213
2 The pre-processing applied 214
3 Benefits of pre-processing 215
4 Deriving landscape patterns in the agricultural matrix 217
5 Summary and outlook 220
Note 221
References 221
Chapter 2.7 A hybrid texture-based and region-based multiscale image segmentation algorithm 229
1 Introduction 230
2 Methodology 232
3 Discussion of Results 237
4 Conclusions and future work 242
Acknowledgements 243
References 243
Chapter 2.8 Semi-automated forest stand delineation using wavelet based segmentation of very high resolution optical imagery 245
1 Introduction 246
2 Artificial imagery 246
3 Wavelets transforms 249
4 Materials 250
5 Method 251
6 Results and discussion 255
7 Conclusion 261
Acknowledgements 262
References 262
Chapter 2.9 Quality assessment of segmentation results devoted to object-based classification 265
1 Introduction 265
2 Segmentation quality indices 267
3 Case study 269
4 Results 271
5 Discussion 275
Conclusion 277
Acknowledgement 277
References 277
Section 3 Automated classification, mapping and updating: forest 280
Chapter 3.1 Object-based classification of QuickBird data using ancillary information for the detection of forest types and NATURA 2000 habitats 281
1 Introduction 282
2 Data and Methods 283
3 Results 289
4 Discussion and Outlook 293
References 294
Chapter 3.2 Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery 297
1 Introduction 298
2 Local variance, spatial autocorrelation and image objects associated with forest stand map 299
3 Study area and data sources 300
4 Methodology 301
5 Results and discussion 303
6 Summary and conclusion 304
Acknowledgements 306
References 306
Chapter 3.3 An object-based approach for the implementation of forest legislation in Greece using very high resolution satellite data 314
1 Introduction 315
2 Study area 317
3 Materials and methodology 318
4 Results and discussion 322
5 Conclusions 327
6 Acknowledgements 328
References 328
Chapter 3.4 Object-based classification of SAR data for the delineation of forest cover maps and the detection of deforestation – A viable procedure and its application in GSE Forest Monitoring 331
1 Introduction 332
2 JERS Test sites and data 333
3 Methodology 335
4 Results 338
5 Discussion of JERS Results and Methodology 342
6 Implementation of the Object-Based Classification Approach at the Russian Service case of GSE FM 343
7 Conclusions and Outlook 345
References 346
Acknowledgements 347
Chapter 3.5 Pixels to objects to information: Spatial context to aid in forest characterization with remote sensing 348
Introduction 349
Applications 351
Time since disturbance estimation 353
Capture of large area forest dynamics 355
Discussion 359
Conclusion 363
Section 4 Automated classification, mapping and updating: environmental resource management and agriculture 367
Chapter 4.1 Object-oriented oil spill contamination mapping in West Siberia with Quickbird data 368
1 Introduction 368
2 The OSCaR pilot study (Oil Spill Contamination Mapping in Russia) 371
3 Data 371
4 Methods 374
5 Results and Discussion 378
6 Summary 381
Acknowledgements 381
References 381
Chapter 4.2 An object-oriented image analysis approach for the identification of geologic lineaments in a sedimentary geotectonic environment 384
1 Introduction 385
2 Methodology 386
3 Results and Discussion 395
4 Conclusions 397
References 398
Chapter 4.3 Classification of linear environmental impacts and habitat fragmentation by object-oriented analysis of aerial photographs in Corrubedo National Park (NW Iberian Peninsula) 400
1 Introduction 401
2 Material and methods 403
3 Results and discussion 410
4 Conclusions 414
5 References 414
Acknowledgements 415
Chapter 4.4 Multi-scale functional mapping of tidal marsh vegetation using object-based image analysis 416
1 Introduction 416
2 Methods 424
3 Results 433
4 Discussion 437
5 Conclusions 439
6 References 439
Chapter 4.5 A Local Fourier Transform approach for vine plot extraction from aerial images 444
1 Introduction 444
2 Method 446
3 Results 451
4 Conclusion and discussion 456
Acknowledgments 456
References 457
Section 5 Automated classification, mapping and updating: land use / land cover 458
Chapter 5.1 Object-based classification of IKONOS data for vegetation mapping in Central Japan 459
1 Introduction 460
2 Object-based classification in vegetation mapping 461
3 Methods 463
4 Results and Discussion 468
5 Conclusions 473
Acknowledgements 474
References 474
Chapter 5.2 Structural biodiversity monitoring in savanna ecosystems: Integrating LiDAR and high resolution imagery through object-based image analysis 476
1 Monitoring structural biodiversity in savanna ecosystems 477
2 Woody canopy delineation from black and white aerial photographs 479
3 Extracting woody vegetation structural attributes from LiDAR and high resolution aerial photography 483
4 Implications for the monitoring of savanna structural diversity 488
6 References 489
Chapter 5.3 Fusion of multispectral optical and SAR images towards operational land cover mapping in Central Europe 491
1 Introduction 492
2 Study Area and Experimental Data 493
3 Methodology 494
4 Results 497
5 Discussion 506
6 Conclusions and Outlook 507
Acknowledgement 508
References 508
Chapter 5.4 The development of integrated object-based analysis of EO data within UK national land cover products 510
1 Background 511
2 Object-based land cover mapping 511
3 Summary 523
4. References 524
5. Acknowledgements 525
Section 6 Automated classification, mapping and updating: urban applications 526
Chapter 6.1 Detecting informal settlements from QuickBird data in Rio de Janeiro using an object-based approach 527
1 Introduction 528
2 Methods and general methodologies 530
3 Accuracy Assessment 546
4 Conclusion and outlook 547
References 548
Chapter 6.2 Opportunities and limitations of object-based image analysis for detecting urban impervious and vegetated surfaces using true-colour aerial photography 550
1 Introduction 551
2 Data and methods 553
3. Results and discussion 557
4. Conclusions 562
References 563
Chapter 6.3 Object-based Image Analysis using QuickBird satellite images and GIS data, case study Belo Horizonte (Brazil) 565
1 Introduction and problem setting 566
2 Brief description of test sites 567
3 Object-based image classifications 568
4 Spatial inferences 575
5 Conclusions and Perspectives 580
References 581
Chapter 6.4 An object-based approach to detect road features for informal settlements near Sao Paulo, Brazil 583
1 Introduction 584
2 Study area, data and tools 586
3 Methodology 587
4 Results 593
5 Quantitative Analyses 595
6 Conclusions 599
Acknowledgements 600
References 600
Section 7 Development of new methodologies 602
Chapter 7.1 Object-oriented analysis of image and LiDAR data and its potential for a dasymetric mapping application 603
1 Introduction 603
2 Data and Study Area 605
3 Methodology 607
4 Results 610
5 Conclusion and Outlook 615
6 References 615
Acknowledgements 616
Chapter 7.2 Characterising mountain forest structure using landscape metrics on LiDAR-based canopy surface models 617
1 Introduction 618
2 Study area and data 620
3 Methodology and Implementation 621
4 Results 627
5 Discussion 630
6 Conclusions 632
References 633
Chapter 7.3 Object detection in airborne laser scanning data - an integrative approach on object-based image and point cloud analysis 636
1 Introduction 637
2 Related work 638
3 Methodology 641
4 Application: Classification of roof facets 648
5 Conclusion 650
References 651
Chapter 7.4 Support Vector Machine classification for Object- Based Image Analysis 654
1 Introduction 655
2 Methodology 657
3 Discussion of Results 661
4 Conclusions 666
Acknowledgements 667
References 667
Chapter 7.5 Genetic adaptation of segmentation parameters 669
1 Introduction 670
2 Genetic Algorithms 671
3 Adaptation of segmentation parameters using a genetic algorithm 672
4 Segmentation procedure 675
5 Experiments 676
6 Conclusions and future work 683
Acknowledgments 684
References 684
Chapter 7.6 Principles of full autonomy in image interpretation. The basic architectural design for a sequential process with image objects 686
Introduction 687
Homogeneous versus non-homogeneous objects 687
Edge objects 688
Sequential classification 689
Representative populations 691
Template matching 691
Template matching 691
Categorization 692
Self-adapting 692
Central role of edges 693
Anchor objects 693
VHSR analysis 694
Standardization and outlook 697
The quest for image understanding 698
References 698
Chapter 7.7 Strategies for semi-automated habitat delineation and spatial change assessment in an Alpine environment 700
1 Introduction 701
2 Geographical Settings 703
3 Data and Data pre-processing 705
4 Methods 706
5 Results 712
6 Discussion 718
Acknowledgements 719
References 719
Section 8 Burning research questions, research needs and outlook 722
Chapter 8.1 On segment based image fusion 723
1 Introduction 724
2 Decision based fusion 725
3 GIS and NDVI based image enhancement 730
4 Conclusion 741
References 742
Chapter 8.2 Modelling uncertainty in high resolution remotely sensed scenes using a fuzzy logic approach 743
1 Introduction 743
2 Problems in uncertainty determination 744
3 Previous work 746
4 Fuzzy certainty measure 749
5 Summary and future work 754
References 755
Chapter 8.3 Assessing image segmentation quality – concepts, methods and application 757
1 Introduction and related work 757
2 Evaluated segmentation software 758
3 Evaluation methods 761
4 Results and discussion 764
5 Conclusions 769
References 770
Acknowledgments 772
Chapter 8.4 Object-fate analysis: Spatial relationships for the assessment of object transition and correspondence 773
Introduction 774
Results and discussion 781
Conclusions 785
Acknowledgements 787
References 787
Index 790