Blaschke / Lang / Hay Object-Based Image Analysis

Spatial Concepts for Knowledge-Driven Remote Sensing Applications
1. Auflage 2008
ISBN: 978-3-540-77058-9
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 817 Seiten

This book brings together a collection of invited interdisciplinary persp- tives on the recent topic of Object-based Image Analysis (OBIA). Its c- st tent is based on select papers from the 1 OBIA International Conference held in Salzburg in July 2006, and is enriched by several invited chapters. All submissions have passed through a blind peer-review process resulting in what we believe is a timely volume of the highest scientific, theoretical and technical standards. The concept of OBIA first gained widespread interest within the GIScience (Geographic Information Science) community circa 2000, with the advent of the first commercial software for what was then termed ‘obje- oriented image analysis’. However, it is widely agreed that OBIA builds on older segmentation, edge-detection and classification concepts that have been used in remote sensing image analysis for several decades. Nevert- less, its emergence has provided a new critical bridge to spatial concepts applied in multiscale landscape analysis, Geographic Information Systems (GIS) and the synergy between image-objects and their radiometric char- teristics and analyses in Earth Observation data (EO).

Autoren/Hrsg.

Blaschke, Thomas

Lang, Stefan

Hay, Geoffrey

Inhaltsverzeichnis

1;Preface;5
2;Acknowledgements;8
3;Contents;9
4;External Reviewers;15
5;Section 1 Why object-based image analysis;18
5.1;Chapter 1.1 Object-based image analysis for remote sensing applications: modeling reality – dealing with complexity;19
5.1.1;1 Monitoring needs in a dynamic world;20
5.1.2;2 A plurality of solutions – conditioned information and geons;24
5.1.3;3 Class modeling;27
5.1.4;4 Object assessment and evaluation;34
5.1.5;6 Conclusion;40
5.1.6;Acknowledgements;40
5.1.7;References;40
5.2;Chapter 1.2 Progressing from object-based to object-oriented image analysis;44
5.2.1;1 Introduction;44
5.2.2;2 Methodology;46
5.2.3;3 Case study – single tree detection;50
5.2.4;4 Discussion;56
5.2.5;5 References;56
5.3;Chapter 1.3 An object-based cellular automata model to mitigate scale dependency;58
5.3.1;1 Introduction;59
5.3.2;2 Scale dependency in spatial analysis and modeling;60
5.3.3;3 The Vector-based Geographic Cellular Automata Model (VecGCA);67
5.3.4;4. Conclusion;80
5.3.5;Acknowledgements;81
5.3.6;References;81
5.4;Chapter 1.4 Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline;89
5.4.1;1 Introduction;89
5.4.2;2 What is GEOBIA? A definition;91
5.4.3;3 Why GEOBIA instead of OBIA?;92
5.4.4;4 GEOBIA: A key objective;93
5.4.5;5 Why is GEOBIA?;94
5.4.6;6 GEOBIA SWOT;95
5.4.7;7 GEOBIA Tenets;100
5.4.8;8. Conclusion;101
5.4.9;Acknowledgements;102
5.4.10;References;102
5.5;Chapter 1.5 Image objects and geographic objects;104
5.5.1;1 Introduction;104
5.5.2;2 Image-objects;107
5.5.3;3 Geo-objects;111
5.5.4;4 Linking image-objects to geo-objects;117
5.5.4.1;4.1 Meaningful image-objects;118
5.5.4.2;4.2. Object-based classification;119
5.5.5;5 Summary;121
5.5.6;Acknowledgements;121
5.5.7;References;121
6;Section 2 Multiscale representation and object-based classification;124
6.1;Chapter 2.1 Using texture to tackle the problem of scale in land-cover classification;125
6.1.1;1 Introduction;125
6.1.2;2 A conceptual model of aerial photo interpretation;127
6.1.3;3 Methodology;130
6.1.4;4 Conclusions and Future Work;142
6.1.5;References;143
6.2;Chapter 2.2 Domain-specific class modelling for one-level representation of single trees;145
6.2.1;1 Introduction;146
6.2.2;2 Study Areas and Data sets;147
6.2.3;3 Methodology;149
6.2.4;4 Results and Discussion;155
6.2.5;5 Conclusions;159
6.2.6;References;160
6.2.7;Acknowledgments;163
6.3;Chapter 2.3 Object recognition and image segmentation: the Feature Analyst® approach;164
6.3.1;1 Introduction;165
6.3.2;2 Learning Applied to Image Analysis;166
6.3.3;3 Feature Analyst;167
6.3.4;5 Conclusions;175
6.3.5;References;177
6.4;Chapter 2.4 A procedure for automatic object-based classification;179
6.4.1;1 Introduction;180
6.4.2;2 Theoretical background;181
6.4.3;3 Towards automation;183
6.4.4;4 Case studies;186
6.4.5;5. CONCLUSION;193
6.4.6;References;194
6.5;Chapter 2.5 Change detection using object features;195
6.5.1;1 Introduction;195
6.5.2;2 Methodology;198
6.5.3;3 Case study;204
6.5.4;4. Conclusions and future work;209
6.5.5;References;210
6.6;Chapter 2.6 Identifying benefits of pre-processing large area QuickBird imagery for object-based image analysis;212
6.6.1;1 Introduction;213
6.6.2;2 The pre-processing applied;214
6.6.3;3 Benefits of pre-processing;215
6.6.4;4 Deriving landscape patterns in the agricultural matrix;217
6.6.5;5 Summary and outlook;220
6.6.6;Note;221
6.6.7;References;221
6.7;Chapter 2.7 A hybrid texture-based and region-based multiscale image segmentation algorithm;229
6.7.1;1 Introduction;230
6.7.2;2 Methodology;232
6.7.3;3 Discussion of Results;237
6.7.4;4 Conclusions and future work;242
6.7.5;Acknowledgements;243
6.7.6;References;243
6.8;Chapter 2.8 Semi-automated forest stand delineation using wavelet based segmentation of very high resolution optical imagery;245
6.8.1;1 Introduction;246
6.8.2;2 Artificial imagery;246
6.8.3;3 Wavelets transforms;249
6.8.4;4 Materials;250
6.8.5;5 Method;251
6.8.6;6 Results and discussion;255
6.8.7;7 Conclusion;261
6.8.8;Acknowledgements;262
6.8.9;References;262
6.9;Chapter 2.9 Quality assessment of segmentation results devoted to object-based classification;265
6.9.1;1 Introduction;265
6.9.2;2 Segmentation quality indices;267
6.9.3;3 Case study;269
6.9.4;4 Results;271
6.9.5;5 Discussion;275
6.9.6;Conclusion;277
6.9.7;Acknowledgement;277
6.9.8;References;277
7;Section 3 Automated classification, mapping and updating: forest;280
7.1;Chapter 3.1 Object-based classification of QuickBird data using ancillary information for the detection of forest types and NATURA 2000 habitats;281
7.1.1;1 Introduction;282
7.1.2;2 Data and Methods;283
7.1.3;3 Results;289
7.1.4;4 Discussion and Outlook;293
7.1.5;References;294
7.2;Chapter 3.2 Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery;297
7.2.1;1 Introduction;298
7.2.2;2 Local variance, spatial autocorrelation and image objects associated with forest stand map;299
7.2.3;3 Study area and data sources;300
7.2.4;4 Methodology;301
7.2.5;5 Results and discussion;303
7.2.6;6 Summary and conclusion;304
7.2.7;Acknowledgements;306
7.2.8;References;306
7.3;Chapter 3.3 An object-based approach for the implementation of forest legislation in Greece using very high resolution satellite data;314
7.3.1;1 Introduction;315
7.3.2;2 Study area;317
7.3.3;3 Materials and methodology;318
7.3.4;4 Results and discussion;322
7.3.5;5 Conclusions;327
7.3.6;6 Acknowledgements;328
7.3.7;References;328
7.4;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
7.4.1;1 Introduction;332
7.4.2;2 JERS Test sites and data;333
7.4.3;3 Methodology;335
7.4.4;4 Results;338
7.4.5;5 Discussion of JERS Results and Methodology;342
7.4.6;6 Implementation of the Object-Based Classification Approach at the Russian Service case of GSE FM;343
7.4.7;7 Conclusions and Outlook;345
7.4.8;References;346
7.4.9;Acknowledgements;347
7.5;Chapter 3.5 Pixels to objects to information: Spatial context to aid in forest characterization with remote sensing;348
7.5.1;Introduction;349
7.5.2;Applications;351
7.5.3;Time since disturbance estimation;353
7.5.4;Capture of large area forest dynamics;355
7.5.5;Discussion;359
7.5.6;Conclusion;363
8;Section 4 Automated classification, mapping and updating: environmental resource management and agriculture;367
8.1;Chapter 4.1 Object-oriented oil spill contamination mapping in West Siberia with Quickbird data;368
8.1.1;1 Introduction;368
8.1.2;2 The OSCaR pilot study (Oil Spill Contamination Mapping in Russia);371
8.1.3;3 Data;371
8.1.4;4 Methods;374
8.1.5;5 Results and Discussion;378
8.1.6;6 Summary;381
8.1.7;Acknowledgements;381
8.1.8;References;381
8.2;Chapter 4.2 An object-oriented image analysis approach for the identification of geologic lineaments in a sedimentary geotectonic environment;384
8.2.1;1 Introduction;385
8.2.2;2 Methodology;386
8.2.3;3 Results and Discussion;395
8.2.4;4 Conclusions;397
8.2.5;References;398
8.3;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
8.3.1;1 Introduction;401
8.3.2;2 Material and methods;403
8.3.3;3 Results and discussion;410
8.3.4;4 Conclusions;414
8.3.5;5 References;414
8.3.6;Acknowledgements;415
8.4;Chapter 4.4 Multi-scale functional mapping of tidal marsh vegetation using object-based image analysis;416
8.4.1;1 Introduction;416
8.4.2;2 Methods;424
8.4.3;3 Results;433
8.4.4;4 Discussion;437
8.4.5;5 Conclusions;439
8.4.6;6 References;439
8.5;Chapter 4.5 A Local Fourier Transform approach for vine plot extraction from aerial images;444
8.5.1;1 Introduction;444
8.5.2;2 Method;446
8.5.3;3 Results;451
8.5.4;4 Conclusion and discussion;456
8.5.5;Acknowledgments;456
8.5.6;References;457
9;Section 5 Automated classification, mapping and updating: land use / land cover;458
9.1;Chapter 5.1 Object-based classification of IKONOS data for vegetation mapping in Central Japan;459
9.1.1;1 Introduction;460
9.1.2;2 Object-based classification in vegetation mapping;461
9.1.3;3 Methods;463
9.1.4;4 Results and Discussion;468
9.1.5;5 Conclusions;473
9.1.6;Acknowledgements;474
9.1.7;References;474
9.2;Chapter 5.2 Structural biodiversity monitoring in savanna ecosystems: Integrating LiDAR and high resolution imagery through object-based image analysis;476
9.2.1;1 Monitoring structural biodiversity in savanna ecosystems;477
9.2.2;2 Woody canopy delineation from black and white aerial photographs;479
9.2.3;3 Extracting woody vegetation structural attributes from LiDAR and high resolution aerial photography;483
9.2.4;4 Implications for the monitoring of savanna structural diversity;488
9.2.5;6 References;489
9.3;Chapter 5.3 Fusion of multispectral optical and SAR images towards operational land cover mapping in Central Europe;491
9.3.1;1 Introduction;492
9.3.2;2 Study Area and Experimental Data;493
9.3.3;3 Methodology;494
9.3.4;4 Results;497
9.3.5;5 Discussion;506
9.3.6;6 Conclusions and Outlook;507
9.3.7;Acknowledgement;508
9.3.8;References;508
9.4;Chapter 5.4 The development of integrated object-based analysis of EO data within UK national land cover products;510
9.4.1;1 Background;511
9.4.2;2 Object-based land cover mapping;511
9.4.3;3 Summary;523
9.4.4;4. References;524
9.4.5;5. Acknowledgements;525
10;Section 6 Automated classification, mapping and updating: urban applications;526
10.1;Chapter 6.1 Detecting informal settlements from QuickBird data in Rio de Janeiro using an object-based approach;527
10.1.1;1 Introduction;528
10.1.2;2 Methods and general methodologies;530
10.1.3;3 Accuracy Assessment;546
10.1.4;4 Conclusion and outlook;547
10.1.5;References;548
10.2;Chapter 6.2 Opportunities and limitations of object-based image analysis for detecting urban impervious and vegetated surfaces using true-colour aerial photography;550
10.2.1;1 Introduction;551
10.2.2;2 Data and methods;553
10.2.3;3. Results and discussion;557
10.2.4;4. Conclusions;562
10.2.5;References;563
10.3;Chapter 6.3 Object-based Image Analysis using QuickBird satellite images and GIS data, case study Belo Horizonte (Brazil);565
10.3.1;1 Introduction and problem setting;566
10.3.2;2 Brief description of test sites;567
10.3.3;3 Object-based image classifications;568
10.3.4;4 Spatial inferences;575
10.3.5;5 Conclusions and Perspectives;580
10.3.6;References;581
10.4;Chapter 6.4 An object-based approach to detect road features for informal settlements near Sao Paulo, Brazil;583
10.4.1;1 Introduction;584
10.4.2;2 Study area, data and tools;586
10.4.3;3 Methodology;587
10.4.4;4 Results;593
10.4.5;5 Quantitative Analyses;595
10.4.6;6 Conclusions;599
10.4.7;Acknowledgements;600
10.4.8;References;600
11;Section 7 Development of new methodologies;602
11.1;Chapter 7.1 Object-oriented analysis of image and LiDAR data and its potential for a dasymetric mapping application;603
11.1.1;1 Introduction;603
11.1.2;2 Data and Study Area;605
11.1.3;3 Methodology;607
11.1.4;4 Results;610
11.1.5;5 Conclusion and Outlook;615
11.1.6;6 References;615
11.1.7;Acknowledgements;616
11.2;Chapter 7.2 Characterising mountain forest structure using landscape metrics on LiDAR-based canopy surface models;617
11.2.1;1 Introduction;618
11.2.2;2 Study area and data;620
11.2.3;3 Methodology and Implementation;621
11.2.4;4 Results;627
11.2.5;5 Discussion;630
11.2.6;6 Conclusions;632
11.2.7;References;633
11.3;Chapter 7.3 Object detection in airborne laser scanning data - an integrative approach on object-based image and point cloud analysis;636
11.3.1;1 Introduction;637
11.3.2;2 Related work;638
11.3.3;3 Methodology;641
11.3.4;4 Application: Classification of roof facets;648
11.3.5;5 Conclusion;650
11.3.6;References;651
11.4;Chapter 7.4 Support Vector Machine classification for Object- Based Image Analysis;654
11.4.1;1 Introduction;655
11.4.2;2 Methodology;657
11.4.3;3 Discussion of Results;661
11.4.4;4 Conclusions;666
11.4.5;Acknowledgements;667
11.4.6;References;667
11.5;Chapter 7.5 Genetic adaptation of segmentation parameters;669
11.5.1;1 Introduction;670
11.5.2;2 Genetic Algorithms;671
11.5.3;3 Adaptation of segmentation parameters using a genetic algorithm;672
11.5.4;4 Segmentation procedure;675
11.5.5;5 Experiments;676
11.5.6;6 Conclusions and future work;683
11.5.7;Acknowledgments;684
11.5.8;References;684
11.6;Chapter 7.6 Principles of full autonomy in image interpretation. The basic architectural design for a sequential process with image objects;686
11.6.1;Introduction;687
11.6.2;Homogeneous versus non-homogeneous objects;687
11.6.3;Edge objects;688
11.6.4;Sequential classification;689
11.6.5;Representative populations;691
11.6.6;Template matching;691
11.6.7;Template matching;691
11.6.8;Categorization;692
11.6.9;Self-adapting;692
11.6.10;Central role of edges;693
11.6.11;Anchor objects;693
11.6.12;VHSR analysis;694
11.6.13;Standardization and outlook;697
11.6.14;The quest for image understanding;698
11.6.15;References;698
11.7;Chapter 7.7 Strategies for semi-automated habitat delineation and spatial change assessment in an Alpine environment;700
11.7.1;1 Introduction;701
11.7.2;2 Geographical Settings;703
11.7.3;3 Data and Data pre-processing;705
11.7.4;4 Methods;706
11.7.5;5 Results;712
11.7.6;6 Discussion;718
11.7.7;Acknowledgements;719
11.7.8;References;719
12;Section 8 Burning research questions, research needs and outlook;722
13;Chapter 8.1 On segment based image fusion;723
13.1;1 Introduction;724
13.2;2 Decision based fusion;725
13.3;3 GIS and NDVI based image enhancement;730
13.4;4 Conclusion;741
13.5;References;742
14;Chapter 8.2 Modelling uncertainty in high resolution remotely sensed scenes using a fuzzy logic approach;743
14.1;1 Introduction;743
14.2;2 Problems in uncertainty determination;744
14.3;3 Previous work;746
14.4;4 Fuzzy certainty measure;749
14.5;5 Summary and future work;754
14.6;References;755
15;Chapter 8.3 Assessing image segmentation quality – concepts, methods and application;757
15.1;1 Introduction and related work;757
15.2;2 Evaluated segmentation software;758
15.3;3 Evaluation methods;761
15.4;4 Results and discussion;764
15.5;5 Conclusions;769
15.6;References;770
15.7;Acknowledgments;772
16;Chapter 8.4 Object-fate analysis: Spatial relationships for the assessment of object transition and correspondence;773
16.1;Introduction;774
16.2;Results and discussion;781
16.3;Conclusions;785
16.4;Acknowledgements;787
16.5;References;787
17;Index;790