Contents Summary i Samenvatting iii Aknowledgements vii Contents ix 1 Introduction 1 1.1 The need for urban trees 2 1.2 Monitoring urban trees 3 1.3 Monitoring urban trees in the Netherlands: the Boom en Beeld project 4 1.4 Geospatial approach for tree monitoring 6 1.5 Image analysis methods for tree extraction on VHR images 8 1.6 Data quality and accuracy of remote sensing classification products 9 1.7 Problem statement 10 1.8 Research objectives and questions 13 1.9 Thesis outline 14 2 Context-sensitive extraction of tree crown objects using VHR images 15 2.1 Introduction 16 2.2 Test sites and data 17 2.3 GEOBIA approach for tree identification 19 2.4 Experiment design and GEOBIA implementation 26 2.5 Results 31 2.6 Discussion 33 2.7 Conclusions 38 3 MRF based SRM for identification of urban trees in VHR images 39 3.1 Introduction 40 3.2 Super resolution mapping 42 3.3 Implementation 45 3.4 Results 54 3.5 Discussion 59 3.6 Conclusions 64 4 Quantification of crown changes and change uncertainty of urban trees 65 4.1 Introduction 66 4.2 Change detection method 67 4.3 Change detection experiment 75 4.4 Experimental results and accuracy assessment 80 4.5 Discussion 87 4.6 Conclusions 90 5 Change detection using region-based active contours in VHR images 93 5.1 Introduction 94 5.2 Study area and data 96 5.3 Tree crown monitoring using active contours and image fitting 98 5.4 Results and assessment of accuracy 108 5.5 Discussion 113 5.6 Conclusions 120 6 Synthesis 123 6.1 Conclusions 124 6.2 Reflections 126 6.3 A monitoring system for the city of the 21st century 132 6.4 Recommendations 137 A Appendices 139 A.I GEOBIA algorithms for tree crown identification 139 A.2 Assumptions, ease of implementation and sensitivity of contextual rules for tree crown extraction 140 A.3 Pseudo-code for SRM energy minimization 141 Bibliography 143