14 9 Statistical Difference Models for Change Detection in Multispectral Images 9.1. Introduction 9.2. Overview of the change detection problem 9.3. The Rayleigh–Rice mixture model for the magnitude of the difference image 9.4. A compound multiclass statistical model of the difference image 9.5. Experimental results 9.6. Conclusion 9.7. References
16 Index
List of Illustrations
1 Chapter 1Figure 1.1. The main technical components of an unsupervised CD processFigure 1.2. 2D polar change representation domain in the C2VA methodFigure 1.3. Block scheme of the proposed M2C2VA techniqueFigure 1.4. Block scheme of the proposed superpixel-level multiclass CD approachFigure 1.5. Illustration of the decision-level fusion-based binary CD step. For ...Figure 1.6. Color-infrared composite of bitemporal QuickBird pan-sharpened image...Figure 1.7. False color composite of QuickBird images of the Indonesia tsunami d...Figure 1.8. 2D compressed change representation in the polar domain (Xuzhou data...Figure 1.9. Determination of the optimal segmentation scale in the Xuzhou datase...Figure 1.10. Comparison of the multiclass CD maps obtained by: (a) IR-MAD; (b) S...Figure 1.11. 2D compressed change representation in the polar domain (Indonesia ...Figure 1.12. Determination of the optimal segmentation scale in the Indonesia ts...Figure 1.13. Comparison of the CD maps obtained by: (a) IR-MAD; (b) S2CVA; (c) p...
2 Chapter 2Figure 2.1. An idealized parameter value function showing a linear trend with se...Figure 2.2. Figure showing the connection between the p-value for an outcome of ...Figure 2.3. The power function for testing whether two G(6, βt)-distributions, t...Figure 2.4. Simulating 128 × 128 pixel values at two time points with independen...Figure 2.5. Simulating 128 × 128 pixel values according to the signal + noise mo...Figure 2.6. Each column represents a simulation study on the distribution of 128...Figure 2.7. Simulating 128 × 128 pixel values at two time points with independen...Figure 2.8. Flowchart for the change detection algorithm. In the left part, we a...Figure 2.9. RGB images of diagonal elements of L-band SAR data acquired in 1998 ...Figure 2.10. Left: the values of the likelihood ratio test statistic for the omn...Figure 2.11. The first image shows when the first detected change occurred. In t...Figure 2.12. Histograms for intermediate p-values for areas covered with forest ...Figure 2.13. (Top) Zoomed-in views of Radarsat-2 images showing two moving dredg...Figure 2.14. Port of Tripoli: First four change maps of a total of 68 covering t...Figure 2.15. Fraction of positive definite changes (vessel arrivals) at the main...Figure 2.16. Change fractions showing effects of the 2020 Covid-19 lockdown star...Figure 2.17. Buzi district, Mozambique: Six change maps of a total of 15 for 16 ...Figure 2.18. Change images for the region around Fishlake, South Yorkshire. Left...Figure 2.19. Change fractions over the 2018 growing season for agricultural fiel...
3 Chapter 3Figure 3.1. General procedure for a change detection methodologyFigure 3.2. UAVSAR dataset used in this study for Scene 1. Four dates are availa...Figure 3.3. UAVSAR dataset used in this study for Scene 2. Two dates are availab...Figure 3.4. UAVSAR dataset used in this study for Scene 3Figure 3.5. Ground truth for Scenes 1, 2 and 3. For a color version of this figu...Figure 3.6. Illustration of the sliding windows (in gray) approach (p = 3, N = 9...Figure 3.7. ROC plots for a window size of 5 × 5 for the three scenes. Top: Scen...Figure 3.8. Output of
4 Chapter 4Figure 4.1. Flowchart providing the steps involved in MDDM computation from wave...Figure 4.2. Block diagram representing the framework for the detection and analy...Figure 4.3. Illustration of a BDF-MDDM and its clean version (MDF-MDDM) when two...Figure 4.4. Second diagonal of the MDF-MDDM shown in Figure 4.3, highlighting th...Figure 4.5. MDF-MDDM computed at a large scale, approximately 200 square kilomet...Figure 4.6. Second diagonals of the MDF-MDDMs shown in Figure 4.5 when restricte...Figure 4.7. Framework for evolution clustering. Analysis 1 involves dissimilarit...Figure 4.8. Clusters of dynamics for the Chamonix-Mont Blanc site. Cyan square: ...
5 Chapter 5Figure 5.1. Location of the study areas. For a color version of this figure, see...Figure 5.2. Altitude–time diagrams of VH SAR backscatters from the ascending orb...Figure 5.3. (a) Time series of Sentinel-1 VH observations from the ascending orb...Figure 5.4. (a) Wet snow cover extent derived from Sentinel-1 descending/ascendi...Figure 5.5. Correlation matrix of observation time series computed from formula ...Figure 5.6. (a) Metrics computed over test area 3 near Maljasset station using O...Figure 5.7. (a) Same as Figure 5.6(a) but for test area 2 using October 17, 2017...Figure 5.8. Same as Figure 5.7(a) but using pixels for which the logarithm of th...Figure 5.9. Selection of metrics computed over test area 2 for ranges of altitud...
6 Chapter 6Figure 6.1. Cyclonic field model. The eyewall has a usual diameter of 30–60 km. ...Figure 6.2. Isaac hurricane images. Courtesy: @Nasa-Images, Geostationary Operat...Figure 6.3. Sample | textures reconstructed by forcing to zero SWT approximation...Figure 6.4. 2D DWPT PSD of for the sample images | given by Figure 6.2. The PSD ...Figure 6.5. Comparison of diagonal elements (isotropy concern) of 2D DWPT and SW...Figure 6.6. [Top]: an Isaac image