Image registration is a fundamental task in remote sensing image processing that is used to match two or more images taken, for example, at different times, from different sensors or from different view points. In this dissertation, we have evolved and combined two distinct techniques namely Mutual Information (MI) and Scale Invariant Feature Transform (SIFT) to extend their applicability for multimodal SAR-Optical and SAR-SAR matching respectively. We analyze the performance of MI for very high resolution remote sensing images and evaluate (feature extraction, classification, segmentation, discrete optimization) for improving its accuracy, applicability and processing time for VHR images (mainly TerraSAR-X and IKONOS-2) acquired over dense urban areas. We also analyze changes to improve the feature detection, identification and matching steps of the SIFT processing chain for multimodal SAR images.
«
Image registration is a fundamental task in remote sensing image processing that is used to match two or more images taken, for example, at different times, from different sensors or from different view points. In this dissertation, we have evolved and combined two distinct techniques namely Mutual Information (MI) and Scale Invariant Feature Transform (SIFT) to extend their applicability for multimodal SAR-Optical and SAR-SAR matching respectively. We analyze the performance of MI for very high...
»