We consider the problem of despeckling synthetic aperture radar (SAR) images and propose an approach we call feature preserving despeckling (FPD). FPD is obtained through the adoption of a regularized SAR image reconstruction algorithm for the despeckling problem. FPD performs smoothing of homogeneous regions while preserving strong scatterers as well as region boundaries. We implement FPD in CUDA for fast parallel processing. We evaluate the performance of FPD through its impact on the performance of railway detection. To this end, we propose a semi-automated algorithm for railway detection in SAR images. We compare the performance of FPD to well-known despeckling methods and demonstrate the improvements it provides for railway detection.
Feature preserving SAR despeckling and its parallel implementation with application to railway detection
2012
4 Seiten, 3 Bilder, 2 Tabellen, 14 Quellen
Aufsatz (Konferenz)
Datenträger
Englisch
Preserving our railway heritage
British Library Online Contents | 1996
Preserving our railway heritage
Online Contents | 1996
Noise2Noise self-supervised deep learning holographic despeckling method
British Library Conference Proceedings | 2022
|Preserving metal work in railway bridges
Engineering Index Backfile | 1943
|BEMD based adaptive Lee filter for despeckling of SAR images
Elsevier | 2022
|