Feature Preserving SAR Despeckling and Its Parallel Implementation with Application to Railway Detection

Inhalt:
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.