Nonparametric Edge Detection in Speckled Imagery

TL;DR

This paper introduces nonparametric edge detection methods for speckled SAR images, demonstrating their superior accuracy and simplicity over existing techniques through numerical comparisons and real data application.

Contribution

It proposes new nonparametric edge detection methods for speckled imagery and compares their performance to recent existing methods, showing improvements in accuracy and computational efficiency.

Findings

Some proposed methods outperform existing ones in accuracy.

Proposed methods are computationally simpler.

Application to real SAR data confirms effectiveness.

Abstract

We address the issue of edge detection in Synthetic Aperture Radar imagery. In particular, we propose nonparametric methods for edge detection, and numerically compare them to an alternative method that has been recently proposed in the literature. Our results show that some of the proposed methods display superior results and are computationally simpler than the existing method. An application to real (not simulated) data is presented and discussed.