Edge Detection in Urban Areas using Multichannel SAR Interferometry

Building edge detection is a task of increasing importance in last decays. In this paper we propose a novel approach to handle this problem using jointly both SAR amplitude and phase data. The technique is based on a stochastic estimation and on Markov Random Field (MRF). The algorithm computes the building edge map looking for the discontinuities of both phase and reflectivity using jointly the amplitude and the phase of SAR images. Compared to classical amplitude based edge detectors and to phase based ones, the proposed method shows an improvement in terms of detection accuracy and false alarm rate.