Stability and sensitivity of topographic features for SAR target characterization

The use of topographic features has been proposed classifying targets in synthetic aperture radar (SAR) images. These features are based upon the curvature properties of a surface model that is used to estimate the underlying image intensity. The stability of these features with respect to aspect and sensor noise is investigated. Attention is given to ensure appropriate registration of SAR images and to the modeling of noise in the SAR imaging process. Sensitivity and stability of features are quantitatively and qualitatively analyzed based on each pixel's label, and on the relative groupings of features respectively in the corresponding images. Stability results are presented for simulated XPATCH images as well as the MSTAR Target Dataset.