Stability and sensitivity of topographic features for synthetic aperture radar target characterization

The use of topographic features is proposed for classifying targets in synt hetic-aperture radar (SAR) images. These features are based on the curvatur e properties of a surface model that is used to estimate the underlying ima ge intensity. The stability of these features with respect to aspect, senso r noise. and squint is investigated. Attention is given to ensuring appropr iate registration of the 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 in the corresponding images. Stability results are p resented for images obtained from XPATCH simulation software as well from a s the Moving and Stationary Target Recognition target data set. The stabili ty of these features is compared with the stability of features obtained di rectly from the SAR magnitude images. (C) 1999 Optical Society of America [ S0740-3232(99)01202-8].