Optimal Object Discrimination and Orientation Determination in Synthetic Aperture Radar Images

Abstract

Detection and identification of objects in SAR images is complicated by the presence of speckle. This is true for both human and machine detection. We formulate and analyze the performance of maximum likelihood tests for determining the orientation of an object and for discriminating among a set of known objects in a speckled image. We then generalize the tests into three classes of pattern recognition problems, corresponding to orthogonal, antipodal, and biorthogonal signal detection problems. Finally, we compare the performance of these tests to the results of Korwar and Pierce for human interpretation of objects in speckled images.