Predicting an upper bound on SAR ATR performance

We present a method for predicting a tight upper bound on performance of a vote-based approach for automatic target recognition (ATR) in synthetic ape rture radar (SAR) images. In such an approach, each model target is represe nted by a set of SAR views, and both model and data views are represented b y rations of scattering centers. The proposed method considers data distort ion factors such as uncertainty, occlusion, and clutter, as well as model f actors such as structural similarity. Firstly, we calculate a measure of th e similarity between a given model view and each view in the model set, as a function of the relative transformation between them. Secondly, we select a subset of possible erroneous hypotheses that correspond to peaks In simi larity functions obtained in the first step. Thirdly, we determine an upper bound on the probability of correct recognition by computing the probabili ty that every selected hypothesis gets less votes than those for the model view under consideration. The proposed method is validated using MSTAR publ ic SAR data, which are obtained under different depression angles, configur ations, and articulations.