GPU-Accelerated Feature Extraction and Target Classification for High-Resolution SAR Images

Synthetic aperture radar automatic target recognition (SAR-ATR) typically consists of 3 main stages: preprocessing(also known as prescreening), feature extraction, and classification. For high-dimensional feature space, the computation time required to construct it by sequential programming is considerably long. In this study, parts of an ATR system, in particular the feature extraction stage, were implemented on Graphics Processing Unit (GPU) for speed up. For Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, the 3-stage ATR process constructing a 28-dimension feature space using 2987 samples performed over 6 times faster running a GPU implemented code than that of a sequential code on average.