Reliable target feature extraction and classification using potential target information

A reliable target feature extraction process is proposed in this paper. The locations of dominant scatterers have been widely adopted as target features in automatic target recognition (ATR) systems. However, the direct use of the locations shows high variability and results in a negative effect on target classification performance. Here, we propose a novel grid cell structure that uses information regarding potential targets to be classified. The grid cell structure extracts stable features from SAR images with a relatively lower computational complexity. A novel target feature that uses information about the variability of scatterers is also proposed. Simulation results, using real target measurements taken from the MSTAR dataset, demonstrate that the new feature vectors improve classification performance.