Automatic target recognition using multi-diversity radar

The information content of radar target signatures is a key aspect for automatic target recognition. The role of high-range resolution is investigated as a function of the illuminating wavelength. The classification performance is evaluated using (i) full-scale 2D inverse synthetic aperture radar images obtained from a stepped-frequency chirp modulation radar system and (ii) the corresponding sub-spectra of the target reflectivity function forming lower resolution images at differing centre frequencies. The classification performance as given by different combinations of RF frequencies are also evaluated and compared with the coherent reconstruction from the full bandwidth. Finally, the classification results are also computed using multiple aspects to sense the target. In this way, classification performance as function of diversity space is examined.