New variations of MINACE filters are considered for detection and recognition of objects and rejection of clutter in synthetic aperture radar (SAR) data. Multiple classes of objects with distortions present must be handled. Good performance in the presence of object obscurations is also needed. We present initial very attractive results that aid different modules in a SAR automatic target recognition processor. For 4 class test set data, we show detection performance of PD > 99.8 percent with PFA is congruent to 0.026/km2; for classification we show PC > 96.6 percent with PFA is congruent to 0.026/km2. Selected tests with noise and obscurations present and of object in real SAR background are also included. All results used full shift-invariance tests.
David P. Casasent,
"SAR detection and recognition filters", Proc. SPIE 3070, Algorithms for Synthetic Aperture Radar Imagery IV, (28 July 1997); doi: 10.1117/12.281550; https://doi.org/10.1117/12.281550