Autonomous time-frequency morphological feature extraction algorithm for LPI radar modulation classiflcation

An autonomous (no human operator intervention) feature extraction algorithm that can be used for classification of low probability of intercept (LPI) radar modulations using time-frequency (T-F) images is presented. The approach uses erosion and a new adaptive threshold binarization algorithm embedded within a recursive dilation process to autonomously determine the modulation energy centroid (radar's carrier frequency). The modulation is then cropped from the original T-F image and the adaptive algorithm is used again to compute a binary feature vector for input into a multi-layer perceptron classification network. Classification results for five simulated radar modulations are shown to demonstrate the feature extraction approach and quantify the performance of the algorithm.