Nonlinear clutter cancellation and detection using a memory-based predictor

In this paper, a nonlinear prediction (NLP) method is proposed as an alternative to the conventional linear prediction (LP) method for clutter cancellation. Because of the nonlinearity and non-Gaussianity of a clutter process, a nonlinear predictor is therefore needed to suppress clutter optimally. A memory-based predictor which uses a table look-up strategy to perform NLP is used in this work. The advantages of the memory-based approach are fast learning, algorithmic simplicity, robustness and suitability for parallel implementation. The memory-based predictor is then used as an adaptive detector for small surface target detection embedded in clutter. The effectiveness of the new method is demonstrated using real sea clutter data, and the results show improvement when compared with the conventional LP techniques.