A Novel Threshold Optimization Technique for CFAR Detection in Weibull Clutter using Fuzzy-Neural Networks

This work provides an effective approach based on adaptive neuro-fuzzy inference system to the solution of constant false alarm rate (CFAR) detection for Weibull clutter statistics. The optimal detection thresholds of the ML-CFAR (maximum-likelihood CFAR) detector in Weibull clutter with unknown shape parameter are obtained using fuzzy-neural networks (FNN) technique. The genetic learning algorithm (GA) is applied for the training of the FNN threshold estimator. The proposed FNN-ML-CFAR algorithm proved to be efficient particularly in the case of spiky clutter. Experimental results showed the effectiveness of an adaptive neurofuzzy threshold estimator under different system conditions and it is also shown that the FNN-ML-CFAR detector can achieve better performances than the conventional ML-CFAR algorithm.