Automatic target detection using a dynamic learning neural network

Automatic detection of targets in a radar image is an important problem with many applications. The radar echoes from a target have to compete with the echoes from the clutter. A clutter signal can be modeled by a nonlinear deterministic dynamical system. A dynamic learning neural network is used to approximate the nonlinear system in terms of the polynomial basis function. As an example, the neural network is applied to a SAR image from the MSTAR public release data set for target detection. The results suggest that the proposed approach provides better detection evaluation measures, including detection rate, false detection rate, and lose detection rate than those of the conventional CFAR detector.