SMALL TARGET DETECTION IN SEA CLUTTER BASED ON CHAOS

摘要

Traditionally, sea clutter is modeled as a stochastic process, which has a bad performance in small target detection when sea clutter is strong. In recent years, based on the existence of at least one positive Lyapunov exponent and a finite correlation, sea clutter is considered to be chaos, which provides a new idea in analysis of sea clutter. A neural network is well suited to reconstruct the nonlinear dynamics of a chaotic process. In the paper, the RBF network, which is one kind of the neural networks, is trained with the real-life data and a model-based detection method using neural network as a predictor is presented.