Surface Ship Classification in a Littoral Environment using Fusion of Hydroacoustic and Electromagnetic Data

Abstract

In this paper we investigate if underwater electrode arrays can complement hydrophones in passive surveillance situations with occasionally poor hydroacoustic conditions. The application is classification of passing surface ships as either light or heavy. Different signal processing and fusion techniques are compared in conjunction with a support vector machine classifier. It is shown that in some situations, the fusion of electrode and hydroacoustic data actually improves the performance of the passive surveillance system. At best, our system correctly classifies 22 ship passages out of 23 possible.