Naval Target Classification Based on the Confusion Matrix

In this paper, we propose an algorithm for the classification of naval targets, which is based on the fusion of the class information provided by three imaging sensors: a video camera, an infrared (IR) camera, and an airborne radar operating in spotlight Synthetic Aperture Radar (SAR) mode. The purpose of the fusion process is to elaborate the outputs of these three imaging sensors in order to obtain an accurate and reliable estimate of the target class. The performance of each imaging sensor is modelled by means of its confusion matrix (CM). The entries of the matrix are used to make the decision on the target class by each sensor. Then a final decision on the class is made, using an appropriate fusion rule in order to combine the decisions coming from the three sensors. Two decision rules are compared: a majority voting rule and a maximum likelihood rule. The overall performance of the classification process is evaluated by means of the "fused" confusion matrix, i.e. the matrix pertinent to the final decision on the target class. The main contribution of this approach is the development of a methodology that allows to easily include the classification process inside the Monte Carlo simulator of a large integrated system, without increasing its overall computational load.