W-band maritime target classification using high resolution range profiles

A W-band radar model was developed and tested using six point-scatterer maritime targets to assess the performance of four classifiers: traditional maximum correlation, naïve Bayes, polynomial kernel support vector machine (SVM) and radial basis function (RBF) SVM. W-band is characterized by scintillations caused by subtle aspect and range changes, making classification potentially problematic. High resolution range profiles (HRRPs) were used as the feature vectors with minimal pre-processing. Training and test datasets were generated by rotating the targets in the azimuth plane. A receiver operating characteristic (ROC) analysis was conducted, as well as precision, recall, and accuracy measures derived, and confusion matrices obtained for each classifier under a specific operating point. It was found that the traditional correlation approach performed best under the given circumstances, closely followed by the two SVM approaches and naïve Bayes. It was also found that different classifiers were better suited to classifying particular targets.