Advanced Signal Processing & Classification: UXO Standardized Test Site Data

Abstract : Our objective was to study discrimination capabilities of feature based characterization and classification techniques using standard survey data acquired by others at the UXO Standardized Test Sites in APG and YPG. The fundamental issues investigated included the model used during characterization and the impact that classifier selection has on classification performance. After re-leveling and lagging the EM61 cart data, we inverted anomaly data for each data type using dipole, ellipsoidal, empirical, loop fit, joint frequency-time domain, and singularity expansion models. We then classified the resulting feature vectors with SVM, RVM, GLRT, and KNN statistical classifiers. We evaluated classification performance using two metrics derived from ROC curves; namely, (i) the total area under the curve and (ii) the probability of false alarms at 0.95 probability of detection. We selected five data sets to include in this study based on data quality, type, signalto- noise, and availability at appropriate intermediate processing stages. The datasets included time-domain EM61 (man-towed single sensor cart and vehicle-towed array), time-domain EM63, frequency-domain GEM-3, and magnetic data. None of the classifiers or sensor/model combinations performed extremely well when the targets of interest (TOI) included 20mm- through 155mm-projectiles. Classification performance measures, defined here using area under the curve, were 0.8 for the best case(s). Additionallyh, all classifiers or sensor/model combinations produced multiple false negatives. False alarm rates, at a detection performance of 0.95, were as high as 0.95. Simplifying the problem by artificially limiting the UXO by size or by analyzing data acquired in a cued deployment did improve classification performances. Segmenting the UXO by size classes improved classification in direct proportion to the extent that the features of the UXO and clutter classes were separable.