UXO classification procedures applied to advanced EMI sensors and models

Unexploded Ordnances (UXO) classification procedure consists of the following: background subtractions, data inversions and targets feature parameters estimations, and separating UXO from non-hazardous anomalies. First, each dataset is normalized by a corresponding Tx-current; then, all data files are background subtracted; third, the background corrected data are inverted and targets intrinsic (effective polarizabilities) and extrinsic (locations) are extracted; next, the extracted intrinsic and extrinsic parameters are used for generating prioritized and training targets lists; Finally, once the ground truth for training targets are provided, then prioritized targets are reclassified and final dig list is created. In this paper, the detailed steps of UXO classification procedure using the advanced EMI sensors and models are presented along with the processing and analysis approaches that are used to generate a prioritized dig list.