Detection of Shallowly Buried Landmines Using Sequential Ground Penetrating Radar Signals

Abstract

Detection of shallowly buried landmines using ground penetrating radar (GPR) signals is studied. Detector employed here is designed by using hidden Markov models (HMMs) to characterize the sequential information in GPR signals. In order to check the performance of the detector, it is applied to example data calculated by using a two-dimensional FDTD method. Detection performance is presented for receiver operating characteristic (ROC) curves. The results show that good detection performance is obtained even for landmines buried at shallow depths under a rough ground surface where the responses from the landmines and those from the ground surface overlap in time.