How transferable are downward-looking and handheld ground penetrating radar data? Experiments in the context of buried threat detection

摘要

In this work we consider the problem of developing algorithms for the automatic detection of buried threats usinghandheld Ground Penetrating Radar (HH-GPR) data. The development of algorithms for HH-GPR is relativelynascent compared to algorithm development efforts for larger downward-looking GPR (DL-GPR) systems. One ofthe biggest bottlenecks for the development of algorithms is the relative scarcity of labeled HH-GPR data that can beused for development. Given the similarities between DL-GPR data and HH-GPR data however, we hypothesizedthat it may be possible to utilize DL-GPR data to support the development of algorithms for HH-GPR. In this workwe assess the detection performance of a HH-GPR-based BTD algorithm as we vary the amounts and characteristicsof the DL-GPR data included in the development of HH-GPR detection algorithms. The results indicate thatsupplementing HH-GPR data with DL-GPR does improve performance, especially when including data collected overburied threat locations.