An exploration of gradient based features for buried threat detection using a handheld ground penetrating radar

摘要

In this work we consider the problem of developing algorithms for the automatic detection of buried threats inhandheld Ground Penetrating Radar (HH-GPR) data. The development of algorithms for HH-GPR is relativelynascent compared to larger downward-looking GPR (DL-GPR) systems. A large number of buried threat detection(BTD) algorithms have been developed for DL-GPR systems. Given the similarities between DL-GPR data and HHGPRdata, effective BTD algorithm designs may be similar for both modalities. In this work we explore theapplication of successful class of DL-GPR-based algorithms to HH-GPR data. In particular, we consider the class ofalgorithms that are based upon gradient-based features, such as histogram-of-oriented gradients (HOG) and edgehistogram descriptors. We apply a generic gradient-based feature with a support vector machine to a large dataset ofHH-GPR data with known buried threat locations. We measure the detection performance of the algorithm as wevary several important design parameters of the feature, and identify those designs that yield the best performance.The results suggest that the design of the gradient histogram (GH) feature has a substantial impact on its performance.We find that a tuned GH algorithm yields substantially-better performance, but ultimately performs similarly to theenergy-based detector. This suggests that GH-based features may not be beneficial for HH-GPR data, or that furtherinnovation will be needed to achieve benefits.