MACHINE LEARNING METHODS APPLIED IN DETECTION OF BURIED TARGETS FOR GROUND PENETRATING RADAR

The Ground penetrating radar (GPR) is a nondestructive tool to detect buried objects for infrastructure maintenance, archeological surveys, military application and other use. After analyzing the one-dimensional (A-scan), two-dimensional (B-scan) or three-dimensional (C-scan) images of GPR, the position and material of targets can be recognized. And machine learning techniques has become more popular in the data processing of GPR because their relative low cost, high speed and high accuracy. In this work, the application of some machine learning methods such as support vector machine (SVM), dictionary Learning (DL), neural networks (NNs) and hidden Markov models (HMMs) in the GPR for the detection of underground targets will be introduced.