Generalized Hough Transform and ANN for subsurface cylindrical object location and parameters inversion from GPR data

Targets location and parameter inversion are always active research field of Ground Penetrating Radar (GPR) and useful to address some challenges in civil and military applications. Since the amplitude and delay of receiving signal could correspondingly change due to varying of the dimension, and material of targets, permittivity of background. So, in this paper, we present a new framework integrated Generalized Hough Transform (GHT) with neural network to reconstruct their non-linear relationship and implement targets location and parameter inversion. The results based on simulated data demonstrate the high accuracy.