Recognition system of Underground Object Shape using ground penetrating radar datagram

摘要

Objects that have been buried underground cannot be recognized due to the opaqueness of the soil. To recognize objects that have been buried, ground penetrating radar (GPR) by the assistance of computer-aided system was used. This paper proposes the latter, which is called the Recognition System of Underground Object Shape using GPR datagram. The hyperbola from cylinder and cube metal object that had been buried in the ground is differentiated using two features of their respective A-scans. The two features are skewness and standard deviation. The percentage accuracy using Artificial Neural Network (ANN) Classification System approach was used to determine the shape of underground object. This technique was applied on 102 datagram in the form of A-scans signal using GPR. Results collected have shown very high percentage of accuracy. Therefore, it is suggested that this technique is capable to obtain shape of underground with the assistance of GPR.