Multiparameter Adaptive Target Classification Using Full-Polarimetric GPR: A Novel Approach to Landmine Detection

Abstract

Full-polarimetric ground penetrating radar (FP-GPR) can measure the ability of an object to change the polarization of electromagnetic waves. Compared to the traditional GPR, it has a stronger capability to identify underground objects. In recent years, a series of polarization decomposition methods have been applied to the FP-GPR data processing to obtain the polarimetric attributes and enhance the capability of targets identification. Different polarimetric attributes characterize different features of a target but there is still no effective way to integrate these attributes and take their respective advantages for target classification. In this article, we propose a particle center AdaBoost (PCAD) method and achieve the multiparameter adaptive target identification. The experimental results indicate that the PCAD method can automatically select suitable parameters during the training process for different targets. Compared to the single-parameter classification and the AdaBoost methods based on the traditional average and Bagging method, the PCAD method presents higher correct rates in classification. Finally, the proposed method is applied to landmine detection. The results demonstrate that the landmine is a composite scatterer that can generate surface scattering signals on its surface and dipole and volume scattering signals from its interior; based on the color-coded two-dimensional image by PCAD, we can distinguish landmines from other targets.