Particle Center Supported Plane for Subsurface Target Classification based on Full Polarimetric Ground Penetrating Radar

Abstract

The subsurface target classification of ground penetrating radar (GPR) is a popular topic in the field of geophysics. Among the existing classification methods, geometrical features and polarimetric attributes of targets are primarily used. As polarimetric attributes contain more information of targets, polarimetric decomposition methods, such as H-Alpha decomposition, have been developed for target classification of GPR in recent years. However, the classification template used in H-Alpha classification is preset depending on the experience of synthetic aperture radar (SAR); therefore, it may not be suitable for GPR. Moreover, many existing classification methods require excessive human operation, particularly when outliers exist in the sample (the data set containing the features of targets); therefore, they are not efficient or intelligent. We herein propose a new machine learning method based on sample centers, i.e., particle center supported plane (PCSP). The sample center is defined as the point with the smallest sum of distances from all points in the same sample, which is considered as a better representation of the sample without significant effect of the outliers. In this proposed method, particle swarm optimization (PSO) is performed to obtain the sample centers; the new criterion for subsurface target classification is achieved. We applied this algorithm to full polarimetric GPR data measured in the laboratory and outdoors. The results indicate that, comparing with support vector machine (SVM) and classical H-Alpha classification, this new method is more efficient and the accuracy is relatively high.

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

“…where w is the inertia weight; r1, r2 are two random numbers between 0 to 1; c1, c2 are learning factors [28]. The iteration continues till the variation of PC is less than a threshold μ:…”

“…However, these methods are all based on the theory of SAR. Since some differences of measurement exist between GPR and SAR, such as the medium and distance of propagation for electromagnetic waves, observation methods, and noise characteristics, the polarimetric analysis methods used in SAR may not be suitable for GPR [28]. Therefore, we have proposed a particle center based method [28] before to modified the H-Alpha identification method.…”

“…Since some differences of measurement exist between GPR and SAR, such as the medium and distance of propagation for electromagnetic waves, observation methods, and noise characteristics, the polarimetric analysis methods used in SAR may not be suitable for GPR [28]. Therefore, we have proposed a particle center based method [28] before to modified the H-Alpha identification method. Particle center is a type of proposed data center which is a better representation of the sample with fewer effects of the outliers [28] and can enhance the identification ability of FP-GPR.…”

“…Therefore, we have proposed a particle center based method [28] before to modified the H-Alpha identification method. Particle center is a type of proposed data center which is a better representation of the sample with fewer effects of the outliers [28] and can enhance the identification ability of FP-GPR. However, this method is mainly for the double-parameters classification such as the H and α features and has difficulties when it is promoted to multi-parameter identification.…”

“…16(b) is surrounded by the other data and two weak classifiers are needed to identify the orange histogram. The error curve 1 with red color is computed using (28), whereas the error curve 2 with blue color is computed using the formula below:…”