RBF kernel based SVM classification for landmine detection and discrimination

Abstract

Ground Penetrating Radar (GPR) is used for subsurface exploration across different applications like landmines detection. It can detect and deliver the response of any buried kinds of object, however it cannot discriminate between landmines and false alarms. In this paper, we propose a detection method based on support vector machine (SVM) using one-dimensional GPR delivered data called Ascans. Each Ascan data is considered as a feature input for the proposed SVM classifier based on RBF Kernel. This method is tested on MACADAM database. Used data includes responses of different kind of landmines (targets) and responses of other objects (outliers) like alusquare, wood stick, pine, sodacan and stone buried in different types of soils. In order to evaluate the performance of our detection method, we have used three evaluation measures which are the Receiver Operating Characteristic (ROC) curves, the Area Under the Curve for the ROCs (AUC) and the running time. We have obtained 94.71% as AUC and 1.028s as running time. So, experimental results prove that the proposed method can successfully detect landmines and discriminate between targets and outliers.