A novel landmine detection system based on within and between subclasses dispersion information

ABSTRACT

Abstract: Millions of anti-personnel landmines have been left in the ground during war conflicts in many countries, which causes many security, humanitarian and economic problems. It is therefore necessary to develop an automatic and efficient technique for landmines detection and localization, in order to clear the existing minefields. Ground-penetrating radar (GPR) is a geophysical method that is able to detect any buried object in the soil, but it suffers from high false alarm rate. Several landmine detection and localization systems have been developed, using GPR data and based on competitive classification methods, such as the One-class Support Vector Machine (OSVM), which handles the common problem of unbalanced data, in a proper manner. Nevertheless, in the landmine detection problem, we assume that the target class is composed of several subclasses related to metallic contents, which are not considered by related classification methods, including OSVM. For this reason, in this paper, we propose a subclass landmine detection and localization system based on a novel variation of the OSVM that takes into account the existence of subclasses in the landmine target class in order to jointly minimize the within and between subclass dispersion and to estimate the optimal decision function. Our proposed landmine detection and localization method has been evaluated and compared to other methods based on relevant one-class classifiers, on several real-world datasets extracted from the well-known MACADAM database. Experimental results have shown clearly that our proposed method is competitive with the existing relevant one-class classifiers, in landmine detection.

Acknowledgements

We thank the ōbex project for language editing support.

Disclosure statement