How can data fusion help humanitarian mine action?

Abstract

In this article, we present our views regarding multi-sensor data fusion potentials to help two types of humanitarian mine action: close-in detection and mined area reduction. Several approaches are discussed, reflecting our thoughts and experience in this extremely sensitive field of application. For close-in detection, our work on modelling and fusion of extracted features is based on two main methods, one related to the belief function theory and the other one to the possibility theory. The approaches are tested using real data coming from three complementary sensors (ground-penetrating radar, infrared sensor, and metal detector), collected within the Dutch HOM-2000 project. These results are obtained within two Belgian humanitarian demining projects, HUmanitarian DEMining (HUDEM) and Belgian Mine Action Technology (BEMAT). In the case of mined area reduction, our multi-sensor data fusion methods are based on the belief function theory and on the fuzzy logic and applied to real data of synthetic-aperture radar and multi-spectral sensors, gathered within the EU project on Space and Airborne Mined Area Reduction Tools (SMART). The importance of including various knowledge sources is discussed too.