Advances on the detection of Landmines and IEDs in Colombia using UWB GPR and Machine Learning Techniques

In this paper we present the latest results of a research program on the use of ground penetrating radar and machine learning-based algorithms for humanitarian demining in Colombia. We describe the experimental setup developed, which includes a polarimetric GPR-UWB unit, a radar positioning system, and a control unit. We describe as well a soil characterization campaign and an IED classification technique based on Support Vector Machine.