Determining the coordinates of objects detected by a 1Tx + 4Rx antenna system using an artificial neural network; free space case

Abstract

We investigated the implementation of artificial neural networks in the detection and discrimination of landmines and similar objects. The experimental data were obtained by using impulse GPR with a 1 Tx + 4Rx antenna system. The possibility of improving the input data by the moving average method was shown. Object identifications and positions are perfect for low noise and for object positions directly under the antenna array. Accuracy declines with increased noise and with distance from the antenna array. For positions of objects that are offset from the training data, the position is still determined with the greatest possible accuracy. The artificial neural network has proven successful in the task of determining the type and positions of the test objects.