Application of artificial neural networks for fusion of data from radar and depth sensors applied for persons’ monitoring

Abstract

The research reported in this paper is related to the fusion of measurement data from the impulse-radar sensors and infrared depth sensors applied in a system for unobtrusive monitoring of elderly persons. Three methods for data fusion, based on the artificial neural networks – one trained on real-world data, and two trained on synthetic data generated on the basis of two different models of the data – are compared with respect to their capacity of decreasing the uncertainty of position estimation in a series of experiments which involved the tracking of a moving person.