Comparison of sixteen methods for fusion of data from impulse-radar sensors and depth sensors applied for monitoring of elderly persons

Abstract

This paper is devoted to the comparison of sixteen methods for fusion of measurement data from impulse-radar sensors and infrared depth sensors, i.e. two sensor technologies that may be employed in care services for elderly persons. These methods are compared with respect to their potential for decreasing the uncertainty of estimation of monitored person’s position: eight of them consist in fusing the impulse-radar data and depth data whenever new data points are available, and the other eight consist in fusing the whole sequences of the data acquired during a predefined time interval. The numerical experiments, based on the real-world data, show that the best overall results are obtained for two methods of data fusion, viz. a method based on the Kalman filter and a method using the Tikhonov regularization technique to generate a smooth approximation of the data.