People Counting Based on an IR-UWB Radar Sensor

In this paper, we propose a people counting algorithm using an impulse radio ultra-wideband radar sensor. The proposed algorithm is based on a strategy of understanding the pattern of the received signal according to the number of people, not detecting each of a large number of people in the radar's received signal. To understand the pattern of the signal, we detect the major clusters from the signal and find the amplitudes of main pulses having the maximum amplitude among the pulses constituting each cluster. We generate a probability density function of the amplitudes of the main pulses from the major clusters according to the number of people and distances. Then, we derive maximum likelihood (ML) equation for people counting. Using the derived ML equation, real-time people counting is possible with a small amount of computation. In addition, since the proposed algorithm does not detect individual clusters for each person but based on the overall cluster behavior of the signals according to the number of people, it enables people counting even in a dense multipath environment, such as a metal-rich environment. In order to prove that the proposed algorithm can be operated in real time in various environments, we performed experiments in an indoor environment and an elevator with a metal structure. Experimental results show that people counting is performed with an mean absolute error of less than one person on average.