Radio tomographic imaging and tracking of stationary and moving people via kernel distance

Network radio frequency (RF) environment sensing (NRES) systems pinpoint and track people in buildings using changes in the signal strength measurements made by a wireless sensor network. It has been shown that such systems can locate people who do not participate in the system by wearing any radio device, even through walls, because of the changes that moving people cause to the static wireless sensor network. However, many such systems cannot locate stationary people. We present and evaluate a system which can locate stationary or moving people, without calibration, by using kernel distance to quantify the difference between two histograms of signal strength measurements. From five experiments, we show that our kernel distance-based radio tomographic localization system performs better than the state-of-the-art NRES systems in different non line-of-sight environments.

1. Introduction

Localization of people using wireless sensor networks has significant benefits in elder care, security, and smart facility applications [3], [19], [20]. Standard “radio localization” systems locate a transmitter tag, or allow a receiver to estimate its position [3], [16]. For these mentioned applications, it is critical to be able to locate all people, regardless of whether they carry a radio device. In this paper, we explore “network RF environment sensing” (NRES), that is, using a static wireless sensor network to create an image map of the people and objects and thus locate them in an area of interest based on the changes they cause in the radio frequency (RF) environment. An extensive review of reported NRES research can be found in [20]. NRES is also called “device-free localization” [25], “passive localization” [28], or “sensor-less sensing” [26]. Unlike infrared or thermal, RF penetrates non-metal walls, and thus NRES is useful for emergency applications. For example, in a hostage situation, police could deploy wireless devices outside of the building and learn in real time where people are located in the building, information that may save live. NRES systems can also be used in emergency situations to help rescuers like firefighters locate victims.