Sensor-Data Fusion for Multi-Person Indoor Location Estimation

Abstract

We consider the problem of estimating the location of people as they move and work in indoor environments. More specifically, we focus on the scenario where one of the persons of interest is unable or unwilling to carry a smartphone, or any other “wearable” device, which frequently arises in caregiver/cared-for situations. We consider the case of indoor spaces populated with anonymous binary sensors (Passive Infrared motion sensors) and eponymous wearable sensors (smartphones interacting with Estimote beacons), and we propose a solution to the resulting sensor-fusion problem. Using a data set with sensor readings collected from one-person and two-person sessions engaged in a variety of activities of daily living, we investigate the relative merits of relying solely on anonymous sensors, solely on eponymous sensors, or on their combination. We examine how the lack of synchronization across different sensing sources impacts the quality of location estimates, and discuss how it could be mitigated without resorting to device-level mechanisms. Finally, we examine the trade-off between the sensors’ coverage of the monitored space and the quality of the location estimates.

Next Generation Wireless Technologies for Internet of Things

“…The results exhibited by the authors confirm not only the effectiveness of monitoring through their platform but that in specific contexts the installation of a wireless sensor network may be the best choice since it is less invasive compared to a wired solution. On the contrary, the problem of estimating the location of multiple individuals moving and interacting in an indoor space is analyzed in [ 11 ]. In this case, the authors propose a multi-sensor data-fusion framework, relying on a unifying location-estimate representation as a confidence map of the indoor space.…”

An Indoor Positioning Approach Based on Fusion of Cameras and Infrared Sensors

“…In [30] a fusion application with a similar approach as the one we present in this paper, combining the observations with covariance-matrix weights and running Monte Carlo simulations to test models and further comparison with real measurements is shown. An Interesting approach [31] where motion sensors and Bluetooth Low Energy (BLE) beacon are fused by means of a weighted sum.…”

An Indoor Positioning Approach Based on Fusion of Cameras and Infrared Sensors

“…shown. An Interesting approach [31] where motion sensors and BLE (Bluetooth Low Energy) beacon are fused by means of a weighted sum.…”