Sensor-Data Fusion for Multi-Person Indoor Location Estimation
AbstractWe 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. View Full-Text
Share & Cite This Article
Mohebbi, P.; Stroulia, E.; Nikolaidis, I. Sensor-Data Fusion for Multi-Person Indoor Location Estimation. Sensors 2017, 17, 2377.
Mohebbi P, Stroulia E, Nikolaidis I. Sensor-Data Fusion for Multi-Person Indoor Location Estimation. Sensors. 2017; 17(10):2377.Chicago/Turabian Style
Mohebbi, Parisa; Stroulia, Eleni; Nikolaidis, Ioanis. 2017. "Sensor-Data Fusion for Multi-Person Indoor Location Estimation." Sensors 17, no. 10: 2377.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.