Title :
Sensor placement for indoor multi-occupant tracking
Author :
Masoud Vatanpour Azghandi;Ioanis Nikolaidis;Eleni Stroulia
Author_Institution :
Computing Science Department, University of Alberta, Edmonton, Alberta, Canada
fDate :
7/1/2015 12:00:00 AM
Abstract :
We consider the problem of localizing and tracking multiple occupants in an indoor space, where the occupants are tagged with RFID tags and the space is embedded with anonymous (Passive Infrared, PIR) motion sensors and identity (RFID reader) sensors. Our localization method uses the RFID readings to disambiguate the occupants´ trajectories recognized by the motion sensors. Due to their high cost and generally cumbersome placement requirements, RFID readers must be judiciously placed; in this paper, we study the placement of the readers such that the occupants´ trajectory ambiguity is reduced. We rely on a heatmap representing the frequency with which individuals visit locations as they move through the indoor space and on models of coverage for the PIR sensors and RFID readers and develop a heuristic for the RFID reader placement. We demonstrate the effectiveness of our method via simulations.
Keywords :
"Radiofrequency identification","Trajectory","Space heating","Tracking","Signal processing algorithms","Heuristic algorithms"
Conference_Titel :
Information, Intelligence, Systems and Applications (IISA), 2015 6th International Conference on
DOI :
10.1109/IISA.2015.7388030