Home // International Journal On Advances in Networks and Services, volume 9, numbers 1 and 2, 2016 // View article

Multi-Target Data Association in Binary Sensor Networks for Ambulant Care Support

Authors:
Sebastian Matthias Müller
Andreas Hein

Keywords: Multi-target tracking; Assisted living; Wireless sensor networks; home automation; smart homes; telemedicine

Abstract:
Numerous applications of home automation, security and ambulant medical care use binary sensors such as passive infrared motion sensors or light barriers to monitor activity in the house. While the data of individual sensors does not facilitate the recognition and separation of the presence of more than one person, there exist multi-target tracking algorithms that allow for at least a partial separation of activity in data from multiple persons. While many tracking algorithms demonstrate good performance across various sensing modalities and sensor setups, little research has been done to determine the impact of placement and varying density of sensors for tracking performance. This paper presents the results of two evaluations of a Bayesian multi-hypothesis multi-target tracking algorithm on data of residents monitored by a network of binary sensors. The algorithm’s performance is evaluated across varying quantity and placement. It is shown that the approach outperforms other approaches in low-resolution setups using data collected in a home lab and further demonstrate its applicability in a field trial across three households. While tracking performance naturally decreases with the number of sensors, it also strongly varies by sensor positioning.

Pages: 20 to 29

Copyright: Copyright (c) to authors, 2016. Used with permission.

Publication date: June 30, 2016

Published in: journal

ISSN: 1942-2644