A Novel Indoor Tracking Algorithm Based on Particle Filter

DOI

10.2991/icimm-15.2015.214How to use a DOI?

Keywords

Indoor positioning; Location fingerprint; Particle filter; Tracking

Abstract

Nowadays target tracking has become a hot issue of indoor positioning in the military or civilian areas. Due to the nonlinear characteristics of the indoor environment, there exist some difficulties in indoor tracking scheme. In this paper, we proposed an indoor tracking algorithm based on particle filter. RSS values were severed as the observed values and the naive Bayesian algorithm was used to collect RSS samples for estimating the probability density distribution as a location fingerprinting in our proposed algorithm. Then a system of track model was created. Moreover, particle filter was introduced in order to process positioning error which was brought by system noise and observation noise and solve tracking problems of mobile terminal. Experimental results show our algorithm achieves great accuracy and robustness in tracking trajectory aspect and performs better than the tracking algorithm using Kalman filter.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiayan Zhu
AU  - Meng Wu
PY  - 2015/07
DA  - 2015/07
TI  - A Novel Indoor Tracking Algorithm Based on Particle Filter
BT  - Proceedings of the 5th International Conference on Information Engineering for Mechanics and Materials
PB  - Atlantis Press
SP  - 1196
EP  - 1200
SN  - 2352-5401
UR  - https://doi.org/10.2991/icimm-15.2015.214
DO  - 10.2991/icimm-15.2015.214
ID  - Zhu2015/07
ER  -