Logo Logo
Switch Language to German
Schauer, Lorenz; Marcus, Philipp; Linnhoff-Popien, Claudia (2016): Towards Feasible Wi-Fi based Indoor Tracking Systems Using Probabilistic Methods. 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 4-7 October 2016, Alcalá de Henares, Madrid, Spain.
Full text not available from 'Open Access LMU'.


Wi-Fi enabled devices periodically broadcast unencrypted management information which can easily be used for an involuntary tracking of users in an area of interest. However, reliable trajectory estimations on this data remain challenging, due to arbitrary and imprecise position fixes of moving targets. Probabilistic methods can help to increase the estimation accuracy significantly, but may degrade other important metrics, e.g. scalability, complexity, or robustness. In this paper, we investigate probabilistic solutions for a feasible tracking system for indoor scenarios. Beside the usage of Viterbi's algorithm and a common particle filter, we propose a novel state particle filter with a more restricted transition model based on discrete state nodes. All methods are compared and evaluated on various user traces using real Wi-Fi captures from common mobile devices at our office building. The results indicate that the proposed state particle filter performs best in terms of accuracy, and precision while using a smaller amount of particles which renders this approach scalable, and thus, feasible for indoor tracking systems.