Medvesek, J;
Symington, A;
Trost, A;
Hailes, S;
(2015)
Gaussian process inference approximation for indoor pedestrian localisation.
Electronics Letters
, 51
(5)
pp. 417-419.
10.1049/el.2014.4436.
![[thumbnail of ELL-2014-4436.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) Preview |
Text
ELL-2014-4436.pdf Available under License : See the attached licence file. Download (360kB) |
Abstract
Clutter has a complex effect on radio propagation, and limits the effect- iveness of deterministic methods in wireless indoor positioning. In contrast, a Gaussian process ( GP ) can be used to learn the spatially correlated measurement error directly from training samples, and build a representation from which a position can be inferred. A method of exploiting GP inference to obtain measurement predictions from within a pose graph optimisation framework is presented. However, GP inference has a run-time complexity of O ( N 3 ) in the number of train- ing samples N , which precludes it from being called in each optimiser iteration. The novel contributions of this work are a method for building an approximate GP inference map and an O (1) bi-cubic interpolation strategy for sampling this map during optimisation. Using inertial, magnetic, signal strength and time-of- fl ight measurements between four anchors and a single mobile sensor, it is shown empirically that the presented approach leads to decimetre precision indoor pedestrian localisation
| Type: | Article |
|---|---|
| Title: | Gaussian process inference approximation for indoor pedestrian localisation |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1049/el.2014.4436 |
| Publisher version: | http://dx.doi.org/10.1049/el.2014.4436 |
| Language: | English |
| Additional information: | This paper is a postprint of a paper submitted to and accepted for publication in Electronics Letters and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library |
| Keywords: | Gaussian processes, approximation theory, interpolation, clutter, indoor radio, pedestrians, radionavigation, graph theory, computational complexity, optimisation, iterative methods, Gaussian process inference approximation, indoor pedestrian localisation, clutter, radio propagation, deterministic methods, wireless indoor positioning, spatially correlated measurement error, training samples, GP inference method, pose graph optimisation framework, run-time complexity, optimiser iteration, O(1) bi-cubic interpolation strategy, signal strength, time-of-flight measurements, magnetic strength, inertial strength, single mobile sensor, decimetre precision indoor pedestrian localisation |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1467275 |
Archive Staff Only
 |
View Item |
