FHWS/Fusion2016
Archived
3
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

added abstract

Browse Source
This commit is contained in:
Toni
2016-02-13 14:45:36 +01:00
parent 997c31e2c2
commit fcf5f7b437
1 changed files with 8 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
tex/chapters/abstract.tex
View File

@@ -1,19 +1,11 @@
\begin{abstract} \begin{abstract}
DUMMY ABSTRACT. We present an indoor localisation system that integrates different sensor modalities, Navigating to a desired destination is a key aspect of indoor localisation. Up to this point many different systems using present or past information for estimating the pedestrian's position were presented.
namely Wi-Fi, barometer, iBeacons, step- and turn-detection for localisation of pedestrians within buildings Our work proposes a novel approach that incorporates prior navigation knowledge by using realistic human walking paths.
over multiple floors. To model the pedestrian's movement, which is constrained by walls and other obstacles, In order to create such paths, we present a method that assigns an importance factor to every node of a regular tessellated graph by avoiding walls and detecting doors.
we propose a state transition based upon random walks on graphs. The human movement is then modelled by moving along adjacent nodes into the most proper walking-direction.
%This model also frees us from the burden of frequently updating the system. To be able of going into the 3rd dimension, realistically shaped stairs for step-wise floor changes are used.
In addition we make use of barometer information to estimate the current floor. The position is estimated over multiple floors integrating different sensor modalities, namely Wi-Fi, iBeacons, barometer, step-detection and turn-detection.
\commentByFrank{entweder alle sensoren nennen, oder weglassen? sonst wirkt es nicht schluessig}ds The system was tested by omitting any time-consuming calibration process and starting with a uniform distribution instead of a well known pedestrian location.
Furthermore, we present a statistical approach to avoid the incorporation of faulty heading information caused The evaluation shows that adding prior knowledge is able to improve the localisation, even for unpredictable behaviour, faulty measurements and for poorly chosen system parameters.
by changing the smartphone's position.
\commentByFrank{ueber statistical reden wir nochma. einerseits ja, andererseits irgendwie nein.}
The evaluation of the system within a $\SI{77}{\meter}$ $\times$ $\SI{55}{\meter}$ sized building with 4 floors
shows that high accuracy can be achieved while also keeping the update-rates low.
\commentByFrank{We will show that incorporating prior knowledge, such as the pedestrian's desired destination,
improves the overall localisation process and prevents various error-conditions.}
\commentByToni{Das ist der alte Abstract vom letzten Paper. :D Da wollte ich noch nen ganz neuen schreiben. Das mach ich aber immer gaaaanz am ende}
\end{abstract} \end{abstract}