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

introduction as far as possible at this point in time

Browse Source
This commit is contained in:
Toni
2016-01-25 23:03:15 +01:00
parent cada10cbe4
commit f3856d9473
2 changed files with 6 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tex/chapters/abstract.tex
View File

@@ -1,5 +1,5 @@
\begin{abstract} \begin{abstract}
We present an indoor localisation system that integrates different sensor modalities, namely Wi-Fi, barometer, iBeacons, step-detection and turn-detection for localisation of pedestrians within buildings over multiple floors. To model the pedestrian's movement, which is constrained by walls and other obstacles, we propose a state transition based upon random walks on graphs. This model also frees us from the burden of frequently updating the system. In addition we make use of barometer information to estimate the current floor. Furthermore, we present a statistical approach to avoid the incorporation of faulty heading information caused by changing the smartphone's position. DUMMY ABSTRACT. We present an indoor localisation system that integrates different sensor modalities, namely Wi-Fi, barometer, iBeacons, step-detection and turn-detection for localisation of pedestrians within buildings over multiple floors. To model the pedestrian's movement, which is constrained by walls and other obstacles, we propose a state transition based upon random walks on graphs. This model also frees us from the burden of frequently updating the system. In addition we make use of barometer information to estimate the current floor. Furthermore, we present a statistical approach to avoid the incorporation of faulty heading information caused by changing the smartphone's position.
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. 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.
\end{abstract} \end{abstract}

38
tex/chapters/introduction.tex
View File

@@ -6,35 +6,14 @@ Most modern indoor localisation systems primarily use smartphones for determinin
%Therefore, the most accurate position is represented by a peak of the probability distribution. %Therefore, the most accurate position is represented by a peak of the probability distribution.
In our previous work we were able to present such a localisation system based on all the above mentioned sensors including the phone's barometer \cite{Ebner-15}. In our previous work we were able to present such a localisation system based on all the above mentioned sensors including the phone's barometer \cite{Ebner-15}.
In pedestrian navigation, the human movement underlies the characteristics of walking speed and walking direction. Additionally, environmental restrictions need to be considered as well, for example, walking through walls is in most cases impossible. Therefore, incorporating environmental knowledge is a necessary and gainful step. Like other systems, we are using a graph-based approach for this. The main advantage of such an approach is that the graph only samples valid locations. The unique feature of our approach is the way in how we model the human movement. This is done by using random walks on graphs, which are based upon the heading of the pedestrian. However, this suffers from several drawbacks, we want to address within this work. In pedestrian navigation, the human movement underlies the characteristics of walking speed and walking direction. Additionally, environmental restrictions need to be considered as well, for example, walking through walls is in most cases impossible. Therefore, incorporating environmental knowledge is a necessary and gainful step. Like other systems, we are using a graph-based approach for this. The main advantage of such an approach is that the graph only samples valid locations. The unique feature of our approach is the way in how we model the human movement. This is done by using random walks on graphs, which are based upon the heading of the pedestrian. However, the system presented in \cite{Ebner-15} suffers from two major drawbacks, we want to solve within this work.
The transition model presented in \cite{Ebner-15} uses discrete floors. Changing the floor on a discrete basis is like jumping down the staircase. This does not resemble real world floor changes and it could be shown that a correct estimation strongly depends on the quality of $z$-transitions. To address this problem we extended the graph by identically shaped stairs, allowing a step-wise transition in the $z$-direction. Firstly, the transition model of our past approach uses discrete floors. Changing the floor on a discrete basis is like jumping down the staircase. This does not resemble real world floor changes and it could be shown that a correct estimation strongly depends on the quality of $z$-transitions. To address this problem we extended the graph by realistically shaped stairs, allowing a step-wise transition in the $z$-direction.
However, we also discovered that correct estimation
strongly depends on the quality of z-transitions. If one is
missed or incorrectly detected, the estimation only slowly re-
covers. The presented discrete transition does not resemble real
world floor changes and thus not always works as expected.
Our current transition model uses discrete floors. Chang-
ing the floor on a discrete basis is like jumping down the
staircase. Such a transition would e.g. require the barometer
to detect an immediate pressure change. In reality, the pressure
slowly increases while walking down the stairs. This traps the
density on the previous floor until the pedestrian has reached
the end of the staircase and the sensor values actually match
a floor-change. However, until then, the density might have
already passed the stairwell and thus has no chance of changing
the floor
senkrechte stockwerke, wehcseln schwer blabal.. Therefore, we extend the graph by additional non-discrete nodes which resemble the shape of the stairs.
blumenverteilung, kurven laufen fällt schwer... bessers ziehen.
considering a navigation scenario... we present a novel method for pedestrian navigation by using pathfinding methods. to achieve a preferably realistic path, areas near a wall are less likely to be choosen for the path then a door or a small hallway. ... probability map/graph ... dijkstra doof... deswegen abstände zur wand mit einbeziehen.
Secondly, another drawback is the way in how the pedestrian's walking behaviour is modelled. At the moment the heading is only calculated between two adjacent nodes. That means, we are only able to perform \SI{45}{\degree} turns. \commentByToni{Ich denke hier kann Frank E. mehr zu schreiben. Bin mir nicht sicher wie ich das Problem gut schildern kann.} blumenverteilung, kurven laufen fällt schwer... bessers ziehen.
The problem of localization can be simplified by assuming a person navigation. Such applications are used to navigate a pedestrian to a given target destination. So, based on this assumption the starting point, which is the current position of the pedestrian, as well as the destination are known beforehand. Regarding a graph-based transition model, one could suggest to calculate the shortest path between start and destination. However, this often leads to paths running very unnatural alongside walls. Additionally, the human walking behaviour is highly affected by visual distractions, comfort, disorientation and many other factors. Therefore, we present a novel method for pedestrian navigation by using XXX methods to achieve a preferably realistic path, areas near a wall are less likely to be choosen for the path then a door or a small hallway. ... probability map/graph ...
\commentByToni{Wissen ja noch nicht was wir hier genau nehmen, deswegen erstmal leer}
\begin{itemize} \begin{itemize}
\item Hinführen zum Thema 1/4 + Abstract (haben so wenig platz nur 8 seiten...) \item Hinführen zum Thema 1/4 + Abstract (haben so wenig platz nur 8 seiten...)
@@ -51,10 +30,3 @@ considering a navigation scenario... we present a novel method for pedestrian na
\item Aufbau der Arbeit (falls platz, haben nur 8 Seiten) \item Aufbau der Arbeit (falls platz, haben nur 8 Seiten)
\end{itemize} \end{itemize}
Since the estabishlement of mobile
\cite{Nurminen14-MMF}