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

senf zu experimente abgegeben

Browse Source
This commit is contained in:
Toni
2016-02-13 18:01:26 +01:00
parent fcf5f7b437
commit 8dcedb3e97
4 changed files with 74 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tex/chapters/conclusion.tex
View File

@@ -1,6 +1,6 @@
\section{Conclusion}
\section{Future Work}
\commentByFrank{balance zwischen den einzelnen wahrscheinlichkeiten ist oft ein schmaler grad. wieviel turn erlauben, wieviel auf den pfad zwingen. das verbesern}
\commentByFrank{position der APs wissen ist viel arbeit. vereinfachen durch test-walks auf vorgegebenen pfaden -> numerisch optimieren wo APs sind}
\commentByToni{quadtress. stellen die groesse der zellen variable ein. je nach bedarf.}

128
tex/chapters/experiments.tex
View File

@@ -6,46 +6,45 @@
%
We conducted 4 distinct walks, for testing short distances, long distances, critical sections
and ignoring the shortest-path suggested by the system.
Due to an inhouse exhibition during that time, many places were crowded and \docWIFI{} signals
Due to an in-house exhibition during that time, many places were crowded and \docWIFI{} signals
are attenuated more than usual.
Each acquired path is backed by ground truth information to enable error calculation.
This ground truth is measured by recording a timestamp at a marked spot on the walking route.
During the walk, the pedestrian had to click a button on the smartphone application
when passing a marker. Between two consecutive points, a constant movement speed is assumed.
Thus, the ground truth might not be \SI{100}{\percent} accurate, but fair enough to conduct
error measurements. All walks were conducted using a Google Nexus 6 and a Samsung Galaxy S5.
error measurements. All walks were performed using a Google Nexus 6 and a Samsung Galaxy S5.
As the Samsung Galaxy S5's \docWIFI{} can not be limited to the \SI{2.4}{\giga\hertz} band only,
its scans take much longer than those of the Google Nexus 6:
\SI{3500}{\milli\second} vs. \SI{600}{\milli\second}.
Also, the Nexus' barometer sensor provides readings both more frequent and far more accurate than
the Galaxy does. This results in a much better localisation of the Nexus smartphone.
the Galaxy does. This results in a much better localisation using the Nexus smartphone.
Despite being fast enough to run in realtime on the smartphone itself, computation was done offline using
the condensation algorithm with \SI{7500}{} particles as realization of the recursive density estimation \cite{todo}.
the CONDENSATION particle filter with \SI{7500}{} particles as realization.
The weighted arithmetic mean of the particles was used as state estimation.
As mentioned earlier, the position of all \docAP{}s (about 5 per floor) is known beforhand.
As mentioned earlier, the position of all \docAP{}s (about 5 per floor) is known beforehand.
Due to legal terms, we are not allowed to depict their positions and therefore omit this information within the figures.
Additionally we used three \docIBeacon{}s for slight enhancements in some areas.
Additionally, we used three \docIBeacon{}s for slight enhancements in some areas.
The empirically chosen values for \docWIFI{} were $P_{0_{\text{wifi}}} = \SI{-46}{\dBm}, \mPLE_{\text{wifi}} = \SI{2.7}{}$,
and $\mPLE_{\text{ib}} = \SI{1.5}{}$ for the \docIBeacon{}s, respectively.
%
Due to omitting a time-consuming calibration process for those values we expect the localistation
process to perform generally worse compared to fingerpring methods \todo{cite}. However,
incorporating prior knowledge will often compensate for those poorly chosen system parameters.
Due to omitting a time-consuming calibration process for those values we expect the localisation process to perform generally worse compared to standard fingerprinting methods \cite{Ville09}.
However, incorporating prior knowledge will often compensate for those poorly chosen system parameters.
As uncertainties we used $\sigma_\text{wifi} = \sigma_\text{ib} = 8.0$, both growing with each measurement's age.
While the pressure change was assumed to be \SI{0.105}{$\frac{\text{\hpa}}{\text{\meter}}$}, all other barometer-parameters
are determined automatically (see \ref{sec:sensBaro}). The step size for the transition was configured to be \SI{70}{\centimeter}
with an allowed derivation of \SI{10}{\percent}. The heading deviation in \refeq{eq:transSimple} was \SI{25}{\degree}.
As we start with a uniformation distribution for $\mStateVec_0$ (random position and heading), the first few estimations
As we start with a discrete uniform distribution for $\mStateVec_0$ (random position and heading), the first few estimations
are omitted from the error calculation to allow the system to somewhat settle its initial state. Even though, the error
during the follwing few seconds is expected to be much higher than the error when starting with a well known initial
position and heading.
during the following few seconds is expected to be much higher than the error when starting with a well known initial
position and heading.
The follwing evaluations will depict the improvements prior path knowledge is able to provide
The following evaluations will depict the improvements that the prior path knowledge is able to provide,
even when other system parameters are badly chosen.
Just adding importance-factors described in \ref{sec:wallAvoidance} and \ref{sec:doorDetection}
to the simple transition \refeq{eq:transSimple} addresses only minor local errors
@@ -53,7 +52,7 @@
and is therefore not further evaluated.
To examine the contribution our approach is able to provided, we will have a closer look
at a long walk with many stairs, intentionally leaving the shortest path several times,
named path 4 (see \ref{fig:paths}).
named path 4 (see fig. \ref{fig:paths}).
%
@@ -71,46 +70,7 @@
\commentByFrank{in den ersten paar sec ist die pfad-info teils hinderlich, da die genaue position noch sehr unklar ist und sich erst einstellen muss.
deshalb geht der fehler hier oft leicht hoch}
\newcommand{\refSeg}[1]{$(#1)$}
Fig. \ref{errorTimedNexus} shows the error for the individual segments of path 1 and path 4 recorded with the Google Nexus 6.
Remember that we start with a uniform distribution instead of a well known pedestrian location. Therefor the first few estimations
reside somewhere near the center of the building and result in a very high error contribution
(see fig. \ref{nexusPathDetails} \refSeg{1}).
%
Even when removing those initial estimations from the error calculation, the next few seconds are still erroneous
due to (intentionally) bad system parameters (see \ref{sec:sensors}). Furthermore, as the pedestrian is not yet walking,
our proposed method is not yet able to addres those error. This can be seen in both
fig. \ref{fig:nexusPathDetails} \refSeg{1} (the red are in the upper left)
and fig \ref{fig:errorTimedNexus} \refSeg{1}.
%
However, as soon as the pedestrian starts moving down the hallway \refSeg{2} the error is reduced dramatically.
Adding prior knowledge centers the density in the middle of the floor, ensures the heading is directed towards
the shortest path and thus produces even better localisation results.
%
Directly hereafter, we ignore the shortest path \refSeg{3'} determined by the system and walk along \refSeg{3}
instead. Of course, this leads to a temporally increasing error, as the system needs to detect this path change
and takes some time to recover (see \ref{fig:errorDistNexus} \refSeg{3}). The new path to the desired destination
is \refSeg{3''} which is also ignored. Instead, we took a much longer route down the stairwell \refSeg{4}.
After this change is detected by the system, prior knowledge is able to reduce the error for segment \refSeg{5}.
%
Immediately hereafter follows a long, straight walk down the hallway. While the \docWIFI{} component pulls
the pedestrian into the rooms on the right side, the actual walking route was located on the left side
of the wall (see ground truth in fig. \ref{fig:nexusPathDetails} \refSeg{6}). While prior knowledge prevents
the density being draged into the office-rooms, the estimated path is still located on the wrong side
of the hallway. As both sides of the floor result in a route with almost the same length,
just knowing the pedestrian's destination is not able to provide further improvments.
Thus, a constant error of approximately the floor's width remains (see \ref{fig:nexusPathDetails} \refSeg{6}).
%
Due to the excellent barometer installed within the Nexus 6, the stair provides were small estimation
errors \refSeg{7}. Hereafter follows a critical area with high errors and multimodalities. Due to an
inhouse exhibition during the time of recording, we had to leave the ground truth by a few meters.
Furthermore, the overcrowded areas lead to attenuated \docWIFI{} signals. Both reasons lead to the
density being dragged into another stairwell (see \ref{fig:nexusPathDetails}, red lines in the lower right).
The resulting multimodality (two staircases possible at the same time) leads to a rising error
\refSeg{8}, \refSeg{9}. At the end of the walk \refSeg{10} the system is able to recover, again.
% error development over time while walking along a path
% error development over time while walking along a path
\begin{figure}
\input{gfx/eval/error_timed_nexus}
\caption{Development of the error while walking along
@@ -120,7 +80,6 @@
staircases just before the destination (9).}
\label{fig:errorTimedNexus}
\end{figure}
\begin{figure}
\input{gfx/eval/path_nexus_detail}
\caption{Detailed path analysis depicting the individual segments of path 4. Their corresponding error contribution can
@@ -128,6 +87,47 @@
times ($3'$ and $3''$) our approach is still able to improve the overall localisation error.}
\label{fig:nexusPathDetails}
\end{figure}
%
\newcommand{\refSeg}[1]{$(#1)$}
Fig. \ref{fig:errorTimedNexus} shows the error for path 4 recorded with the Google Nexus 6.
\commentByToni{heisst das teil nicht motorola nexus 6?}
For a better understanding of the following discussion, the path was divided into $10$ individual segments.
Remember that we start with a uniform distribution instead of a well known pedestrian location.
Therefore, the first few estimations
reside somewhere near the centre of the building and result in a very high error contribution
as illustrated in fig. \ref{fig:nexusPathDetails} \refSeg{1}.
%
Even when removing those initial estimations from the error calculation, the next few seconds are still erroneous
due to (intentionally) bad system parameters introduced in section \ref{sec:sensors}. Furthermore, as the pedestrian is not yet walking,
our proposed method is also not yet able to address those errors. This can be seen
at the red area in the upper left corner of fig. \ref{fig:nexusPathDetails} \refSeg{1} and within segment \refSeg{1} of fig. \ref{fig:errorTimedNexus}.
%
However, as soon as the pedestrian starts moving down the hallway \refSeg{2} the error is reduced dramatically.
Adding prior knowledge centres the density in the middle of the floor, ensures the heading is directed towards
the shortest path and thus produces even better localisation results.
%
Directly hereafter, we ignore the shortest path \refSeg{3'} determined by the system and walk along \refSeg{3}
instead. Of course, this leads to a temporally increasing error, as the system needs to detect this path change
and takes some time to recover (see fig. \ref{fig:errorDistNexus} \refSeg{3}). The new path to the desired destination
is \refSeg{3''} which is also ignored. Instead, we took a much longer route down the stairwell \refSeg{4}.
After this change is detected by the system, prior knowledge is able to reduce the error for segment \refSeg{5}.
%
Immediately hereafter follows a long, straight walk down the hallway. While the \docWIFI{} component pulls
the pedestrian into the rooms on the right side, the actual walking route was located on the left side
of the wall (see ground truth in fig. \ref{fig:nexusPathDetails} \refSeg{6}). While prior knowledge prevents
the density being dragged into the office-rooms, the estimated path is still located on the wrong side
of the hallway. As both sides of the floor result in a route with almost the same length,
just knowing the pedestrian's destination is not able to provide further improvements.
Thus, a constant error of approximately the floor's width remains. This is clearly visible in fig. \ref{fig:nexusPathDetails} \refSeg{6}.
%
Due to the excellent barometer installed within the Nexus 6, changing the floor provides only small estimation errors in segment \refSeg{7}.
It follows a critical area with high errors and multimodalities.
Due to an in-house exhibition during the time of recording, we had to leave the ground truth by a few meters.
Furthermore, the overcrowded areas lead to attenuated \docWIFI{} signals. Both reasons cause the
density being dragged into another stairwell (see fig. \ref{fig:nexusPathDetails}, red lines in the lower right).
The resulting multimodality (two staircases possible at the same time) leads to a rising error
\refSeg{8}, \refSeg{9}. At the end of the walk \refSeg{10} the system is able to recover, again.
% overall error-distribution for nexus and galaxy
\begin{figure}
@@ -149,6 +149,8 @@
% error values
\begin{table}
\centering
\label{tbl:errNexus}
\caption{Median error for walks conducted with the Nexus 6.}
\begin{tabular}{|l|c|c|c|c|}
\hline
& Path1 & Path2 & Path3 & Path4 \\\hline
@@ -156,12 +158,12 @@
Shortest (\refeq{eq:transShortestPath}) & \SI{2.72}{\meter} & \SI{2.98}{\meter} & \SI{2.48}{\meter} & \SI{3.06}{\meter} \\\hline
Multipath (\refeq{eq:transMultiPath}) & \SI{2.62}{\meter} & \SI{2.14}{\meter} & \SI{2.46}{\meter} & \SI{2.75}{\meter} \\\hline
\end{tabular}
\label{tbl:errNexus}
\caption{Median error for walks conducted with the Nexus 6.}
\end{table}
\begin{table}
\centering
\label{tbl:errGalaxy}
\caption{Median error for walks conducted with the Galaxy S5.}
\begin{tabular}{|l|c|c|c|c|}
\hline
& Path1 & Path2 & Path3 & Path4 \\\hline
@@ -169,8 +171,6 @@
Shortest (\refeq{eq:transShortestPath}) & \SI{ 5.86}{\meter} & \SI{4.14}{\meter} & \SI{5.14}{\meter} & \SI{5.20}{\meter} \\\hline
Multipath (\refeq{eq:transMultiPath}) & \SI{ 6.35}{\meter} & \SI{4.21}{\meter} & \SI{5.03}{\meter} & \SI{6.79}{\meter} \\\hline
\end{tabular}
\label{tbl:errGalaxy}
\caption{Median error for walks conducted with the Galaxy S5.}
\end{table}
\begin{figure}
@@ -187,16 +187,6 @@
\label{fig:bergwerkPath3Galaxy}
\end{figure}
\begin{itemize}
\item Nochmal kurz auf die Probleme des letzten Systems eingehen (schon teil der introduction)
\item Da letztes mal nur 1 Pfad, machen wir dieses mal mehrere!
\item Stelle normale Lokalisation der Pfad Lokalisation gegenüber und überlege wo Probleme auftreten
\item nutze den "natürlichen Pfad" und einen normalen dijkstra
\item Analysiere Probleme ggf. mit schönen Grafiken.
\item Vergleich zum Schluss das neue System mit dem Alten um eine schöne Conclusion der Verbesserungen einzuleiten.
\end{itemize}
\commentByFrank{sensorausfall simulieren, z.b. in der mitte, oder auf einer treppe}
\commentByFrank{zwischendrin mal stehenbleiben und schauen ob auch das klappt}
\commentByFrank{zu grosser einfluss vom pfad ist also kein allheilmittel.. kann, wie beim treppenhaus, auch nach hinten los gehen}

34
tex/chapters/introduction.tex
View File

@@ -11,38 +11,31 @@ Especially the hard problem of pedestrian localisation and navigation has lately
Most modern indoor localisation systems primarily use smartphones to determine the position of a pedestrian.
Especially the phone's inertial measurement unit (IMU) as well as external information like Wi-Fi or Bluetooth
are used to collect the necessary data. Additionally, environmental knowledge is often incorporated e.g. by using
floor maps. This combination of highly different sensor types is also known as sensor fusion.
are used to collect the necessary data.
Additionally, environmental knowledge is often incorporated e.g. by using floormaps.
This combination of highly different sensor types is also known as sensor fusion.
Here, probabilistic methods like particle- or Kalman filters are often used to approximate a probability
distribution describing the pedestrian's possible whereabouts.
Here, probabilistic methods like particle- or Kalman filters are often used to approximate a probability distribution describing the pedestrian's possible whereabouts.
This procedure can be separated into two probabilistic models:
The transition model, which represents the dynamics of the pedestrian
and predicts his next accessible locations,
and the evaluation model, which estimates the probability for the position also corresponding to
The transition model, which represents the dynamics of the pedestrian and predicts his next accessible locations, and the evaluation model, which estimates the probability for the position also corresponding to
recent sensor measurements.
%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 sensors
mentioned above, 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 sensors mentioned above, including the phone's barometer \cite{Ebner-15}.
In pedestrian navigation, the human movement is subject to the characteristics of walking speed and -direction.
Additionally, environmental restrictions need to be considered as well, for example,
walking through walls is impossible.
Additionally, environmental restrictions need to be considered as well, for example, walking through walls is impossible.
Therefore, incorporating environmental knowledge is a necessary and gainful step.
Like other systems, we are using a graph-based approach to sample only valid movements.
The unique feature of our approach is the way how we model the human movement.
This is done by using random walks on a graph, which are based on the heading of the
pedestrian.
Despite very good results, the system presented in \cite{Ebner-15} suffers from two drawbacks,
we want to solve within this work.
This is done by using random walks on a graph, which are based on the heading of the pedestrian.
Despite very good results, the system presented in \cite{Ebner-15} suffers from two drawbacks, we want to solve within this work.
First, the transition model of our previous approach uses discrete floor-changes.
Although the overall systems provides viable results, it does not resemble real-world floor changes.
Especially the barometric sensor is affected due to its continuous pressure measurements.
The discrete model prevents the barometer's full potential.
It could further be shown that a correct estimation strongly depends on the quality of $z$-transitions.
To address this problem we extended the graph by adding realistic stairs, allowing a step-wise transition
in the $z$-direction.
To address this problem we extended the graph by adding realistic stairs, allowing a step-wise transition in the $z$-direction.
Second, the heading for modelling the pedestrian's walking behaviour is calculated between two adjacent nodes.
This restricts the transition to perform only discrete \SI{45}{\degree} turns. In most scenarios this assumption performs
@@ -50,8 +43,7 @@ well, since the... However, walking sharp turns and ... is not
\commentByToni{Ich denke hier kann Frank E. noch bissle was schreiben, oder?}
\commentByFrank{ja das werde ich noch anpassen, dass es stimmt und die probleme beschreibt}
To improve the complex problem of localising a person indoors, prior knowledge given by a pedestrian navigation can be used.
\commentByFrank{klingt etwas komisch. -- given by a navigation system -- oder sowas in der art?}
To improve the complex problem of localising a person indoors, prior knowledge given by a navigation system can be used.
Such applications are used to navigate a user to his desired destination.
This limits the unpredictability of human movement to a certain degree.
So, based on this assumption, the destination is known beforehand and the starting point is the pedestrian's currently estimated position.
@@ -63,13 +55,11 @@ Therefore, we present a novel approach that detects walls using the inverted gra
In order to model areas near walls less likely to be chosen for walking, a probabilistic weight is assigned to every node of the graph.
This allows a variety of options for integrating additional knowledge about the environment and enables us to address another problem:
\commentByFrank{wie waers mit: entering or leaving rooms is very unlikely as only a few nodes (doors) allow doing so}
Walking through a door has a lower probability than remaining on the corridor, since only a few nodes are representing it.
Entering or leaving rooms is very unlikely as only a few nodes are representing doors and allow doing so.
This can be tackled by making such areas more likely.
Therefore, a novel approach for detecting doors using again the inverted graph and the principal component analysis (PCA) \cite{Hotelling1933} is presented within this work.
\commentByFrank{auch hier vlt das inverted erstmal noch weg lassen wegen platz}
\commentByFrank{wenn dir das weighted graph immer noch nicht gefaellt: -- weights attached the nodes -- oder sowas?}
Finally, it is now possible to calculate more natural and realistic paths using the weighted graph.
We introduce two different methods which make use of the given destination and thereby provide a targeted movement.
To the best of our knowledge, this approach is the first one that uses prior navigation knowledge to increase the localisation results.