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

8 pages..

Browse Source
This commit is contained in:
toni
2016-02-25 15:03:10 +01:00
parent 360756cf21
commit a8b91b141d
2 changed files with 14 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tex/chapters/experiments.tex
View File

@@ -10,12 +10,12 @@
and ignoring the shortest-path suggested by the system. and ignoring the shortest-path suggested by the system.
Due to an in-house 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. are attenuated.
To enable error calculation, each acquired path is backed by ground truth information. % To enable error calculation, each acquired path is backed by ground truth information.
The ground truth is measured by recording a timestamp at marked spots on the walking route. The ground truth is measured by recording a timestamp at marked spots on the walking route.
While walking, the pedestrian clicked a button on the smartphone application While walking, the pedestrian clicked a button on the smartphone application
when passing a marker. Between two consecutive points, a constant movement speed is assumed. 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 for Thus, the ground truth might not be \SI{100}{\percent} accurate, but fair enough for error measurements.
error measurements. All walks were performed using a Motorola Nexus 6 and a Samsung Galaxy S5. All walks were performed using a Motorola 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, 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 Motorola Nexus 6: its scans take much longer than those of the Motorola Nexus 6:
@@ -53,15 +53,11 @@
% %
The following evaluations will depict the improvements that the 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.
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
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
% like not sticking too close to walls. In most cases this lead only to slight improvements % like not sticking too close to walls. In most cases this lead only to slight improvements
and is therefore not further evaluated. and is therefore not further evaluated.
To examine the contribution our approach is able to provide, we will have a closer look To examine the contribution our approach is able to provide, we will have a closer look at a long walk with many stairs, intentionally leaving the shortest path several times, named path 4 (see fig. \ref{fig:paths}).
at a long walk with many stairs, intentionally leaving the shortest path several times,
named path 4 (see fig. \ref{fig:paths}).
% %
% all paths we evaluated % all paths we evaluated
\begin{figure} \begin{figure}
@@ -107,7 +103,7 @@
This can be seen at the red area in the upper left corner of fig. \ref{fig:nexusPathDetails} \refSeg{1} and within 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}. segment \refSeg{1} of fig. \ref{fig:errorTimedNexus}.
% %
Starting with both, known position and heading, reduced the error by about \SI{15}{\percent} when using prior knowledge and Starting instead with both, known position and heading, reduced the error by about \SI{15}{\percent} when using prior knowledge and
by \SI{25}{\percent} when omitting prior knowledge. As prior knowledge directs the density towards a known target, by \SI{25}{\percent} when omitting prior knowledge. As prior knowledge directs the density towards a known target,
it is able to compensate unknown initial headings which explains the \SI{10}{\percent} difference. it is able to compensate unknown initial headings which explains the \SI{10}{\percent} difference.
% %
@@ -127,8 +123,8 @@
the density from being dragged into the office-rooms, the estimated path is still located on the wrong side the density from 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, 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. just knowing the pedestrian's destination is not able to provide further improvements.
Thus, a constant error of approximately the floor's width remains. Thus, a constant error of approximately the floor's width remains
This is clearly visible in fig. \ref{fig:nexusPathDetails} \refSeg{6}. as seen in fig. \ref{fig:nexusPathDetails} \refSeg{6}.
% %
Due to the excellent barometer installed within the Nexus 6, changing the floor provides only small estimation Due to the excellent barometer installed within the Nexus 6, changing the floor provides only small estimation
errors in segment \refSeg{7}. errors in segment \refSeg{7}.
@@ -136,7 +132,7 @@
Due to an in-house exhibition during the time of recording, we had to leave the ground truth by a few meters. 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 move the Furthermore, the overcrowded areas lead to attenuated \docWIFI{} signals. Both reasons move the
density into another stairwell (see fig. \ref{fig:nexusPathDetails}, red lines in the lower right). density 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 The resulting multimodality (two staircases possible) leads to a rising error
\refSeg{8}, \refSeg{9}. At the end of the walk \refSeg{10} the system is able to recover, again. \refSeg{8}, \refSeg{9}. At the end of the walk \refSeg{10} the system is able to recover, again.
@@ -154,11 +150,11 @@
% \caption{Nicht so markant beim galaxy, denke aber der platz reicht eh nicht, also einfach kurz erwaehnen} % \caption{Nicht so markant beim galaxy, denke aber der platz reicht eh nicht, also einfach kurz erwaehnen}
%\end{figure} %\end{figure}
The median error values for all other paths and the other smartphone are listed in table The median errors for all conducted walks are listed in table \ref{tbl:errNexus}. Furthermore, fig. \ref{fig:errorDistNexus}
\ref{tbl:errNexus}. Furthermore, fig. \ref{fig:errorDistNexus}
depicts the error development for several percentile values. As can be seen, adding prior depicts the error development for several percentile values. As can be seen, adding prior
knowledge is able to improve the localisation for all examined situations, even when knowledge improves the localisation for all examined situations, even when
leaving the suggested path or when facing bad/slow sensor readings. leaving the suggested path or when facing bad/slow sensor readings.
\newpage
%\commentByFrank{fig. \ref{fig:errorDistNexus} erwaehnt} %\commentByFrank{fig. \ref{fig:errorDistNexus} erwaehnt}
% error values % error values

4
tex/chapters/grid.tex
View File

@@ -257,9 +257,7 @@
\newcommand{\pathRef}{v_\text{ref}} \newcommand{\pathRef}{v_\text{ref}}
% %
Before every transition, the centre-position $\pathCentroid = \fPos{\mStateVec_{t-1}^*}$ of the current sample-set, where Before every transition, the centre-position $\pathCentroid = \fPos{\mStateVec_{t-1}^*}$ of the current sample-set, where
\begin{equation} $\mStateVec_{t-1}^* = \argmax_{\mStateVec_{t-1}} \enspace p(\mStateVec_{t-1} \mid \mObsVec_{t-1})$
\mStateVec_{t-1}^* = \underset{\mStateVec_{t-1}}{\argmax} \enspace p(\mStateVec_{t-1} | \mObsVec_{t-1})
\end{equation}
represents the most proper state of the posterior distribution at time $t-1$, is calculated. represents the most proper state of the posterior distribution at time $t-1$, is calculated.
% %
% %