FHWS/IPIN2018
Archived
4
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Small fixes

Browse Source
This commit is contained in:
MBulli
2018-09-16 20:16:47 +02:00
parent 05da3a9324
commit 08af2ad411
9 changed files with 33 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tex/chapters/experiments.tex
View File

@@ -16,7 +16,7 @@ It was created using our 3D map editor software based on architectural drawings
Sensor measurements are recorded using a simple mobile application that implements the standard Android sensor functionalities.
As smartphones we used either a Samsung Note 2, Google Pixel One or Motorola Nexus 6.
The computation of the state estimation as well as the \docWIFI{} optimization are done offline using an Intel Core i7-4702HQ CPU with a frequency of \SI{2.2}{GHz} running \SI{8}{cores} and \SI{16}{GB} main memory.
However, similar to our previous, award-winning system, the setup is able to run completely on commercial smartphones as well as it uses C++ code \cite{torres2017smartphone}.
However, similar to our previous, award-winning system, the setup is able to run completely on commercial smartphones as it written in high performant C++ code \cite{torres2017smartphone}.
%Sensor measurements are recorded using a simple mobile application that implements the standard Android SensorManager.
The experiments are separated into four sections:
@@ -96,7 +96,7 @@ Besides the advantages the mesh offers, it also has a few disadvantages compared
The computation time has increased due to the calculation of reachable destinations.
With the graph, only the direct neighbours are of interest, which can be implemented very efficiently using a tree structure.
Further, the graph allows the easily store meta information on its nodes, for example Wi-Fi fingerprints or precalculations for shortest-path methods.
This is more difficult using the mash and requires the handling of baricentric coordinates.
This is more difficult using the mesh and requires the handling of baricentric coordinates.
\subsection{\docWIFI{} Optimization}
@@ -185,11 +185,11 @@ looking at the optimziation errors, this can be varified... etc pp
The 4 chosen walking paths can be seen in fig. \ref{fig:floorplan}.
Walk 0 is \SI{152}{\meter} long and took about \SI{2.30}{\minute} to walk.
Walk 2 has a length of \SI{223}{\meter} and Walk 3 a length of \SI{231}{\meter}, both required about \SI{6}{\minute} to walk.
Finally, walk 3 is \SI{310}{\meter} long and needs \SI{10}{\minute} to walk.
All walks were carried out be 4 different male testers using either a Samsung Note 2, Google Pixel One or Motorola Nexus 6 for recording the measurements.
Finally, walk 3 is \SI{310}{\meter} long and takes \SI{10}{\minute} to walk.
All walks were carried out by 4 different male testers using either a Samsung Note 2, Google Pixel One or Motorola Nexus 6 for recording the measurements.
All in all, we recorded \SI{28}{} distinct measurement series, \SI{7}{} for each walk.
The picked walks intentionally contain erroneous situations, in which many of the above treated problems occur.
Thus we are able to discuss everything in detail.
This allows us to discuss everything in detail.
A walk is indicated by a set of numbered markers, fixed to the ground.
Small icons on those markers give the direction of the next marker and in some cases provide instructions to pause walking for a certain time.
The intervals for pausing vary between \SI{10}{\second} to \SI{60}{\second}.
@@ -236,7 +236,7 @@ We discuss the single results of table \ref{table:overall} starting with walk 0.
Here, the pedestrians started at the top most level, walking down to the lowest point of the building.
The first critical situation occurs immediately after the start.
While walking down the small staircase, many particles are getting dragged into the room to the right due to erroneous Wi-Fi readings.
At this point, the activity "walking down" is recognized, however only a for very short period.
At this point, the activity "walking down" is recognized, however only for a very short period.
This is caused by the short length of the stairs.
After this period, only a small number of particles changed the floor correctly, while a majority is stuck within the right-hand room.
The activity based evaluation $p(\vec{o}_t \mid \vec{q}_t)_\text{act}$ prevents particles from further walking down the stairs, while the resampling step mainly draws particles in already populated areas.
@@ -278,13 +278,14 @@ Only two \docAPshort{}'s provide a solid signal within this area, leading to a h
\begin{figure}[t!]
\centering
\begin{subfigure}[t]{0.48\textwidth}
\begin{subfigure}[t]{0.45\textwidth}
\def\svgwidth{\columnwidth}
{\input{gfx/wifiOptGlobalFloor/wifiOptGlobalFloor.eps_tex}}
\caption{}
\label{fig:walk3:wifiopt}
\end{subfigure}
\begin{subfigure}[t]{0.50\textwidth}
\hfil
\begin{subfigure}[t]{0.45\textwidth}
\resizebox{1\textwidth}{!}{\input{gfx/errorOverTimeWalk3/errorOverTime.tex}}
\caption{}
\label{fig:walk3:time}
@@ -330,12 +331,13 @@ Regarding the underlying particle set, different shapes of probability distribut
%
\begin{figure}[t]
\centering
\begin{subfigure}{0.48\textwidth}
\begin{subfigure}{0.45\textwidth}
\resizebox{1\textwidth}{!}{\input{gfx/walk.tex}}
\caption{}
\label{fig:walk1:kde}
\end{subfigure}
\begin{subfigure}{0.50\textwidth}
\hfil
\begin{subfigure}{0.45\textwidth}
\resizebox{1\textwidth}{!}{\input{gfx/errorOverTimeWalk1/errorOverTime.tex}}
\caption{}
\label{fig:walk1:kdeovertime}
@@ -370,7 +372,7 @@ We have highlighted some interesting areas with coloured squares.
The greatest difference between the respective estimation methods can be seen inside the green square, the gallery wing of the museum.
While the weighted-average (blue) produces a very straight estimated path, the KDE-based method (red) is much more volatile.
This can be explained by the many small rooms that pedestrians pass through.
The doors act like a bottleneck, which is why many particles run against walls and are thus either drawn on a new position within a reachable area (cf. section \ref{sec:estimation}) or walk along the wall towards the door.
The doors act like bottlenecks, which is why many particles run against walls and thus are either drawn on a new position within a reachable area (cf. section \ref{sec:estimation}) or walk along the wall towards the door.
This causes a higher uncertainty and diversity of the posterior, what is more likely to be reflected by the KDE method than by the weighted-average.
Additionally, the pedestrian was forced seven times to look at paintings (stop walking) between \SI{10}{\second} and \SI{20}{\second}, just in this small area.
Nevertheless, even if both estimated paths look very different, they produce similar errors.
@@ -380,13 +382,13 @@ Due to a poorly working \docAPshort{}, in the lower corner of the big room the p
By allowing some particles to walk through the wall and thus down the stairs, the impoverishment could be dissolved.
The KDE-based estimation illustrates this behaviour very accurate.
Another situation in which the estimated paths do not provide sufficient results can be seen inside the teal square.
The room is very isolated from the rest of the building, which is reflected in the fact that only 3 \docAPshort{}'s are detected.
The room is very isolated from the rest of the building, which is reflected by the fact that only 3 \docAPshort{}'s are detected.
The pedestrians have been asked to cross the room at a quick pace, leading to a higher step rate and therefore update rate of the filter.
The results within this area lead to the assumption, that even if Wi-Fi has a bad coverage, it influences the estimation results the most.
The PDR based transition alone is able to walk alongside the ground truth in an accurate manner.
However, this is of course only true if we consider this area individually, without the rest of the walk due to the accumulating bias of the relative sensors involved.
In the end, it is a question of optimal harmony between transition and evaluation.
We hope to further improve such situations in future work by enabling the transition step to provide a weight to particles that walk very likely, especially in situation were Wi-Fi provides bad readings.
We hope to further improve such situations in future work by enabling the transition step to provide a weight to particles that walk very likely, especially in situation where Wi-Fi provides bad readings.
\begin{figure}[t]
\centering
@@ -397,7 +399,7 @@ We hope to further improve such situations in future work by enabling the transi
\end{figure}
To summarize, the KDE-based approach for estimation is able to resolve multimodalities.
It does not provide a smooth estimated path, since it depends more on an accurate sensor model then a weighted-average approach, but is very suitable as a good indicator about the real performance of a sensor fusion system.
It does not provide a smooth estimated path, since it depends more on an accurate sensor model than a weighted-average approach, but is suitable as a good indicator about the real performance of a sensor fusion system.
At the end, in the here shown examples we only searched for a global maxima, even though the KDE approach opens a wide range of other possibilities for finding a best estimate.