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

updated tex. sensors done.

Browse Source
This commit is contained in:
Toni
2016-02-12 15:40:52 +01:00
parent f0215731ce
commit 6b02336277
6 changed files with 40 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tex/chapters/conclusion.tex
View File

@@ -5,4 +5,6 @@
\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.}
\commentByFrank{multimodalitaeten (z.B. treppenhaeuser). fixen durch andere estimations}
\commentByToni{oder durch smoothing}
\commentByToni{Aufzuege hinzufuegen. Vertical Acceleration benutzen.}

50
tex/chapters/grid.tex
View File

@@ -1,10 +1,10 @@
\section{Transition Model}
\label{sec:trans}
To sample only transitions $p(\mStateVec_{t} \mid \mStateVec_{t-1})$ that are actually feasible
To sample only transitions that are actually feasible
within the environment, we utilize a \SI{20}{\centimeter}-gridded graph
$G = (V,E)$, $v_{x,y,z} \in V$, $e_{v_{x,y,z}}^{v_{x',y',z'}} \in E$
derived from the buildings floorplan as described in \cite{ipin2015}.
derived from the buildings floorplan as described in section \ref{sec:relatedWork}.
However, we add improved $z$-transitions by also modelling realistic
stairwells using nodes and edges as can be seen in fig. \ref{fig:gridStairs}.
@@ -21,6 +21,7 @@
The corresponding vertices are determined using intersections of the segments with the bounding-box
for each vertex.
\commentByToni{Der Teil wird mir gar nicht klar irgendwie. Kann mir vor allem den letzten Satz nicht vorstellen.}
\commentByFrank{mention?: clean z-transitions, remove x/y nodes by adding bounding boxes}
To reduce the system's memory footprint, we search for the largest connected region within the graph and
@@ -29,29 +30,26 @@
\newcommand{\gHead}{\theta}
\newcommand{\gDist}{d}
Walking the grid is now possible by moving along adjacent nodes into a given walking-direction
until a desired distance is reached \cite{ipin2015}.
until a desired distance $\gDist$ is reached \cite{Ebner-15}.
In order to use meaningful headings $\gHead$ and distances $\gDist$
(matching the pedestrian's real heading and walking speed) for each transition,
we use the current sensor-readings $\mObsVec_{t}$ for hinted instead of truly random adjustments.
During a walk, each edge has an assigned probability $p(e)$ which depends on a chosen implementation.
Usually, this probability describes aspects like a comparison of the edge's angle $\angle e$ with the
current heading $\gHead$. However, it is also possible to incorporate additional prior knowledge to favor
some vertices/edges
\commentByFrank{im system-teil anmerken: $\mObsVec_t^{\mObsSteps} \in \N$}
\begin{align}
%
\begin{align}
\mStateVec_{t}^{\mStateHeading} = \gHead &= \mStateVec_{t-1}^{\mStateHeading} + \mObsVec_t^{\mObsHeading} + \mathcal{N}(0, \sigma_{\gHead}^2) \\
\gDist &= \mObsVec_t^{\mObsSteps} \cdot \SI{0.7}{\meter} + \mathcal{N}(0, \sigma_{\gDist}^2)
\end{align}
%
During a walk, each edge has an assigned probability $p(e)$ which depends on a chosen implementation.
Usually, this probability describes aspects like a comparison of the edge's angle $\angle e$ with the
current heading $\gHead$. However, it is also possible to incorporate additional prior knowledge to favor
some vertices/edges.
For comparison purpose we define a simple weighting method that assigns a probability to each edge
based on the deviation from the currently estimated heading $\gHead$:
\commentByFrank{das erste $=$ ist komisch. bessere option?}
\commentByToni{Find ich jetzt nicht tragisch. Eher notwendig fuers Verstaendnis.}
\begin{equation}
p(e) = p(e \mid \gHead) = N(\angle e \mid \gHead, \sigma_\text{dev}^2).
\label{eq:transSimple}
@@ -61,20 +59,18 @@
\section{TITLE?}
\section{Navigation Knowledge}
Assuming navigation, the pedestrian wants to reach a well-known destination and represents additional
prior knowledge. Most probabily, the pedestrian will stick to the path presented by
a navigation system. However, some deviations like chatting to someone or taking another router
cannot be strictly ruled out. We will therefor describe a system that is able to deal with such variants
as well as present an algorithm to calculate realistic routes based on aforemention grid.
prior knowledge. Most probably, the pedestrian will stick to the path presented by
a navigation system. However, some deviations like chatting to someone or taking another route
cannot be strictly ruled out. We will therefore describe a system that is able to deal with such variants
as well as present an algorithm to calculate realistic routes based on the aforementioned grid.
Simply running a shortest-path algorithm as Dijkstra or A* \todo{cite} using the previously created floorplan
would oviously lead to non-realistic paths sticking to the walls and walking many diagonals. In order
to calculate paths the resemble pedestrian walking behaviour we thus need some adjustments to the
route calculation.
As discussed in section \ref{sec:relatedWork}, simply running a shortest-path algorithm as Dijkstra or A* using the previously created graph would obviously lead to non-realistic paths sticking to the walls and walking many diagonals.
In order to calculate paths the resemble pedestrian walking behavior we thus need some adjustments to the route calculation.
\subsection{wall avoidance}
\subsection{Wall Avoidance}
\label{sec:wallAvoidance}
As already mentioned, shortest-path calculation usually sticks close to walls to reduce the path's length.
@@ -102,7 +98,7 @@
\subsection{door detection}
\subsection{Door Detection}
\label{sec:doorDetection}
Doors are usually anchored between two (thin) walls and have a normed width. Examining only a limited region
@@ -144,7 +140,7 @@
\subsection{path estimation}
\subsection{Path Estimation}
\label{sec:pathEstimation}
Based on aforementioned assumptions, the final importance for each node is

1
tex/chapters/relatedwork.tex
View File

@@ -1,4 +1,5 @@
\section{Related Work}
\label{sec:relatedWork}
Like mentioned before, most state-of-the-art systems use recursive state estimators like Kalman- and particle filters.
They differ mainly by the sensors used, their probabilistic models and how the environmental information are incorporated.

24
tex/chapters/sensors.tex
View File

@@ -42,7 +42,7 @@ The evaluation following the transition then compares the predicted relative pre
\subsection{Wi-Fi \& iBeacons}
For additional absolute location hints, we use the smartphones Wi-Fi and iBeacon sensor to measure the signal-strengths
of nearby transmitters. As the positions of both \docAP{}s and and \docIBeacon{}s are known beforehand, we compare
of nearby transmitters. As the positions of both \docAP{}s and \docIBeacon{}s are known beforehand, we compare
each measurement with its corresponding signal strength prediction which is defined by the 3D distance $d$
and the number of floors $\Delta f$ between the \docAPshort{} and the particle
%
@@ -72,24 +72,12 @@ Therefore, a smaller $\mPLE$ can be chosen to model the signal strength predicti
\subsection{Step- \& Turn-Detection}
\commentByToni{da muessen wir nochmal drueber reden. das problem ist glaube ich. das die state transition vorher zu wenig gestreut hat und dadurch auch zu wenige particles in "hochwinkligen" bereichen hatte. dann haben die turns immer entsprechen einen delay gehabt. bin mir also nicht sicher ob es wirklich das downvoting / sample impoverishment ist. hast du da vielleicht noch ein paar infos für mich? weil unser sigma war ja immer rießig... quasi fast gleichverteilt.}
A big disadvantage of using the state transition as proposal distribution is the high possibility of sample impoverishment due to a small measurement noise. This happens since accurate observations result in high peaks of the evaluation density and therefore the proposal density is not able to sample outside that peak \cite{Isard98:CCD}. This causes a downvoting of particles with increased heading deviation. ...
To prevent degradation within the particle-filter \cite{??} due to downvoting of particles with increased heading deviation, we incorporate the step- and turn-detection within the transition step.
A big disadvantage of using the state transition as proposal distribution is the high possibility of sample impoverishment due to a small measurement noise.
This happens since accurate observations result in high peaks of the evaluation density and therefore the proposal density is not able to sample outside that peak \cite{Isard98:CCD}.
Additionally, erroneous or delayed measurements from absolute positioning sensors like \docWIFI{} may lead to misplaced turns.
This causes a downvoting of particles with increased heading deviation.
Therefore, we incorporate the turn-detection, as well as the related step-detection, directly into the state transition $p(\mStateVec_{t} \mid \mStateVec_{t-1}, \mObsVec_{t-1})$. This leads to a more directed sampling instead of a truly random one.
directly into the transition
$p(\mStateVec_{t} \mid \mStateVec_{t-1}, \mObsVec_{t-1})$.
\cite{thrun?}\cite{lukas2014?} to get a more directed sampling instead of a truly random one.
This happens since accurate observations result in high peaks of the evaluation density and therefore the importance density is not able to sample outside that peak [IB98b].
\commentByFrank{todo: wie wird die unsicherheit in der transition eingebracht, sigma, ..}

11
tex/chapters/system.tex
View File

@@ -28,14 +28,14 @@ It should be noted, that we also include the current observation $\mObsVec_{t}$
Containing all relevant sensor measurements to evaluate the current state, the observation vector is defined as follows:
%
\begin{equation}
\mObsVec = (\mRssiVec_\text{wifi}, \mRssiVec_\text{ib}, \mObsHeading, \mObsPressure) \enspace,
\mObsVec = (\mRssiVec_\text{wifi}, \mRssiVec_\text{ib}, \mObsHeading, \mObsSteps, \mObsPressure) \enspace,
\end{equation}
%
where $\mRssiVec_\text{wifi}$ is the Wi-Fi and $\mRssiVec_\text{ib}$ the iBeacon signal strength vector.
The information, if a step or turn was detected, is given as a Boolean value.
\commentByToni{Wie sieht die Observation nun genau aus? Fehlt da nicht Step und Turn?}
Finally, $\mObsPressure$ is the relative barometric pressure referring to some fixed point in time.
For incorporating the highly different sensor types, one should refer to the process of probabilistic sensor fusion \cite{}.
Finally, $\mObsPressure$ is the relative barometric pressure with respect to some fixed point in time.
For incorporating the highly different sensor types, one should refer to the process of probabilistic sensor fusion \cite{Khaleghi2013}.
By assuming statistical independence of all sensor models, the probability density of the state evaluation is given by
%
\begin{equation}
@@ -51,6 +51,9 @@ By assuming statistical independence of all sensor models, the probability densi
Here, every single component refers to a probabilistic sensor model.
The barometer information is evaluated using $p(\vec{o}_t \mid \vec{q}_t)_\text{baro}$, whereby absolute position information is given by $p(\vec{o}_t \mid \vec{q}_t)_\text{ib}$ for iBeacons and by $p(\vec{o}_t \mid \vec{q}_t)_\text{wifi}$ for Wi-Fi.
\todo{art unseres particle filters hier einfuehren. transition als proposal. dann kann man spaeter bei step und turn besser begruenden warum wir es in die transition ziehen.}
It is well known that finding analytic solutions for densities is very difficult and they only exit in rare cases.
Therefore, numerical solutions like Gaussian filters or the broad class of Monte Carlo methods are deployed \cite{sarkka2013bayesian}.
Since we assume that indoor localisation is a time-sequential, non-linear and non-Gaussian process, a particle filter for approximating the posterior distribution is chosen.
Within this work the state transition $p(\mStateVec_{t} \mid \mStateVec_{t-1}, \mObsVec_{t})$ is used as proposal distribution, what is also known as CONDENSATION algorithm \cite{Isard98:CCD}.

6
tex/egbib.bib
View File

@@ -2507,7 +2507,7 @@ year = {2013}
@inproceedings{Liao2003,
abstract = { Tracking the activity of people in indoor environments has gained considerable attention in the robotics community over the last years. Most of the existing approaches are based on sensors, which allow to accurately determining the locations of people but do not provide means to distinguish between different persons. In this paper we propose a novel approach to tracking moving objects and their identity using noisy, sparse information collected by id-sensors such as infrared and ultrasound badge systems. The key idea of our approach is to use particle filters to estimate the locations of people on the Voronoi graph of the environment. By restricting particles to a graph, we make use of the inherent structure of indoor environments. The approach has two key advantages. First, it is by far more efficient and robust than unconstrained particle filters. Second, the Voronoi graph provides a natural discretization of human motion, which allows us to apply unsupervised learning techniques to derive typical motion patterns of the people in the environment. Experiments using a robot to collect ground-truth data indicate the superior performance of Voronoi tracking. Furthermore, we demonstrate that EM-based learning of behavior patterns increases the tracking performance and provides valuable information for high-level behavior recognition.},
author = {Liao, Lin Liao Lin and Fox, D. and Hightower, J. and Kautz, H. and Schulz, D.},
author = {Liao, Lin and Fox, D. and Hightower, J. and Kautz, H. and Schulz, D.},
booktitle = {Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)},
doi = {10.1109/IROS.2003.1250715},
file = {:home/toni/Documents/literatur/fusion16/Voronoi .pdf:pdf},
@@ -2556,10 +2556,6 @@ year = {2014}
}
@inproceedings{IPIN2015,
title = {Multisensor 3D Indoor Localisation}
}
@article{Hotelling1933,
abstract = {The problem is stated in detail, a method of analysis is derived and its geometrical meaning shown, methods of solution are illustrated and certain derivative problems are discussed. (To be concluded in October issue.) },
author = {Hotelling, H},