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

toni first_draft

Browse Source
This commit is contained in:
Toni
2016-02-15 15:27:00 +01:00
parent 5e46402611
commit ac542ba634
6 changed files with 110 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tex/chapters/abstract.tex
View File

@@ -6,6 +6,6 @@ In order to create such paths, we present a method that assigns an importance fa
The human movement is then modelled by moving along adjacent nodes into the most proper walking-direction.
To be able of going into the 3rd dimension, realistically shaped stairs for step-wise floor changes are used.
The position is estimated over multiple floors integrating different sensor modalities, namely Wi-Fi, iBeacons, barometer, step-detection and turn-detection.
The system was tested by omitting any time-consuming calibration process and starting with a uniform distribution instead of a well known pedestrian location.
The system was tested by omitting any time-consuming calibration process and starts with a uniform distribution instead of a well known pedestrian location.
The evaluation shows that adding prior knowledge is able to improve the localisation, even for unpredictable behaviour, faulty measurements and for poorly chosen system parameters.
\end{abstract}

2
tex/chapters/experiments.tex
View File

@@ -53,7 +53,7 @@
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
and is therefore not further evaluated.
To examine the contribution our approach is able to provided, 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}).
%

21
tex/chapters/grid.tex
View File

@@ -11,7 +11,7 @@
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, depicted in fig. \ref{fig:gridStairs}.
%
\begin{figure}
\centering
\input{gfx/grid/grid}
@@ -22,12 +22,12 @@
}
\label{fig:gridStairs}
\end{figure}
%
Stairs are defined using three points $\vec{\spoint}_1, \vec{\spoint}_2, \vec{\spoint}_3 \in \R^3$ whereby the segment
$[ \vec{\spoint}_1 \vec{\spoint}_2 ]$ describes the starting-edge, and $[ \vec{\spoint}_2 \vec{\spoint}_3 ]$ the stair's direction
(see fig. \ref{fig:gridStairs}). The grid-vertices corresponding to the starting-edge are determined using an intersection of
the segment $[ \vec{\spoint}_1 \vec{\spoint}_2 ]$ with the bounding-box for each vertex.
\commentByToni{Welche Bounding-box? hab ich was ueberlesen?}
To reduce the system's memory footprint, we search for the largest connected region within the graph and
remove all nodes and edges that are not connected to this region.
@@ -46,11 +46,12 @@
%
During a walk, each edge has an assigned probability $p(e)$ which depends on a chosen implementation.
This probability describes aspects such as the likelihood for walking into the edge's direction $\angle e$
given the current heading heading $\gHead$. Furthermore, we will incorporate additional prior knowledge to
given the current heading $\gHead$. Furthermore, we will incorporate additional prior knowledge to
favour some vertices/edges. For each single step on the graph, we calculate $p(e)$ for all available edges,
and, hereafter, randomly draw the to-be-walked edge depending on those probabilities. The random walk ends,
as soon as the distance $d$ is reached. The latter depends on the number of detected steps
$\mObsSteps$ and assumes an average step-size of \SI{0.7}{\meter}.
\commentByToni{steps steps... Allgemein finde ich den Absatz etwas komisch. erst wird p(e) eingefuehrt, dann kommt auf einmal prior knowledge und dann wie wir p(e) berechnen? reihenfolge passt da nicht so und macht es undeutlch. Hier soll doch eigentlich nur erklaert werden wie wir ueber den graphen laufen. egal ob prior oder nicht. laufen muessen wir ja}
For comparison purpose we define a simple weighting method that assigns a probability to each edge
just based on the deviation from the currently estimated heading $\gHead$:
@@ -83,6 +84,7 @@
larger open spaces, somewhere far from the walls. In order to calculate paths that resemble such a walking
behaviour, an importance factor is derived for each vertex within the graph. Those will be used to
adjust weight between two vertices, needed by the shortest-path algorithm.
\commentByToni{The edge's weight?? vielleicht?}
To downvote vertices near walls, we need to get the distance of each vertex from its nearest wall.
We therefore build an inverted version $G' = (V', E')$ of the graph $G$, just containing walls and other obstacles.
@@ -113,7 +115,7 @@
\label{sec:doorDetection}
Doors are usually anchored between two walls and have a normed width. Examining only a limited region
around the door, its surrounding walls describe a flat ellipse with the same center as the door itself.
around the door, its surrounding walls describe a flat ellipse with the same centre as the door itself.
It is thus possible to detect doors within the floorplan using a PCA.
To decide whether a vertex $v_{x,y,z}$ within the (non-inverted) grid $G$ belongs to a door, we use $k$-NN to fetch its
@@ -121,18 +123,19 @@
If the distance $\| \vec{c} - v_{x,y,z} \|$ between the centroid and the vertex-in-question is above a certain threshold,
the node does not belong to a door.
\todo{Distanzformel centroid/vertex. ideen? $\|v1 - v2\|$ oder $d(v1, v2)$?}
\commentByToni{Beides ist gebraeuchlich und $d$ ist kuerzer. von daher wuerde ich $d$ empfehlen.}
Assuming the distance is fine, we compare the two eigenvalues $\{\lambda_1, \lambda_2 \mid \lambda_1 > \lambda_2\}$,
determined by the PCA. If their ratio $\frac{\lambda_1}{\lambda_2}$ is above a certain threshold (flat ellipse)
the node-in-question belongs to a door or some kind of narrow passage.
%
\begin{figure}
\includegraphics[width=\columnwidth]{door_pca}
\caption{Detect doors within the floorplan using $k$-NN and PCA.
While the white nodes are walkable, the black ones represent walls. The grey node is the one in question.}
\label{fig:doorPCA}
\end{figure}
%
Fig. \ref{fig:doorPCA} depicts all three cases where
(left) the node is part of a door,
(middle) the distance between node and k-NN centroid is above the threshold and
@@ -246,7 +249,7 @@
This new reference node $\pathRef$ serves as a comparison base:
\commentByToni{Allgemein mal zur Schreibweise der Vertices. Irgendwie finde ich dieses $v_{x,y,z}$ nicht so gut. Ich denke jeder sieht das wir 3D haben und deswegen könntem man doch schlicht $v$, $v'$, $\hat{v}$ ... nutzen, oder was denkst du?}
\commentByFrank{war der vorschlag von frank d. letztes mal, weil man an vertices nicht einfach attribute (x,y,z) anhaengen kann wie wir es bei $\mObsVec$, $\mStateVec$ haben.}
%
\begin{equation}
\begin{split}
p(v_{x',y',z'} \mid v_{x,y,z})
@@ -259,7 +262,7 @@
\end{split}
\label{eq:transShortestPath}
\end{equation}
%
Eq. \eqref{eq:transShortestPath} combines the simple transition \refeq{eq:transSimple} with
a second probability, downvoting all nodes that are farther away from the reference $\pathRef$
than the previous step. Put another way: grid-steps increasing the distance to the reference

9
tex/chapters/introduction.tex
View File

@@ -41,6 +41,7 @@ Second, the heading for modelling the pedestrian's walking behaviour is calculat
and restricts the transition to perform only discrete \SI{45}{\degree} turns. While this is sufficient
for most cases, minor heading changes are often ignored and the posterior distribution (after walking)
is not smoothly spread.
\commentByToni{Und was machen wir dagegen?}
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.
@@ -50,14 +51,14 @@ Regarding a graph-based transition model, one could suggest to use the shortest
By incorporating this prior knowledge into the state transition step, a new state can be sampled in a more targeted manner.
However, for regular tessellated (grid) graphs, as used in \cite{Ebner-15}, this often leads to paths running very unnatural alongside walls.
Therefore, we present a novel approach that detects walls using the inverted graph (representing walls and obstacles) and a nearest-neighbour search.
\commentByFrank{hier kann man, wenn platz fehlt, vlt noch etwas details weglassen (inverted-graph, knn, etc)}
%\commentByFrank{hier kann man, wenn platz fehlt, vlt noch etwas details weglassen (inverted-graph, knn, etc)}
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.
Since areas near walls are 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:
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}
Therefore, a novel approach for detecting doors using again the inverted graph and a principal component analysis (PCA) \cite{Hotelling1933} is presented within this work.
%\commentByFrank{auch hier vlt das inverted erstmal noch weg lassen wegen platz}
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.

10
tex/chapters/system.tex
View File

@@ -24,11 +24,9 @@
where $x, y, z$ represent the position in 3D space, $\mObsHeading$ the user's heading and $\mStatePressure$ the
relative pressure prediction in hectopascal (hPa).
The recursive part of the density estimation contains all information up to time $t$.
Furthermore, the state transition models the pedestrian's movement based on random walks on graphs,
described in section \ref{sec:trans}.
Furthermore, the state transition models the pedestrian's movement as described in section \ref{sec:trans}.
%It should be noted, that we also include the current observation $\mObsVec_{t}$ in it.
Differing from the usual notation, the state transition also includes the current observation $\mObsVec_{t}$.
\commentByFrank{brauchen wir hier noch das cite?}
Differing from the usual notation, the state transition also includes the current observation $\mObsVec_{t}$ \cite{Koeping14}.
Containing all relevant sensor measurements to evaluate the current state, the observation vector is defined as follows:
%
@@ -38,8 +36,7 @@
%
where $\mRssiVec_\text{wifi}$ and $\mRssiVec_\text{ib}$ contain the measurements of all nearby \docAP{}s (\docAPshort{})
and \docIBeacon{}s, respectively. $\mObsHeading$ and $\mObsSteps$ describe the relative angular change and the number
of steps detected for the pedestrian.
of steps detected for the pedestrian.
Finally, $\mObsPressure$ is the relative barometric pressure with respect to some fixed point in time.
For further information on how to incorporate such highly different sensor types,
one should refer to the process of probabilistic sensor fusion \cite{Khaleghi2013}.
@@ -67,6 +64,5 @@
a particle filter is chosen as approximation of the posterior distribution.
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}.
\commentByFrank{caps? fehlt da noch was?}

173
tex/egbib.bib
View File

@@ -128,7 +128,7 @@ author={Wu Bo and R. Nevatia},
booktitle={Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on},
title={Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection},
year={2006},
month={June},
IGNOREmonth={June},
volume={1},
pages={951-958},
}
@@ -165,9 +165,9 @@ pages={951-958},
@inproceedings{Fang09,
author={Shih-Hau Fang and Tsung-Nan Lin},
booktitle={Intelligent Signal Processing, 2009. WISP 2009. IEEE International Symposium on},
title={Accurate WLAN Indoor Localization Based on RSS, Fluctuations Modeling},
title={{Accurate WLAN Indoor Localization Based on RSS, Fluctuations Modeling}},
year={2009},
month={Aug},
IGNOREmonth={Aug},
pages={27-30},
}
@@ -193,7 +193,7 @@ author={C.R. Wran and A. Azarbayejani and T. Darrell and A. P. Pentland.},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Pfinder: real-time tracking of the human body},
year={1997},
month={Jul},
IGNOREmonth={Jul},
volume={19},
number={7},
pages={780-785},
@@ -207,13 +207,13 @@ pages={780-785},
volume = {19},
number = {2},
pages = {31--40},
month = {12},
IGNOREmonth = {12},
}
@article{Ville09,
author = {Ville Honkavirta and Tommi Perälä and Simo Ali-Löytty and Robert Piche},
title = {A Comparative Survey of WLAN Location Fingerprinting Methods},
journal = {Workshop on Positiong, Navigation and Communication},
journal = {Workshop on Positioning, Navigation and Communication},
year = {2009},
volume = {6},
number = {1},
@@ -315,7 +315,7 @@ author={Luo, R.C. and Chun Chi Lai},
booktitle={Advanced Robotics and Its Social Impacts, 2007. ARSO 2007. IEEE Workshop on},
title={Indoor Mobile Robot Localization using Probabilistic Multi-Sensor Fusion},
year={2007},
month={Dec},
IGNOREmonth={Dec},
pages={1-6},
keywords={feature extraction;mobile robots;sensor fusion;service robots;Hokuyo infrared range-finder;Polaroid 6500 ultrasonic rangers;feature extraction;indoor mobile robot localization;light refraction;mobile service robot;probabilistic multisensor fusion;servo sonar ring;Acoustic materials;Acoustic refraction;Acoustic sensors;Feature extraction;Indoor environments;Mobile robots;Sensor phenomena and characterization;Service robots;Servomechanisms;Sonar measurements},
doi={10.1109/ARSO.2007.4531415},}
@@ -325,7 +325,7 @@ author={Luo, R.C. and Chih-Chia Chang and Chun Chi Lai},
journal={IEEE Sensors Journal},
title={Multisensor Fusion and Integration: Theories, Applications, and its Perspectives},
year={2011},
month={Dec},
IGNOREmonth={Dec},
volume={11},
number={12},
pages={3122-3138},
@@ -338,7 +338,7 @@ author={Blanchart, P. and Liyun He and Le Gland, F.},
booktitle={FUSION 09},
title={Information fusion for indoor localization},
year={2009},
month={July},
IGNOREmonth={July},
pages={2083-2090},
keywords={belief networks;particle filtering (numerical methods);traffic information systems;Bayesian filter;cartographic constraints;indoor localization;information fusion;particle filter approximation;pedestrian user;proximity beacon measurements;Additive noise;Bayesian methods;Glands;Helium;Information filtering;Information filters;Information resources;Particle measurements;Position measurement;Telecommunications;cartographic constraints;information fusion;particle filtering;pedestrian navigation system (PNS);proximity beacon;ranging beacon},}
@@ -347,7 +347,7 @@ author={Golding, A.R. and Lesh, N.},
booktitle={Wearable Computers, 1999. Digest of Papers. The Third International Symposium on},
title={Indoor Navigation Using a Diverse Set Of Cheap, Wearable Sensors},
year={1999},
month={Oct},
IGNOREmonth={Oct},
pages={29-36},
keywords={accelerometers;computerised instrumentation;computerised navigation;force sensors;inference mechanisms;intelligent sensors;learning (artificial intelligence);magnetic sensors;magnetometers;optical sensors;sensor fusion;temperature sensors;user modelling;accelerometers;algorithm performance;context awareness;data cooking module;error rate;high-level features computation;indoor navigation algorithm;information integration;light sensors;machine learning;magnetometers;raw sensor signals;sensor input stream;temperature sensors;user location inference;user state inference;wearable sensors;Accelerometers;Context awareness;Error analysis;Machine learning;Magnetic sensors;Magnetometers;Navigation;Sensor phenomena and characterization;Temperature sensors;Wearable sensors},
doi={10.1109/ISWC.1999.806640},}
@@ -357,7 +357,7 @@ author={Wei Meng and Wendong Xiao and Wei Ni and Lihua Xie},
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={Secure and robust Wi-Fi fingerprinting indoor localization},
year={2011},
month={Sept},
IGNOREmonth={Sept},
pages={1-7},
keywords={fingerprint identification;indoor radio;radio networks;telecommunication security;wireless LAN;K nearest neighbor algorithm;KNN;Wi-Fi wireless networks;access point attacks;distribution estimation;in-building communication infrastructures;indoor positioning;probabilistic fingerprinting localization method;random sample consensus;reference points;robust Wi-Fi fingerprinting indoor localization;secure Wi-Fi fingerprinting indoor localization;weighted-mean method;Accuracy;Distortion measurement;Histograms;IEEE 802.11 Standards;Probabilistic logic;Robustness;Sensors;RANSAC;Wi-Fi;fingerprinting;indoor localization;sensor network;signal strength;wireless network},
doi={10.1109/IPIN.2011.6071908},}
@@ -367,7 +367,7 @@ author={Boonsriwai, S. and Apavatjrut, A.},
booktitle={Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2013 10th International Conference on},
title={Indoor WIFI localization on mobile devices},
year={2013},
month={May},
IGNOREmonth={May},
pages={1-5},
keywords={Global Positioning System;buildings (structures);communication complexity;indoor radio;smart phones;wireless LAN;GPS;WIFI localization techniques;WIFI-enable devices;access points;building structures;computational complexity;fingerprinting localization techniques;indoor WIFI localization;localization algorithms;mobile devices;mobile users;multitrilateration;positioning calculation;reference position;signal degradation;smartphone;system resource consumption;wireless device;wireless signal;Accuracy;Buildings;Databases;Distance measurement;IEEE 802.11 Standards;Mobile communication;Mobile handsets},
doi={10.1109/ECTICon.2013.6559592},}
@@ -377,7 +377,7 @@ author={Mirowski, Piotr and Ho, Tin Kam and Saehoon Yi and MacDonald, Michael},
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals},
year={2013},
month={Oct},
IGNOREmonth={Oct},
pages={1-10},
keywords={LTE;SLAM;WiFi;crowd-sourcing;kernel methods;localization},
doi={10.1109/IPIN.2013.6817853},}
@@ -387,7 +387,7 @@ author={Biswas, J. and Veloso, M.},
booktitle={Robotics and Automation (ICRA), 2010 IEEE International Conference on},
title={WiFi localization and navigation for autonomous indoor mobile robots},
year={2010},
month={May},
IGNOREmonth={May},
pages={4379-4384},
keywords={constraint theory;graph theory;mobile robots;path planning;sampling methods;signal detection;wireless LAN;WiFi localization;WiFi sensory data;autonomous indoor mobile robots;continuous perceptual model;custom built mobile robot;discrete graph based WiFi signal strength sampling;geometric constraints;Indoor environments;Mobile robots;Robot kinematics;Robot sensing systems;Robotics and automation;Robustness;Signal generators;Skeleton;Solid modeling;Sonar navigation},
doi={10.1109/ROBOT.2010.5509842},
@@ -500,7 +500,7 @@ author={Ohya, A. and Kosaka, A. and Kak, A.},
journal={IEEE Transactions on Robotics and Automation},
title={Vision-based navigation by a mobile robot with obstacle avoidance using single-camera vision and ultrasonic sensing},
year={1998},
month={Dec},
IGNOREmonth={Dec},
volume={14},
number={6},
pages={969-978},
@@ -513,7 +513,7 @@ author={Ganapathi, V. and Plagemann, C. and Koller, D. and Thrun, S.},
booktitle={Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on},
title={Real time motion capture using a single time-of-flight camera},
year={2010},
month={June},
IGNOREmonth={June},
pages={755-762},
keywords={filtering theory;motion estimation;pose estimation;filtering algorithm;human pose markerless tracking;kinematic chain;local model-based search;monocular depth image;programmable graphics hardware;real time motion capture;single time-of-flight camera;unscented transform;Biological system modeling;Cameras;Computer science;Filtering algorithms;Graphics;Humans;Kinematics;Layout;Motion analysis;Tracking},
doi={10.1109/CVPR.2010.5540141},
@@ -521,10 +521,10 @@ ISSN={1063-6919},}
@INPROCEEDINGS{Koeping14,
author = {L. K{\"o}ping and M. Grzegorzek and F. Deinzer},
title = {Probabilistic Step and Turn Detection in Indoor Localisation},
title = {{Probabilistic Step and Turn Detection in Indoor Localisation}},
booktitle = {Data Fusion and Target Tracking Conference},
year = {2014},
month = {April},
IGNOREmonth = {April},
}
@ARTICLE{Zhao08,
@@ -532,7 +532,7 @@ author={Tao Zhao and Nevatia, R. and Bo Wu},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Segmentation and Tracking of Multiple Humans in Crowded Environments},
year={2008},
month={July},
IGNOREmonth={July},
volume={30},
number={7},
pages={1198-1211},
@@ -554,7 +554,7 @@ ISSN={0162-8828},}
title = {{On Sequential Monte Carlo Sampling Methods for Bayesian Filtering}},
journal = {Statistics and Computing},
year = {2000},
month = {July},
IGNOREmonth = {July},
volume = {10},
number = {3},
pages = {197-208},
@@ -565,7 +565,7 @@ ISSN={0162-8828},}
title = {{Novel approach to nonlinear/non-Gaussian Bayesian state estimation}},
journal = {IEE Proceedings F Radar and Signal Processing},
year = {1993},
month = {April},
IGNOREmonth = {apr},
volume = {140},
number = {2},
pages = {107-113},
@@ -573,10 +573,10 @@ ISSN={0162-8828},}
@article {Isard98:CCD,
author = {Michael Isard and Andrew Blake},
title = {CONDENSATION - Conditional Density Propagation for Visual Tracking},
title = {{CONDENSATION - Conditional Density Propagation for Visual Tracking}},
journal = {International Journal of Computer Vision},
year = {1998},
month = {August},
IGNOREmonth = {aug},
volume = {29},
number = {1},
pages = {5-28},
@@ -587,7 +587,7 @@ ISSN={0162-8828},}
title = {A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking},
journal = {IEEE Transactions on Signal Processing},
year = {2002},
month = {February},
IGNOREmonth = {feb},
volume = {50},
number = {2},
pages = {174-188},
@@ -1251,7 +1251,7 @@ ISSN={0162-8828},}
publisher={The MIT Press},
address = {Cambridge, MA, USA},
year={2005},
month={8},
IGNOREmonth={8},
isbn={9780262201629},
totalpages={672},
}
@@ -1467,12 +1467,12 @@ ISSN={0162-8828},}
% FHWS Journal
@ARTICLE{Koeping14-ILU,
author={K{\"o}ping, Lukas and Ebner, Frank and Grzegorzek, Marcin and Deinzer, Frank},
title={Indoor Localization Using Step and Turn Detection Together with Floor Map
Information},
title={{Indoor Localization Using Step and Turn Detection Together with Floor Map
Information}},
journal={FHWS Science Journal},
publisher={University of Applied Sciences W{\"u}rzburg - Schweinfurt},
address={W{\"u}rzburg},
pages={9},
numpages={9},
volume={},
number={},
year={2014},
@@ -1480,10 +1480,10 @@ ISSN={0162-8828},}
@inproceedings{Koeping14-PSA,
author = {Lukas K\"{o}ping and Marcin Grzegorzek and Frank Deinzer},
title = {Probabilistic Step and Turn Detection in Indoor Localization},
title = {{Probabilistic Step and Turn Detection in Indoor Localization}},
booktitle = {Conference on Data Fusion and Target Tracking 2014: Algorithms and Applications (DFTT 2014)},
year = {2014},
month = {April},
IGNOREmonth = {April},
address = {Liverpool, UK},
pages = {1-7},
}
@@ -1493,7 +1493,7 @@ ISSN={0162-8828},}
title = {{A Framework for Actively Selecting Viewpoints in Object Recognition}},
journal = {International Journal of Pattern Recognition and Artificial Intelligence},
year = {2009},
month = {June},
IGNOREmonth = {June},
volume = {23},
number = {4},
pages = {765-799},
@@ -1513,7 +1513,7 @@ ISSN={0162-8828},}
title = {FootPath: Accurate map-based indoor navigation using smartphones},
journal = {Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
year = {2011},
month = {September},
IGNOREmonth = {September},
pages = {1-8},
}
@@ -1523,7 +1523,7 @@ author={Mofarreh-Bonab, Mostafa and Ghorashi, Seyed Ali},
booktitle={3th International eConference on Computer and Knowledge Engineering (ICCKE)},
title={A low complexity and high speed gradient descent based secure localization in Wireless Sensor Networks},
year={2013},
month={Oct},
IGNOREmonth={Oct},
pages={300-303},
keywords={gradient methods;iterative methods;least mean squares methods;telecommunication network routing;telecommunication security;wireless sensor networks;LMdS;WSN;fault probability;gradient based method;gradient descent algorithm;gradient descent based secure localization;high speed gradient descent based secure localization;iterative algorithms;least median square;localization;localization error;monitoring applications;network quality;routing;voting based secure localization;wireless sensor networks;Estimation;Monitoring;Robustness;Wireless sensor networks;gradient based localization;iterative algorithm;secure localization},
doi={10.1109/ICCKE.2013.6682841},}
@@ -1533,7 +1533,7 @@ doi={10.1109/ICCKE.2013.6682841},}
title = {Monte Carlo Smoothing for Nonlinear Time Series},
journal = {Journal of the American Statistical Association},
year = {2004},
month = {March},
IGNOREmonth = {March},
volume = {99},
number = {465},
pages = {156-168},
@@ -1544,7 +1544,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Wearable Computers, 2003. Proceedings of the Seventh IEEE International Symposium on},
title={{Using gravity to estimate accelerometer orientation}},
year={2003},
month={October},
IGNOREmonth={October},
pages={252-253},
}
@@ -1553,7 +1553,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Wearable Computers, 2009. ISWC '09. International Symposium on},
title={{Which Way Am I Facing: Inferring Horizontal Device Orientation from an Accelerometer Signal}},
year={2009},
month={September},
IGNOREmonth={September},
pages={149-150},
}
@@ -1562,7 +1562,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Pervasive Computing and Communications (PerCom), 2010 IEEE International Conference on},
title={{Dead reckoning from the Pocket - An Experimental Study}},
year={2010},
month={March},
IGNOREmonth={March},
pages={162-170},
}
@@ -1571,7 +1571,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={Using Barometers to Determine the Height for Indoor Positioning},
year={2013},
month={Oct},
IGNOREmonth={Oct},
pages={1-7},
}
@@ -1580,7 +1580,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={Particle Filter and Smoother for Indoor Localization},
year={2013},
month={October},
IGNOREmonth={October},
pages={1-10},
}
@@ -1589,7 +1589,7 @@ doi={10.1109/ICCKE.2013.6682841},}
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={A Topological Approach with MEMS in Smartphones based on Routing-Graph},
year={2015},
month={October},
IGNOREmonth={October},
pages={1-6},
}
@@ -1608,7 +1608,7 @@ author={Tian, J. and H{\"a}hner, J. and Becker, C. and Stepanov, I. and Rotherme
booktitle={Simulation Symposium, 2002. Proceedings of the 35th Annual},
title={Graph-based Mobility Model for Mobile ad-hoc Network Simulation},
year={2002},
month={April},
IGNOREmonth={April},
pages={337-344},
keywords={graph theory;mobile communication;mobile computing;protocols;telecommunication network routing;ad hoc routing protocols;graph-based mobility model;mobile ad hoc network;mobile ad hoc networks;random walk model;realistic movement;routing protocols;spatial constraints;Brain modeling;Cities and towns;Electronic mail;Mobile ad hoc networks},
doi={10.1109/SIMSYM.2002.1000171},
@@ -1619,7 +1619,7 @@ ISSN={1082-241X},}
title = {Walk Detection and Step Counting on Unconstrained Smartphones},
booktitle = {Proceedings of the 2013 ACM Conference on Ubiquitous Computing},
year = {2013},
month = {September},
IGNOREmonth = {September},
isbn = {978-1-4503-1770-2},
location = {Zurich, Switzerland},
pages = {225--234},
@@ -1630,7 +1630,7 @@ ISSN={1082-241X},}
title = {{A reliable and accurate indoor localization method using phone inertial sensors}},
booktitle = {Proceedings of the 2012 ACM Conference on Ubiquitous Computing},
year = {2012},
month = {September},
IGNOREmonth = {September},
pages = {421--430},
}
@@ -1639,7 +1639,7 @@ ISSN={1082-241X},}
title = {{Pedestrian Localisation for Indoor Environments}},
journal = {Proceedings of the 10th International Conference on Ubiquitous Computing},
year = {2008},
month = {September},
IGNOREmonth = {September},
pages = {114-123},
}
@@ -1648,7 +1648,7 @@ ISSN={1082-241X},}
title={{Information Fusion for Indoor Localization}},
booktitle={Proceedings of the 12th International Conference on Information Fusion},
year={2009},
month={July},
IGNOREmonth={July},
pages={2083--2090},
}
@@ -1678,7 +1678,7 @@ ISSN={1082-241X},}
year = {2001},
pages = {239-245},
booktitle = {Pattern Recognition -- Proceedings of the 23rd DAGM Symposium},
month = {9},
IGNOREmonth = {9},
editor = {B. Radig},
series = {LNCS},
volume = {2191},
@@ -1701,7 +1701,7 @@ author={Fetzer, Toni and Deinzer, Frank and K{\"o}ping, Lukas and Grzegorzek, Ma
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={Statistical Indoor Localization Using Fusion of Depth-Images and Step Detection},
year={2014},
month={October},
IGNOREmonth={October},
pages={1-9}}
@INPROCEEDINGS{Ebner14,
@@ -1709,7 +1709,7 @@ author={Ebner, Frank and Deinzer, Frank and K{\"o}ping, Lukas and Grzegorzek, Ma
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={{R}obust {S}elf-{L}ocalization using {W}i-{F}i, {S}tep/{T}urn-{D}etection and {R}ecursive {D}ensity {E}stimation},
year={2014},
month={October},
IGNOREmonth={October},
pages={1-9}}
@phdthesis{mautz2012indoor,
@@ -1724,7 +1724,7 @@ author={Parviainen, J. and Kantola, J. and Collin, J.},
booktitle={Position, Location and Navigation Symposium, 2008 IEEE/ION},
title={Differential barometry in personal navigation},
year={2008},
month={May},
IGNOREmonth={May},
pages={148-152},
keywords={barometers;height measurement;microsensors;pressure sensors;satellite navigation;MEMS barometer data;altitude information;differential barometry;personal navigation;satellite navigation systems;Costs;Floors;Global Positioning System;Internet;Least squares methods;Micromechanical devices;Satellite navigation systems;Seismic measurements;TCPIP;Ventilation},
doi={10.1109/PLANS.2008.4570051},}
@@ -1740,9 +1740,9 @@ doi={10.1109/PLANS.2008.4570051},}
@inproceedings{Ebner-15,
author={Ebner, Frank and Fetzer, Toni and K{\"o}ping, Lukas and Grzegorzek, Marcin and Deinzer, Frank},
booktitle={Indoor Positioning and Indoor Navigation (IPIN), International Conference on},
title={Multi Sensor 3D Indoor Localisation},
title={{Multi Sensor 3D Indoor Localisation}},
year={2015},
month={October},
IGNOREmonth={October},
pages={1-10},
}
@@ -1773,7 +1773,7 @@ author={Hazas, M. and Scott, J. and Krumm, J.},
journal={Computer},
title={{Location-aware Computing Comes of Age}},
year={2004},
month={February},
IGNOREmonth={February},
volume={37},
number={2},
pages={95-97},
@@ -1785,7 +1785,7 @@ pages={95-97},
journal = {Communications of the ACM},
volume = {54},
number = {5},
month = {May},
IGNOREmonth = {May},
year = {2011},
pages = {121--128},
}
@@ -1796,7 +1796,7 @@ pages={95-97},
journal = {Personal and Ubiquitous Computing},
volume = {7},
number = {1},
month = {May},
IGNOREmonth = {May},
year = {2003},
pages = {70--79},
}
@@ -1824,7 +1824,7 @@ author={Perera, C. and Zaslavsky, A. and Christen, P. and Georgakopoulos, D.},
journal={Communications Surveys Tutorials, IEEE},
title={{Context Aware Computing for The Internet of Things: A Survey}},
year={2014},
month={First Quarter},
IGNOREmonth={First Quarter},
volume={16},
number={1},
pages={414-454},
@@ -1838,11 +1838,11 @@ doi = {10.1109/IPIN.2014.7275539},
file = {:home/toni/Documents/literatur/fusion16/Motion model for positioning with graph-based indoor map.pdf:pdf},
isbn = {978-1-4673-8054-6},
keywords = {Atmospheric measurements,Computational modeling,Particle measurements,Position measurement,Proposals,TLL,Training data,Wireless LAN,graph,graph theory,graph-based indoor map,indoor navigation,indoor positioning,map-matching,motion model,particle filter,particle filtering (numerical methods),position measurement,radio links,real-data WLAN positioning test,total link length,training-free probabilistic pedestrian motion mode,wireless LAN},
month = {oct},
IGNOREmonth = {oct},
pages = {646--655},
publisher = {IEEE},
shorttitle = {Indoor Positioning and Indoor Navigation (IPIN), 2},
title = {{Motion model for positioning with graph-based indoor map}},
title = {{Motion Model for Positioning with Graph-based Indoor Map}},
year = {2014}
}
@@ -1893,7 +1893,7 @@ year = {2014}
author = {Kypraios, Theo},
title = {Introduction to Bayesian Statistics},
year = {2012},
month = {10},
IGNOREmonth = {10},
note = {Lecture Presentation},
url = {https://www.maths.nottingham.ac.uk/personal/tk/files/talks/Cran_10_12.pdf [\today]}
}
@@ -2162,7 +2162,7 @@ number={2},
pages={107-113},
keywords={Bayes methods;Kalman filters;filtering and prediction theory;state estimation;tracking;Gaussian noise;algorithm;bearings only tracking problem;bootstrap filter;extended Kalman filter;measurement model;nonGaussian Bayesian state estimation;nonlinear Bayesian state estimation;random samples;recursive Bayesian filters;simulation;state transition model;state vector density},
ISSN={0956-375X},
month={Apr},
IGNOREmonth={Apr},
}
@@ -2184,7 +2184,7 @@ month={Apr},
@PHDTHESIS{blanco2009phd,
author = {Blanco, Jos{\'{e}}-Luis},
month = {{nov}},
IGNOREmonth = {{nov}},
title = {Contributions to Localization, Mapping and Navigation in Mobile Robotics},
year = {2009},
school = {PhD. in Electrical Engineering, University of Malaga},
@@ -2405,7 +2405,7 @@ year={2009},
pages={122-131},
keywords={graph theory;radio tracking;radiofrequency identification;radionavigation;telecommunication network topology;RFID-based positioning;base graph model;indoor navigation;indoor positioning technologies;indoor tracking;specific reader deployment graph model;symbolic positioning technologies;uniform data management infrastructure;Bluetooth;Computer science;Data structures;Mobile computing;Navigation;Partitioning algorithms;Radiofrequency identification;Space technology;Technology management;Topology},
doi={10.1109/MDM.2009.23},
month={May},}
IGNOREmonth={May},}
@MastersThesis{Ebner:Thesis:2013,
author = {Frank Ebner},
@@ -2448,11 +2448,11 @@ file = {:home/toni/Documents/literatur/fusion16/Real-time indoor navigation usin
isbn = {978-1-4673-8402-5},
keywords = {5th EvAAL indoor navigation competition,Fingerprint recognition,IEEE 802.11 Standard,Indoor navigation,Localisation System,MEMS sensors,Magnetometers,Position measurement,Sensors,WiFi fingerprinting,WiFi positioning,accelerometers,barometer,barometers,dead-reckoning,floor change detection,gyros,gyroscopes,indoor navigation,magnetic features,magnetic matching,magnetometers,micromechanical devices,position-tracking module,radionavigation,real-time indoor navigation,smart phones,smartphone,smartphone sensors,wireless LAN},
mendeley-tags = {Localisation System},
month = {oct},
IGNOREmonth = {oct},
pages = {1--10},
publisher = {IEEE},
shorttitle = {Indoor Positioning and Indoor Navigation (IPIN), 2},
title = {{Real-time indoor navigation using smartphone sensors}},
title = {{Real-time Indoor Navigation using Smartphone Sensors}},
year = {2015}
}
@@ -2463,7 +2463,7 @@ file = {:home/toni/Documents/literatur/fusion16/Mobility Increases Localizabilit
issn = {03600300},
journal = {ACM Computing Surveys},
keywords = {Mobility,smartphones,wireless indoor localization},
month = {apr},
IGNOREmonth = {apr},
number = {3},
pages = {1--34},
publisher = {ACM},
@@ -2484,7 +2484,7 @@ keywords = {Indoor positioning systems,Location techniques,Personal networks},
number = {1},
pages = {13--32},
shorttitle = {Communications Surveys {\&} Tutorials, IEEE},
title = {{A survey of indoor positioning systems for wireless personal networks}},
title = {{A Survey of Indoor Positioning Systems for Wireless Personal Networks}},
volume = {11},
year = {2009}
}
@@ -2497,7 +2497,7 @@ file = {:home/toni/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/K
issn = {15662535},
journal = {Information Fusion},
keywords = {Fusion methodologies,Multisensor data fusion,Taxonomy},
month = {jan},
IGNOREmonth = {jan},
number = {1},
pages = {28--44},
title = {{Multisensor data fusion: A review of the state-of-the-art}},
@@ -2516,7 +2516,7 @@ keywords = {Computer science,Humans,Indoor environments,Particle filters,Pattern
pages = {723--728},
publisher = {IEEE},
shorttitle = {Intelligent Robots and Systems, 2003. (IROS 2003).},
title = {{Voronoi tracking: location estimation using sparse and noisy sensor data}},
title = {{Voronoi Tracking: Location Estimation Using Sparse and Noisy Sensor Data}},
volume = {1},
year = {2003}
}
@@ -2531,9 +2531,9 @@ issn = {1948-660X},
journal = {Journal of Spatial Information Science},
keywords = {context-awareness,indoor spatial data models,location-dependent queries,navigation systems and wayfinding,qualitative spatial representation,quantitative spatial representation},
language = {en},
month = {jun},
IGNOREmonth = {Jun},
number = {4},
pages = {85----123},
pages = {85--123},
title = {{Spatial models for context-aware indoor navigation systems: A survey}},
volume = {1},
year = {2012}
@@ -2541,14 +2541,14 @@ year = {2012}
@inproceedings{Hilsenbeck2014,
abstract = {We propose a graph-based, low-complexity sensor fusion approach for ubiquitous pedestrian indoor positioning using mobile devices. We employ our fusion technique to combine relative motion information based on step detection with WiFi signal strength measurements. The method is based on the well-known particle filter methodology. In contrast to previous work, we provide a probabilistic model for location estimation that is formulated directly on a fully discretized, graph-based representation of the indoor environment. We generate this graph by adaptive quantization of the indoor space, removing irrelevant degrees of freedom from the estimation problem. We evaluate the proposed method in two realistic indoor environments using real data collected from smartphones. In total, our dataset spans about 20 kilometers in distance walked and includes 13 users and four different mobile device types. Our results demonstrate that the filter requires an order of magnitude less particles than state-of-the-art approaches while maintaining an accuracy of a few meters. The proposed low-complexity solution not only enables indoor positioning on less powerful mobile devices, but also saves much-needed resources for location-based end-user applications which run on top of a localization service.},
address = {New York, New York, USA},
address = {New York, NY, USA},
author = {Hilsenbeck, Sebastian and Bobkov, Dmytro and Schroth, Georg and Huitl, Robert and Steinbach, Eckehard},
booktitle = {Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing - UbiComp '14 Adjunct},
doi = {10.1145/2632048.2636079},
file = {:home/toni/Documents/literatur/fusion16/Graph-based Data Fusion of Pedometer and WiFi Measurements for Mobile Indoor Positioning.pdf:pdf},
isbn = {9781450329682},
keywords = {Graph-based Sensor Fusion,Indoor Navigation,Indoor Positioning,Location-based Services,Mobile Computing,Particle Filter,Ubiquitous Localization},
month = {sep},
IGNOREmonth = {sep},
pages = {147--158},
publisher = {ACM Press},
title = {{Graph-based Data Fusion of Pedometer and WiFi Measurements for Mobile Indoor Positioning}},
@@ -2556,11 +2556,15 @@ year = {2014}
}
@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},
title = {{Analysis of a complex of statistical variables into Principal Components. Jour. Educ. Psych., 24, 417-441, 498-520}},
year = {1933}
@article{hotelling1933,
title={{Analysis of a Complex of Statistical Variables into Principal Components.}},
author={Hotelling, Harold},
journal={Journal of educational psychology},
volume={24},
number={6},
pages={417},
year={1933},
publisher={Warwick \& York}
}
@article{Thrun2003,
@@ -2577,7 +2581,7 @@ number = {2},
pages = {111--127},
pmid = {563334},
publisher = {Kluwer Academic Publishers},
title = {{Learning occupancy grid maps with forward sensor models}},
title = {{Learning Occupancy Grid Maps with Forward Sensor Models}},
volume = {15},
year = {2003}
}
@@ -2590,7 +2594,7 @@ file = {:home/toni/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/L
issn = {01989715},
journal = {Computers, Environment and Urban Systems},
keywords = {Grid graph-based representation,Indoor spaces,Network,Structural-based modeling},
month = {nov},
IGNOREmonth = {nov},
number = {6},
pages = {532--540},
title = {{A grid graph-based model for the analysis of 2D indoor spaces}},
@@ -2599,7 +2603,7 @@ year = {2010}
}
@article{elfes1989using,
title={Using occupancy grids for mobile robot perception and navigation},
title={{Using Occupancy Grids for Mobile Robot Perception and Navigation}},
author={Elfes, Alberto},
journal={Computer},
volume={22},
@@ -2617,11 +2621,11 @@ file = {:home/toni/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/G
issn = {15249050},
journal = {IEEE Transactions on Intelligent Transportation Systems},
keywords = {Indoor pedestrian navigation,inertial navigation,multistory localization and mapping,simultaneous localization and mapping (SLAM)},
month = {aug},
IGNOREmonth = {aug},
number = {4},
pages = {1714--1727},
shorttitle = {Intelligent Transportation Systems, IEEE Transacti},
title = {{Pedestrian simultaneous localization and mapping in multistory buildings using inertial sensors}},
title = {{Pedestrian Simultaneous Localization and Mapping in Multistory Buildings using Inertial Sensors}},
volume = {15},
year = {2014}
}
@@ -2648,7 +2652,6 @@ year = {2000}
booktitle={IOP Conference Series: Earth and Environmental Science},
volume={18},
number={1},
pages={012123},
year={2014},
organization={IOP Publishing}
}
@@ -2661,11 +2664,11 @@ doi = {10.1109/GeoInformatics.2011.5980680},
isbn = {9781612848488},
issn = {9781612848495},
keywords = {evacuation planning,grid graph-based model,indoor space},
month = {jun},
IGNOREmonth = {jun},
pages = {1--4},
publisher = {IEEE},
shorttitle = {Geoinformatics, 2011 19th International Conference},
title = {{Indoor evacuation routes planning with a grid graph-based model}},
title = {{Indoor Evacuation Routes Planning with a Grid Graph-based Model}},
year = {2011}
}
@@ -2694,7 +2697,7 @@ isbn = {0018-9448},
issn = {15579654},
journal = {IEEE Transactions on Information Theory},
keywords = {Pattern classification},
month = {jan},
IGNOREmonth = {jan},
number = {1},
pages = {21--27},
pmid = {21919855},