deletions | additions       diff --git a/chapter_Introduction_label_chap_introduction__.tex b/chapter_Introduction_label_chap_introduction__.tex  index a928cf8..14a7150 100644  --- a/chapter_Introduction_label_chap_introduction__.tex  +++ b/chapter_Introduction_label_chap_introduction__.tex 
...
filter (ii) software for augmenting an image with synthetic views,  (iii) a script for evaluating a map based on histograms and  corresponding $x,y$-positions.  \section{Research Questions}  \label{sec:researchquestions}  The research questions addressed in this thesis are:  \begin{itemize}  \item Can 2D positions be estimated in real-time using a machine  learning approach on a limited processor in a modifiable indoor  environment?  %\item Is accurate real-world localization regression possible when the  % training data comprises synthetic data only?  \item Can we predict the suitability of a given map for the proposed  localization approach?  \end{itemize}  \section{Outline}  \label{sec:outline}  The remainder of this thesis is structured as follows.  Chapter~\ref{chap:relatedwork} surveys existing indoor localization  approaches related to this thesis. In Chapter~\ref{chap:methods}, the  developed texton-based approach is presented and its components, the  $k$NN algorithm and the particle filter, are introduced. Details about  the synthetic data generation tool and map evaluation technique are  also given. Chapter~\ref{chap:analysis} describes the setup of the  on-ground and in-flight experiments. The results of the experiments  are presented in Chapter~\ref{chap:results} and discussed in  Chapter~\ref{chap:discussion}. Finally, we draw our conclusions and  indicate future research directions in Chapter~\ref{chap:conclusion}.