deletions | additions       diff --git a/section_Methodology_The_approach_proposed__.tex b/section_Methodology_The_approach_proposed__.tex  index 4e0f218..a4eade4 100644  --- a/section_Methodology_The_approach_proposed__.tex  +++ b/section_Methodology_The_approach_proposed__.tex 
...
\section{Methodology}  The approach proposed in this paper consists in identifying different conditions that may have an impact on tracking performance andon the accuracy of  traffic variables such as counts. For each condition, we need two video samples or regions in the same video where the only or main difference is the change in that condition. The method relies on the following four main steps: \begin{enumerate}  \item Selection of sites and analysis zones: Five five  different camera views are specifically selected to allow for analysis based on the  chosen comparison points. conditions to be compared.  Ten minutes of video are manually annotated for each an  analysis zone in each camera view  to be used as a baseline for the analysis. \item Optimization of tracking parameters over the whole annotated period (10~min):  a ten minute period: The subset of the  tracking parametersused in computer vision  are optimized and saved for each camera view  using the chosen measure of performance for each camera. performance.  These results are used to evaluate traffic data and correlation correlations  of parameters compared to with  the measure of performance. \item Optimization of tracking parameters over the first five minute period: The best results from the tracking parameters optimized for  the first five annotated  minutes of each camera view  are checked for over-fitting by using applied to  the second whole 10 minute  annotated segment video,  as a separate dataset. Close and far well as to sub-regions of the  analysis zones are tested. (two sub-regions, one near and one far from the camera), in order to evaluate over-fitting.  \item The best-fit optimized tracking  parameters from step 3 are applied toto  the full ten minutes of each analysis zone camera view  to check for evaluate the  transferability between sites, camera types and weather conditions. \end{enumerate}  The overview of the methodology is presented in FIGURE~\ref{fig:optimization_overview}.  \subsection{Ground Truth Inventory}  The ground truth data is built using obtained through  manual annotation of the source video data using the Urban Tracker annotation  application \cite{Jodoin_2014}.For each camera sequence 10 minutes of video are manually annotated.  There are 5 five video  sequences selected from 3 three  different roundabouts presented in Table~\ref{tab:gt_inv}. Table~\ref{tab:gt_inv} (a video sequence correspond to a camera views and the terms are used interchangeably). S1S and S1W were recorded with similar field of views on the first site to compare the weather condition. S1S and S2 show comparable views of two different roundabouts (sites 1 and 2). S3V1 was recorded using the same camera as on S1 and S2, and can be compared to S1S and S2 to evaluate the impact of the resolution. S3V1 and S3V2 allow to compare the impact of the type of camera on the same site, with two different views. For each camera view, an analysis zone covering a merging zone of the roundabout is defined inside the zone where automated tracking is performed (site analysis mask) as can be seen in FIGURE~\label{fig:analysis_zone_trajectories}. All vehicles going through the analysis zone of each camera view were manually tracked for 10~min (with bounding boxes drawn around each vehicle every 5-10 frames).  The annotations require between 30 minutes 30~min  and one hour per minute ofannotated  video, depending on the frame rate and the  traffic flow. \begin{table}  \caption{Ground Truth Inventory} Inventory: S1, S2 and S3 refer to the sites 1 to 3, S1S and S1W refer respectively to the videos recorded on the first site in Summer and Winter, and S3V1 and S3V2 refer respectively to the videos recorded simultaneously on the third site with two different cameras covering complementary zones of the roundabout}  \label{tab:gt_inv}  \begin{tabular}{lp{3.2cm}p{2.5cm}p{3cm}ll}  \hline  \textbf{Site} & \textbf{Date \textbf{Time  \& Time} Date}  & \textbf{Number of Annotated Road Users} & \textbf{Camera Type} & \textbf{Conditions} & \textbf{Sample View} \\ \hline  S1S & 12:00pm, July 2012 (Thursday) & 266 & IP Camera 800x600 & Sunny, shadows & \includegraphics[width=4cm]{figures/image2.png}\\  S1W & 8:00am, February 2013 (Friday) & 209 & IP Camera 800x600& Low visibility, winter & \\ 
...