deletions | additions       diff --git a/section_Methodology_The_approach_proposed__.tex b/section_Methodology_The_approach_proposed__.tex  index 4f9653a..c4608e4 100644  --- a/section_Methodology_The_approach_proposed__.tex  +++ b/section_Methodology_The_approach_proposed__.tex 
...
\hline  \textbf{Site} & \textbf{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~pix, 15~fps & Sunny, shadows & \includegraphics[width=4cm]{figures/image2.png}\\ \raisebox{-.5\height}{\includegraphics[width=4cm]{figures/image2.png}}\\  S1W & 8:00am, February 2013 (Friday) & 209 & IP Camera 800x600~pix, 15~fps & Low visibility, winter & \\ \raisebox{-.5\height}{\includegraphics[width=4cm]{figures/image3.png}}\\  S2 & 7:00am, July 2012 (Wednesday) & 64 & IP Camera 800x600~pix, 15~fps & Sunny, some shadows & \\ \raisebox{-.5\height}{\includegraphics[width=4cm]{figures/image4.png}}\\  S3V1 & 4:00pm, August 2013 (Friday) & 80 & IP Camera 1280x1024~pix, 15~fps & Sunny & \\ \raisebox{-.5\height}{\includegraphics[width=4cm]{figures/image5.png}}\\  S3V2 & 4:00pm, August 2013 (Friday) & 312 & GoPro 1920 x 1080~pix, 15~fps, corrected for distortion & Sunny & \\ \raisebox{-.5\height}{\includegraphics[width=4cm]{figures/image6.png}}\\  \end{tabular}  \end{table} 
...
MOTA = 1 - \frac{\sum_{t} (m_t + fp_t + mme_t)}{\sum_t g_t}  \end{displaymath}  where $m_t$, $fp_t$ and $mme_t$ are respectively the number of misses, overdetections (false positives), and mismatches. mismatches for frame $t$.  These depends on matching the trajectories produced by the tracker to the ground truth. In this work, a road user is considered to be tracked in a frame if its centroid is within a given distance in world space from the ground truth bounding box center. Since there may be multiple matches, the hungarian algorithm is used to associate uniquely the ground truth and tracker output so that overdetections (more than one trajectory for the same road user) can be counted. The tracking results depend on these choices and a 5~m distance threshold is used as it is approximately the length of a passenger vehicle. The complementary performance measure of Multiple Object Tracking Precision (MOTP) is reported in the results. It is the average distance between the ground truth and road user trajectories \cite{Bernardin_2008}. This is particularly important for traffic variables such as time and distance headway, and safety analysis based on the proximity in time and space of interacting road users as measured for example by the time to collision indicator~\cite{St_Aubin_2015}. %MOTP is the average distance between expected and actual detections, determined by: 
...
where $d_i$ is the difference between the ranks $x_i$ and $y_i$ for each corresponding MOTA and tracking parameter values in a sample of size $n$.   %\subsection{Effect of MOTA on Traffic Data}  The road user trajectories obtained with the calibrated tracking parameters are analyzed to generate traffic variables. The objective is to identify the relationship of different tracking performance, measured by MOTA, with the traffic variables including traffic flow and spot speeds.  \subsection{Over-fitting}  One of the risks in optimization is that the parameters may be very specific to the five minute video sequence on which it was run. The performance on these five minutes may not be achieved when applied to other video sequences. To determine whether specific parameters are universally applicable, the performance of the results is examined on each camera with the following comparisons.  \begin{itemize} 
...