deletions | additions       diff --git a/section_Methodology_The_approach_proposed__.tex b/section_Methodology_The_approach_proposed__.tex  index 09d1f65..e266688 100644  --- a/section_Methodology_The_approach_proposed__.tex  +++ b/section_Methodology_The_approach_proposed__.tex 
...
\subsection{Over-fitting}  One of the risks in optimization is that the parameters may be very specific to the 5-minute five minute  video sequence on which it was run. The performance on these 5 min 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}  \item The analysis area is split into a close section and a far section. The MOTA is analyzed for both zones independently.(Show an example figure of an analysis zone split into two.)  \item The ground truth is split into two 5-minute sequences. The MOTA result from the full 10-minute sequence is compared to the MOTA from each 5-minute sequence.  \item The same camera is used on two different sites at a similar height and angle.  \item The same camera view is used in both winter conditions and summer conditions. 
...
  \subsection{Transferability}  TODO fill this section. Just realized this was missing. I will fill it. Transferability is verified by applying each set of optimized parameters to each of the other annotated sequences. The full ten minute annotated videos are used to calculate the MOTA, which are then compared to the optimized results as both a percentage and a numerical value. This is done to avoid potential bias from the site selection and vehicle composition, which may lower the MOTA result compared to other cameras, despite having similar tracking performance results.