deletions | additions       diff --git a/section_Results_Table_ref_tab__.tex b/section_Results_Table_ref_tab__.tex  index 54ae77b..70736ec 100644  --- a/section_Results_Table_ref_tab__.tex  +++ b/section_Results_Table_ref_tab__.tex 
...
\section{Results}  Table~\ref{tab:spearman} Since the genetic algorithm was run once for each sequence, the cameras each have a unique dataset from which Spearman's rank correlation coefficient can be extracted. The parameters are individually compared to the MOTA and presented in Table~\ref{tab:spearman}. The winter camera for Site 1 had many results in which no objects were tracked and thus had a MOTA of 0. These sets of parameters were removed from the analysis to obtain a more representative correlation. The number of samples also varied based off of computation time.  \begin{table}  \caption{Spearman's Rank Correlation Coefficient by Parameter and Site}  \label{tab:spearman}  \begin{tabular}{lllllllll} \begin{tabular}{llllllllll}  \hline  \textbf{Site} & Number of Samples &  \textbf{window-size} & \textbf{feature-quality} & \textbf{min-feature-distance-klt} & \textbf{mm-connection-distance} & \textbf{mm-segmentation-distance} & \textbf{mm-tracking-error} & \textbf{min-nfeatures-group} & \textbf{min-feature-time}\\ \hline  Site 1 Summer & 224 &  -0.034 & -0.779 & -0.162 & 0.119 & -0.183 & 0.023 & -0.077 & 0.270\\ Site 1 Winter & 0.266 248  & -0.835 0.210  & -0.054 -0.981  & -0.022 -0.071 & -0.073  & 0.369 0.371  & 0.315 -0.074  & -0.249 -0.470  & 0.070\\ -0.203\\  Site 2 & 347 &  0.317 & -0.598 & 0.189 & 0.415 & 0.106 & 0.222 & 0.043 & 0.150\\ Site 3 Camera 1 & 115 &  0.649 & -0.576 & -0.011 & 0.451 & -0.186 & 0.114 & -0.296 & 0.020\\ Site 3 Camera 2 & 215 &  -0.022 & 0.374 & 0.312 & -0.282 & -0.057 & 0.058 & -0.029 & 0.259\\ \end{tabular}  \end{table}    Performance of the low resolution IP-camera was largely dependent on the feature-quality. In fact, in the case of the winter camera, a MOTA above 0.150 was not found unless the feature-quality was below 0.10 and the best performance came from a feature-quality below 0.01. This suggests that the winter camera should be calibrated separately from any other camera since the most important parameter is directly related to computation time. The range of the feature-quality should also be adjusted for calibration. Another point of mention is that the GoPro camera had no strong correlation towards any of the parameters. The implication is that the high resolution allows for a wide range of parameters to have similar performances. (Future work: try gopro camera in different weather conditions to see if it is also applicable, try to calibrate to reduce computation time since the downside is that it takes very long to find trajectories.)