this is for holding javascript data
Nicolas Saunier edited section_Experimental_Results_subsection_The__.tex
almost 9 years ago
Commit id: 25a941786e8587a6ca4dc2d593820c92a02d0866
deletions | additions
diff --git a/section_Experimental_Results_subsection_The__.tex b/section_Experimental_Results_subsection_The__.tex
index a24a926..b2610fa 100644
--- a/section_Experimental_Results_subsection_The__.tex
+++ b/section_Experimental_Results_subsection_The__.tex
...
The tracking performance of the lower resolution IP~camera was largely dependent on \verb+feature-quality+. In fact, in the case of S1W recorded in Winter, a MOTA above 0.150 was not found unless \verb+feature-quality+ was below 0.10 and the best performance came from a \verb+feature-quality+ of approximately 0.01. This suggests that these video sequences recorded in the Winter should be calibrated separately from the other ones since its most important parameter is directly related to computation time (lower \verb+feature-quality+ will generate more features that take more time to be grouped). The range of \verb+feature-quality+ should also be adjusted for such a calibration. Another point of mention is that the GoPro camera had most of the lowest correlation coefficients with respect to each parameter. The implication is that the high resolution seems to be less sensitive to the choice of tracking parameters to achieve good performance. The third observation is that certain parameters such as \verb+min-tracking-error+ and \verb+min-feature-time+ could be eliminated from the optimization process due to the lack of correlation for all camera views.
\subsection{Over-fitting Analysis}
The second phase of the validation process was to evaluate the performance of optimized parameters compared to the default parameters. The genetic algorithm was run for the first
five minutes 5~min of each video file for between 10 and 30 generations over the course of one to three days depending on the site.
Table (insert table about optimized parameters) is TABLE~\ref{} presents a summary of the optimal parameters found for
these specific sequences. each camera view.
\begin{table}
\label{tab:optimized-parameters}
\caption{} \caption{Default tracking parameters and values optimized for each camera view}
\begin{tabular}{lllllll}
& & \multicolumn{5}{Optimized for}\\
&Default &S1S &S1W &S2 &S3V1 &S3V2\\
\hline
window size &7 &9 &9 &6 &10 &3\\
...