deletions | additions       diff --git a/section_Results_subsection_In_the__.tex b/section_Results_subsection_In_the__.tex  index 855f72f..8525d66 100644  --- a/section_Results_subsection_In_the__.tex  +++ b/section_Results_subsection_In_the__.tex 
...
\section{Results}  \subsection{?}  In the first phase of optimization, the genetic algorithm was run for the full 10 minutes for each video sequence with a corresponding ground truth. Each generation had 20 specimens, a score threshold of 0.2 for natural deaths, a maximum of 60 percent survivors, a crossover rate of 60 percent and a mutation rate of 5 percent. Each specimen contained a  file that  was saved and evaluated in terms of traffic count and average speed at the entrance and exit of each lane of the analysis zone., zone,  represented in figure (insert figure showing counts/speed). There is a strong linear correlation between MOTA and the number of objects tracked as expected, due to the way MOTA is calculated. The total vehicle counts are not necessarily comparable to the number of objects in the ground truth since the genetic algorithm is run on the analysis zones which do not include the whole video. \subsection{Parameter Correlation}  Each unique MOTA from the various optimizations had associated parameters from which Spearman's rank correlation coefficient could be extracted. The parameters were 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 since the higher resolution cameras took over 12 hours for the 20 samples of each generation of the genetic algorithm. 
...
  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 of approximately 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 such a 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. The third implication is that certain parameters such as min-feature-distanceklt and min-feature-time could be eliminated from the optimization process due to the lack of correlation on any camera.(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.)  \subsection{?}  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 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 a summary of the optimal parameters found for these specific sequences. Some parameters such as 'min-feature-distanceklt', 'mm-connection-distance' and 'mm-tracking-error' seem to have converged towards similar values on three of the cameras. However, it is apparent that in most cases the optimal solution is unique.  
...
Another source of error is within the correlation of the parameters with MOTA. Considering the method used to generate the trajectories for each sequence, the genetic algorithm may have remained on a similar set of parameters for many generations which may bias the correlation. The higher resolution cameras also had very few data points for lower MOTA values as seen in the first section of the results. While this has an impact of the numerical value of the correlation, it supports the conclusion that higher resolution cameras rely less on optimal parameters to provide reliable tracking results.