deletions | additions       diff --git a/section_Trajectories_analysis_for_soccer__.tex b/section_Trajectories_analysis_for_soccer__.tex  index 83671ec..5d0325e 100644  --- a/section_Trajectories_analysis_for_soccer__.tex  +++ b/section_Trajectories_analysis_for_soccer__.tex 
...
\section{Trajectories analysis for soccer} \section{Introduction}  \begin{enumerate}  \item exposition of the problem of trajectory analysis for soccer  \item motivation for the development of a MI based metric 
...
\subsection{Trajectories}  The current works on soccer match analysis managed to give semantic data and most of the time they used extra data brought in several matches or championship. In this project we managed to find patterns in the paths of the players clustering players trajectories given only the video of a match filmed with a multi-camera system. The problem of tracking  players with multiple camera have been achieved in \cite{Ben_Shitrit_2011} consistently  even if their paths may intersect over long period of time have been achieved in \cite{Ben_Shitrit_2011}. time.  Our contribution is to provided an a  well fitted similarity measure between trajectories which allows the clustering of the players' trajectories according to the interdependency of their path using clustering via Linear clustering.  Yet only discrete trajectories are available in the form of array which can be of different sizes with different time discretization or with different speed.