deletions | additions       diff --git a/section_Introduction_begin_enumerate_item__.tex b/section_Introduction_begin_enumerate_item__.tex  index 9b22181..c8127ae 100644  --- a/section_Introduction_begin_enumerate_item__.tex  +++ b/section_Introduction_begin_enumerate_item__.tex 
...
\item motivation for the development of a MI based metric  \end{enumerate}  The current works on soccer match analysismanaged to give semantic data and most of the time they  used extra high level  data brought in several matches or championship. and annotation (such as whoscored, transfertmark) which require human annotation.  In this project we limited our input to the video of a match filmed with a multi-camera system. We  focus on an unsupervised classification of the players based on their trajectories extracting automatically from the video of a match  during a short period of time using clustering method. This information is deeply woven into the fabric of team strategy analysis since it is related to the global placing of the players and the centers of the cluster may correspond to the leader of the game during the analysed time interval. Furthermore we limited our input to the video of a match filmed with a multi-camera system. at that period.  We managed to find patterns in the paths of the players clustering players trajectories. The problem of tracking players with multiple camera have been achieved consistently in \cite{Ben_Shitrit_2011} even if their paths may intersect over long period of time. Our Then we need a proper metric so as to cluster the players' trajectories. Thus our  contribution is to provided a well fitted similarity measure between trajectories which allows the clustering of the players' trajectories according to the interdependency of their path using 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.