deletions | additions       diff --git a/section_Introduction_begin_enumerate_item__.tex b/section_Introduction_begin_enumerate_item__.tex  index c8127ae..f54ef41 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 analysis used extra high level data and annotation (such as whoscored, transfertmark) which require human annotation. annotation and so preprocessing.  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 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. 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.  Then we need the clustering of those trajectories require  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.