Lucas Fidon edited untitled.tex  almost 8 years ago

Commit id: 6cd2b7596a69158ae2b4bda8851d601d1bea9b9a

deletions | additions      

       

\textbf{ Abstract}  The main goal of the project is to extract high level semantic data from soccer matches given only the video of a match and using Machine Learning and Computer vision Vision  techniques. \begin{itemize}  \item During the first year I have explored the available techniques allowing to extract the players' trajectories given the videos of a match with several static camera  \item During the second year I focused on the problem of clustering of the players trajectories which leads to the thorny issue of the choice of a reliable and efficient metric for our purpose.