In this work we address the problem of analyzing video sequences and representing meaningful space-time points of interest. We base our work on the 3D shearlet transform. In particular, we exploit the relation between coefficients with similar shearings to build a local representation which turns out to be really informative to understand the local spatio-temporal characteristics of the points that we are considering.
File in questo prodotto:
Non ci sono file associati a questo prodotto.