A multigrid approach for hierarchical motion estimation

摘要: This paper focuses on the estimation of apparent motion field between two consecutive frames in an image sequence. The approach developed here is a tradeoff methods based global parameterized flow models and local dense optic estimators. method relies adaptive multigrid minimization approach. In addition to accelerated convergence toward good estimates, it allows mix different parameterizations estimate relative partitions image. performances resulting algorithms are demonstrated difficult context non-convex energy. Experimental results real world Meteosat sequences presented.