Time-varying motion estimation using orthogonal polynomials and applications

This paper presents a hierarchical motion estimation method considering both a large spatial and temporal support. The problem of motion estimation is formulated as a time-varying parameter estimation problem. The main advantage of the proposed algorithm is its ability to constrain the computation of the flow field spatially and temporally at the same time, by defining each motion parameter as a linear combination of some orthogonal time functions. The number of time basis varies according to the complexity of the movement and is determined automatically by means of a multiresolution approach and of statistical tests. We also present two different applications which underline the validity of the chosen approach