Multiresolution Gaussian mixture models for visual motion estimation

This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion