Domain Decomposition for Parallel Variational Optical Flow Computation

We present an approach to parallel variational optical flow computation by using an arbitrary partition of the image plane and iteratively solving related local variational problems associated with each subdomain. The approach is particularly suited for implementations on PCclusters because inter-process communication is minimized by restricting the exchange of data to a lower-dimensional interface. Our mathematical formulation supports various generalizations to linear/non-linear convex variational approaches, 3D image sequences, spatio-temporal regularization, and unstructured geometries and triangulations. Results concerning the effects of interface preconditioning, inexact subdomain solvers, and the number of subdomains are presented. Our approach provides a major step towards real-time 2D image processing using off-the-shelf PC-hardware and facilitates the efficient application of variational approaches to large-scale image processing problems.