Optical Flow Estimation Using Diffusion Distances

Szymon Wartak, Adrian G. Bors

Research output: Contribution to conferencePaperpeer-review


In this paper we apply the diffusion framework to dense optical flow estimation. Local image information is represented by matrices of gradients between paired locations. Diffusion distances are modelled as sums of eigenvectors weighted by their eigenvalues extracted following the eigen decomposion of these matrices. Local optical flow is estimated by correlating diffusion distances characterizing features from different frames. A feature confidence factor is defined based on the local correlation efficiency when compared to that of its neighbourhood. High confidence optical flow estimates are propagated to areas of lower confidence.
Original languageEnglish
Number of pages4
Publication statusPublished - Aug 2010
Event20th International Conference on Pattern Recognition (ICPR 2010) - Istanbul, Turkey
Duration: 23 Aug 201026 Aug 2010


Conference20th International Conference on Pattern Recognition (ICPR 2010)

Cite this