By the same authors

Optical Flow Estimation Using Diffusion Distances

Research output: Contribution to conferencePaper

Standard

Optical Flow Estimation Using Diffusion Distances. / Wartak, Szymon; Bors, Adrian G.

2010. 189-192 Paper presented at 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey.

Research output: Contribution to conferencePaper

Harvard

Wartak, S & Bors, AG 2010, 'Optical Flow Estimation Using Diffusion Distances' Paper presented at 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey, 23/08/10 - 26/08/10, pp. 189-192. https://doi.org/10.1109/ICPR.2010.55

APA

Wartak, S., & Bors, A. G. (2010). Optical Flow Estimation Using Diffusion Distances. 189-192. Paper presented at 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey. https://doi.org/10.1109/ICPR.2010.55

Vancouver

Wartak S, Bors AG. Optical Flow Estimation Using Diffusion Distances. 2010. Paper presented at 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey. https://doi.org/10.1109/ICPR.2010.55

Author

Wartak, Szymon ; Bors, Adrian G. / Optical Flow Estimation Using Diffusion Distances. Paper presented at 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey.4 p.

Bibtex - Download

@conference{6152db4626e7453db6c5a43b52fe2323,
title = "Optical Flow Estimation Using Diffusion Distances",
abstract = "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.",
author = "Szymon Wartak and Bors, {Adrian G.}",
year = "2010",
month = "8",
doi = "10.1109/ICPR.2010.55",
language = "English",
pages = "189--192",
note = "20th International Conference on Pattern Recognition (ICPR 2010) ; Conference date: 23-08-2010 Through 26-08-2010",

}

RIS (suitable for import to EndNote) - Download

TY - CONF

T1 - Optical Flow Estimation Using Diffusion Distances

AU - Wartak, Szymon

AU - Bors, Adrian G.

PY - 2010/8

Y1 - 2010/8

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=78149485483&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.55

DO - 10.1109/ICPR.2010.55

M3 - Paper

SP - 189

EP - 192

ER -