In this letter, we propose an algorithm to estimate the optical flow fields based on a hierarchical structure composed of spatio-temporal image pyramids obtained from repetitive application of the Gaussian filtering and decimation in both the spatial and temporal domain. In our approach, an inter-level motion smoothness constraint between adjacent pyramid levels is introduced to estimate a unique optical flow field. We show that the pyramid structure allows us to employ the multigrid algorithm, which is known to accelerate the convergence rate. The multigrid algorithm provides a scheme for efficient combination of local and global information to estimate the optical flow field. The experimental results reveal that the combination of local and global information yields a fast convergence behavior and accurate motion estimation results.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shin Hwan HWANG, Sang Uk LEE, "An Optical Flow Estimation Algorithm Using the Spatio-Temporal Hierarchical Structure" in IEICE TRANSACTIONS on Information,
vol. E76-D, no. 4, pp. 507-515, April 1993, doi: .
Abstract: In this letter, we propose an algorithm to estimate the optical flow fields based on a hierarchical structure composed of spatio-temporal image pyramids obtained from repetitive application of the Gaussian filtering and decimation in both the spatial and temporal domain. In our approach, an inter-level motion smoothness constraint between adjacent pyramid levels is introduced to estimate a unique optical flow field. We show that the pyramid structure allows us to employ the multigrid algorithm, which is known to accelerate the convergence rate. The multigrid algorithm provides a scheme for efficient combination of local and global information to estimate the optical flow field. The experimental results reveal that the combination of local and global information yields a fast convergence behavior and accurate motion estimation results.
URL: https://global.ieice.org/en_transactions/information/10.1587/e76-d_4_507/_p
Copy
@ARTICLE{e76-d_4_507,
author={Shin Hwan HWANG, Sang Uk LEE, },
journal={IEICE TRANSACTIONS on Information},
title={An Optical Flow Estimation Algorithm Using the Spatio-Temporal Hierarchical Structure},
year={1993},
volume={E76-D},
number={4},
pages={507-515},
abstract={In this letter, we propose an algorithm to estimate the optical flow fields based on a hierarchical structure composed of spatio-temporal image pyramids obtained from repetitive application of the Gaussian filtering and decimation in both the spatial and temporal domain. In our approach, an inter-level motion smoothness constraint between adjacent pyramid levels is introduced to estimate a unique optical flow field. We show that the pyramid structure allows us to employ the multigrid algorithm, which is known to accelerate the convergence rate. The multigrid algorithm provides a scheme for efficient combination of local and global information to estimate the optical flow field. The experimental results reveal that the combination of local and global information yields a fast convergence behavior and accurate motion estimation results.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - An Optical Flow Estimation Algorithm Using the Spatio-Temporal Hierarchical Structure
T2 - IEICE TRANSACTIONS on Information
SP - 507
EP - 515
AU - Shin Hwan HWANG
AU - Sang Uk LEE
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E76-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1993
AB - In this letter, we propose an algorithm to estimate the optical flow fields based on a hierarchical structure composed of spatio-temporal image pyramids obtained from repetitive application of the Gaussian filtering and decimation in both the spatial and temporal domain. In our approach, an inter-level motion smoothness constraint between adjacent pyramid levels is introduced to estimate a unique optical flow field. We show that the pyramid structure allows us to employ the multigrid algorithm, which is known to accelerate the convergence rate. The multigrid algorithm provides a scheme for efficient combination of local and global information to estimate the optical flow field. The experimental results reveal that the combination of local and global information yields a fast convergence behavior and accurate motion estimation results.
ER -