Uncertainty Models of the Gradient Constraint for Optical Flow Computation

Naoya OHTA

Uncertainty Models of the Gradient Constraint for Optical Flow Computation

Naoya OHTA

Full Text Views

0

Share
Cite this

Summary :

The uncertainty involved in the gradient constraint for optical flow detection is often modeled as constant Gaussian noise added to the time-derivative of the image intensity. In this paper, we examine this modeling closely and investigate the error behavior by experiments. Our result indicates that the error depends on both the spatial derivatives and the image motion. We propose alternative uncertainty models based on our experiments. It is shown that the optical flow computation algorithms based on them can detect more accurate optical flow than the conventional least-squares method.

Publication: IEICE TRANSACTIONS on Information Vol.E79-D No.7 pp.958-964

Publication Date: 1996/07/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing,Computer Graphics and Pattern Recognition

Cite this

Copy

Naoya OHTA, "Uncertainty Models of the Gradient Constraint for Optical Flow Computation" in IEICE TRANSACTIONS on Information, vol. E79-D, no. 7, pp. 958-964, July 1996, doi: .
Abstract: The uncertainty involved in the gradient constraint for optical flow detection is often modeled as constant Gaussian noise added to the time-derivative of the image intensity. In this paper, we examine this modeling closely and investigate the error behavior by experiments. Our result indicates that the error depends on both the spatial derivatives and the image motion. We propose alternative uncertainty models based on our experiments. It is shown that the optical flow computation algorithms based on them can detect more accurate optical flow than the conventional least-squares method.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e79-d_7_958/_p

Copy

@ARTICLE{e79-d_7_958,
author={Naoya OHTA, },
journal={IEICE TRANSACTIONS on Information},
title={Uncertainty Models of the Gradient Constraint for Optical Flow Computation},
year={1996},
volume={E79-D},
number={7},
pages={958-964},
abstract={The uncertainty involved in the gradient constraint for optical flow detection is often modeled as constant Gaussian noise added to the time-derivative of the image intensity. In this paper, we examine this modeling closely and investigate the error behavior by experiments. Our result indicates that the error depends on both the spatial derivatives and the image motion. We propose alternative uncertainty models based on our experiments. It is shown that the optical flow computation algorithms based on them can detect more accurate optical flow than the conventional least-squares method.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Uncertainty Models of the Gradient Constraint for Optical Flow Computation
T2 - IEICE TRANSACTIONS on Information
SP - 958
EP - 964
AU - Naoya OHTA
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E79-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 1996
AB - The uncertainty involved in the gradient constraint for optical flow detection is often modeled as constant Gaussian noise added to the time-derivative of the image intensity. In this paper, we examine this modeling closely and investigate the error behavior by experiments. Our result indicates that the error depends on both the spatial derivatives and the image motion. We propose alternative uncertainty models based on our experiments. It is shown that the optical flow computation algorithms based on them can detect more accurate optical flow than the conventional least-squares method.
ER -