Since the detection of optical flow (two-dimensional motion field on an image) from image sequences is essentially an ill-posed problem, most of the conventional methods use a smoothness constraint for optical flow heuristically and detect reasonable optical flow. However, little discussion exists regarding the degree of smoothness. Furthermore, to recover the relative three-dimensional motion and depth between a camera and a rigid object, in general at first, the optical flow is detected without a rigid motion constraint, and next, the motion and depth are estimated using the detected optical flow. Rigorously speaking, the optical flow should be detected with such a constraint, and consequently three-dimensional motion and depth should be determined. To solve these problems, in this paper, we apply a parametric model to an optical flow, and construct an estimation algorithm based on this model.
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
Norio TAGAWA, Atsuya INAGAKI, Akihiro MINAGAWA, "Parametric Estimation of Optical Flow from Two Perspective Views" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 4, pp. 485-494, April 2001, doi: .
Abstract: Since the detection of optical flow (two-dimensional motion field on an image) from image sequences is essentially an ill-posed problem, most of the conventional methods use a smoothness constraint for optical flow heuristically and detect reasonable optical flow. However, little discussion exists regarding the degree of smoothness. Furthermore, to recover the relative three-dimensional motion and depth between a camera and a rigid object, in general at first, the optical flow is detected without a rigid motion constraint, and next, the motion and depth are estimated using the detected optical flow. Rigorously speaking, the optical flow should be detected with such a constraint, and consequently three-dimensional motion and depth should be determined. To solve these problems, in this paper, we apply a parametric model to an optical flow, and construct an estimation algorithm based on this model.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_4_485/_p
Copy
@ARTICLE{e84-d_4_485,
author={Norio TAGAWA, Atsuya INAGAKI, Akihiro MINAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Parametric Estimation of Optical Flow from Two Perspective Views},
year={2001},
volume={E84-D},
number={4},
pages={485-494},
abstract={Since the detection of optical flow (two-dimensional motion field on an image) from image sequences is essentially an ill-posed problem, most of the conventional methods use a smoothness constraint for optical flow heuristically and detect reasonable optical flow. However, little discussion exists regarding the degree of smoothness. Furthermore, to recover the relative three-dimensional motion and depth between a camera and a rigid object, in general at first, the optical flow is detected without a rigid motion constraint, and next, the motion and depth are estimated using the detected optical flow. Rigorously speaking, the optical flow should be detected with such a constraint, and consequently three-dimensional motion and depth should be determined. To solve these problems, in this paper, we apply a parametric model to an optical flow, and construct an estimation algorithm based on this model.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Parametric Estimation of Optical Flow from Two Perspective Views
T2 - IEICE TRANSACTIONS on Information
SP - 485
EP - 494
AU - Norio TAGAWA
AU - Atsuya INAGAKI
AU - Akihiro MINAGAWA
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2001
AB - Since the detection of optical flow (two-dimensional motion field on an image) from image sequences is essentially an ill-posed problem, most of the conventional methods use a smoothness constraint for optical flow heuristically and detect reasonable optical flow. However, little discussion exists regarding the degree of smoothness. Furthermore, to recover the relative three-dimensional motion and depth between a camera and a rigid object, in general at first, the optical flow is detected without a rigid motion constraint, and next, the motion and depth are estimated using the detected optical flow. Rigorously speaking, the optical flow should be detected with such a constraint, and consequently three-dimensional motion and depth should be determined. To solve these problems, in this paper, we apply a parametric model to an optical flow, and construct an estimation algorithm based on this model.
ER -