A feature-based approach for determining dense long range correspondences

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

A feature-based approach for determining dense long range correspondences. / Wills, J; Belongie, S.

I: Lecture Notes in Computer Science, 2004, s. 170-182.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Wills, J & Belongie, S 2004, 'A feature-based approach for determining dense long range correspondences', Lecture Notes in Computer Science, s. 170-182.

APA

Wills, J., & Belongie, S. (2004). A feature-based approach for determining dense long range correspondences. Lecture Notes in Computer Science, 170-182.

Vancouver

Wills J, Belongie S. A feature-based approach for determining dense long range correspondences. Lecture Notes in Computer Science. 2004;170-182.

Author

Wills, J ; Belongie, S. / A feature-based approach for determining dense long range correspondences. I: Lecture Notes in Computer Science. 2004 ; s. 170-182.

Bibtex

@inproceedings{0ec35f71c6dd4142ac7ae2bcc7e2d5c7,
title = "A feature-based approach for determining dense long range correspondences",
abstract = "Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resulting dense correspondences will become increasingly inaccurate for everything but purely planar objects. Flexible motion models, on the other hand, tend to overfit and thus make partitioning difficult. For this reason, to achieve dense optical flow for image sequences with large inter-frame disparity, we propose a two stage process in which a planar model is used to get an approximation for the segmentation and the gross motion, and then a spline is used to refine the fit. We present experimental results for dense optical flow estimation on image pairs with large inter-frame disparity that are beyond the scope of existing approaches.",
keywords = "MOTION SEGMENTATION",
author = "J Wills and S Belongie",
year = "2004",
language = "English",
pages = "170--182",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
note = "8th European Conference on Computer Vision ; Conference date: 11-05-2004 Through 14-05-2004",

}

RIS

TY - GEN

T1 - A feature-based approach for determining dense long range correspondences

AU - Wills, J

AU - Belongie, S

PY - 2004

Y1 - 2004

N2 - Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resulting dense correspondences will become increasingly inaccurate for everything but purely planar objects. Flexible motion models, on the other hand, tend to overfit and thus make partitioning difficult. For this reason, to achieve dense optical flow for image sequences with large inter-frame disparity, we propose a two stage process in which a planar model is used to get an approximation for the segmentation and the gross motion, and then a spline is used to refine the fit. We present experimental results for dense optical flow estimation on image pairs with large inter-frame disparity that are beyond the scope of existing approaches.

AB - Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resulting dense correspondences will become increasingly inaccurate for everything but purely planar objects. Flexible motion models, on the other hand, tend to overfit and thus make partitioning difficult. For this reason, to achieve dense optical flow for image sequences with large inter-frame disparity, we propose a two stage process in which a planar model is used to get an approximation for the segmentation and the gross motion, and then a spline is used to refine the fit. We present experimental results for dense optical flow estimation on image pairs with large inter-frame disparity that are beyond the scope of existing approaches.

KW - MOTION SEGMENTATION

M3 - Conference article

SP - 170

EP - 182

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

T2 - 8th European Conference on Computer Vision

Y2 - 11 May 2004 through 14 May 2004

ER -

ID: 302160449