A feature-based approach for determining dense long range correspondences
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
A feature-based approach for determining dense long range correspondences. / Wills, J; Belongie, S.
In: Lecture Notes in Computer Science, 2004, p. 170-182.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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