DMCA
Agapito. Robust trajectory-space tv-l1 optical flow for non-rigid sequences (2011)
| Venue: | In EMMCVPR |
| Citations: | 12 - 3 self |
BibTeX
@INPROCEEDINGS{Garg11agapito.robust,
author = {Ravi Garg and Anastasios Roussos and Lourdes Agapito},
title = {Agapito. Robust trajectory-space tv-l1 optical flow for non-rigid sequences},
booktitle = {In EMMCVPR},
year = {2011}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. This paper deals with the problem of computing optical flow between each of the images in a sequence and a reference frame when the camera is viewing a non-rigid object. We exploit the high correlation between 2D trajectories of different points on the same non-rigid surface by assuming that the displacement sequence of any point can be expressed in a compact way as a linear combination of a low-rank motion basis. This subspace constraint effectively acts as a long term regularization leading to temporally consistent optical flow. We formulate it as a robust soft constraint within a variational framework by penalizing flow fields that lie outside the low-rank manifold. The resulting energy functional includes a quadratic relaxation term that allows to decouple the optimization of the brightness constancy and spatial regularization terms, leading to an efficient optimization scheme. We provide a new benchmark dataset, based on motion capture data of a flag waving in the wind, with dense ground truth optical flow for evaluation of multi-view optical flow of non-rigid surfaces. Our experiments, show that our proposed approach provides comparable or superior results to state of the art optical flow and dense non-rigid registration algorithms. 1
Keyphrases
robust trajectory-space tv-l1 optical flow non-rigid sequence non-rigid surface consistent optical flow long term regularization different point robust soft constraint multi-view optical flow superior result low-rank manifold reference frame brightness constancy non-rigid object displacement sequence dense ground truth optical flow low-rank motion basis flow field spatial regularization term high correlation subspace constraint new benchmark dataset efficient optimization scheme linear combination motion capture data flag waving compact way variational framework dense non-rigid registration algorithm quadratic relaxation term optical flow art optical flow
