Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/108757
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Robust trajectory-space TV-L1 optical flow for non-rigid sequences |
Author: | Garg, R. Roussos, A. Agapito, L. |
Citation: | Lecture Notes in Artificial Intelligence, 2011 / Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F. (ed./s), vol.6819 LNCS, pp.300-314 |
Publisher: | Springer |
Issue Date: | 2011 |
Series/Report no.: | Lecture Notes in Computer Science; 6819 |
ISBN: | 9783642230936 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2011) (25 Jul 2011 - 27 Jul 2011 : St. Petersburg, Russia) |
Editor: | Boykov, Y. Kahl, F. Lempitsky, V. Schmidt, F. |
Statement of Responsibility: | Ravi Garg, Anastasios Roussos, and Lourdes Agapito |
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. |
Rights: | © Springer-Verlag Berlin Heidelberg 2011 |
DOI: | 10.1007/978-3-642-23094-3_22 |
Published version: | http://dx.doi.org/10.1007/978-3-642-23094-3_22 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.