Name
Abstract | ||
|---|---|---|
One of the main technique used to recover motion analysis from two images or to register them is variational optical flow, where the pixels of one image are matched to the pixels of the second im- age by minimizing an energy functional. In the standard formulation of variational optical flow, the estimated motion vector field depends on the reference image and is asymmetric. However, in most application the solution should be independent of the reference image. Only few symmet- rical formulations of the optical flow has been proposed in the literature, where the solution is constraint to be symmetric using a combination of the flow in both directions. We propose a new symmetric variational formulation of the optical flow problem, where the flow is naturally sym- metric. Results on the Yosemite sequence show an improved accuracy of our symmetric flow with respect to standard optical flow algorithm. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-75867-9_85 | EUROCAST |
Keywords | Field | DocType |
variational optical flow,standard formulation,optical flow problem,reference image,estimated motion vector field,standard optical flow algorithm,optical flow,new symmetric variational formulation,motion analysis,symmetric optical flow,symmetric flow | Mathematical analysis,Reference image,Flow (psychology),Theoretical computer science,Flow (mathematics),Pixel,Motion vector field,Energy functional,Motion analysis,Geometry,Optical flow,Mathematics | Conference |
Volume | ISSN | ISBN |
4739 | 0302-9743 | 3-540-75866-6 |
Citations | PageRank | References |
6 | 0.60 | 5 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Luis Álvarez | 1 | 129 | 13.58 |
| Carlos A. Castaño-moraga | 2 | 21 | 3.17 |
| Miguel García | 3 | 6 | 0.94 |
| Karl Krissian | 4 | 560 | 37.94 |
| Luis Mazorra | 5 | 18 | 2.31 |
| Agust ´ in Salgado | 6 | 68 | 7.80 |
| Javier Sánchez | 7 | 383 | 31.84 |