Abstract | ||
---|---|---|
We introduce the use of optimization-based multigrid techniques for dense optical flow computation. In particular, we evaluate the performance of a multigrid optimization (MG/OPT) algorithm based on a line search strategy for large-scale optimization like truncated Newton. Our experimental tests have shown that the algorithm outperforms the truncated Newton method even implemented with a coarse to fine strategy. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1117/12.896126 | Proceedings of SPIE |
Keywords | Field | DocType |
Optical flow,multigrid optimization,multiresolution (coarse to fine),truncated Newton | Constraint algorithm,Algorithm,Line search,Regularization (mathematics),Motion estimation,Optical flow,Optimization problem,Multigrid method,Mathematics,Computation | Conference |
Volume | ISSN | Citations |
8009 | 0277-786X | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
El Mostafa Kalmoun | 1 | 20 | 2.87 |
Luis Garrido | 2 | 535 | 28.51 |
Caselles, V. | 3 | 3893 | 421.11 |