Abstract | ||
---|---|---|
A new method for optical flow computation by means of a coupled set of non-linear diffusion equations is presented. This approach integrates the classical differential approach with the correlation type of motion detectors. A measure of inconsistency within the optical flow field which indicates optical flow boundaries. This information is fed back to the optical flow equations in a non-linear way and allows the flow field to be reconstructed while preserving the discontinuities. The whole scheme is also applicable to stereo matching. The model is applied to a set of synthetic and real image sequences to illustrate the behaviour of the coupled diffusion equations. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1007/BFb0028362 | ECCV (2) |
Keywords | Field | DocType |
non-linear diffusion,optical flow,diffusion equation | Non linear diffusion,Stereo matching,Computer vision,Classification of discontinuities,Computer science,Flow (psychology),Artificial intelligence,Real image,Optical flow,Optical flow computation,Detector | Conference |
ISBN | Citations | PageRank |
0-387-57957-5 | 80 | 10.40 |
References | Authors | |
5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marc Proesmans | 1 | 109 | 12.51 |
Luc Van Gool | 2 | 27566 | 1819.51 |
E. Pauwels | 3 | 80 | 10.40 |
Oosterlinck, A. | 4 | 711 | 254.21 |