Abstract | ||
---|---|---|
We introduce a new method to determine the flow field of an image sequence using multi-scale anchor points. These anchor points manifest themselves in the scale-space representation of an image. The novelty of our method lies largely in the fact that the relation between the scale-space anchor points and the flow field is formulated in terms of soft constraints in a variational method. This leads to an algorithm for the computation of the flow field that differs fundamentally from previously proposed ones based on hard constraints. We show a significant performance increase when our method is applied to the Yosemite image sequence, a standard and well-established benchmark sequence in optic flow research. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-03767-2_134 | CAIP |
Keywords | Field | DocType |
optical flow,variational method,scale space | Computer vision,Computer science,Variational method,Flow (psychology),Artificial intelligence,Novelty,Critical path method,Image sequence,Computation | Conference |
Volume | ISSN | Citations |
5702 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pieter van Dorst | 1 | 6 | 1.12 |
Bart Janssen | 2 | 24 | 2.56 |
L. M. J. Florack | 3 | 1212 | 210.47 |
Bart M. Ter Haar Romeny | 4 | 1444 | 227.69 |