Name
Abstract | ||
|---|---|---|
Some recent stereo matching algorithms are based on graph cuts. They transform the matching problem to a minimisation of a global energy function. The minimisation can be done by finding out an optimal cut in a special graph. Different meth- ods were proposed to construct the graph. But all of them, consider for each pixel, all possible disparities between min- imum and maximum values. In this article, a new method is proposed: only some potential values in the disparity range are selected for each pixel. These values can be found using a local analysis of stereo matching. This method allows us to make wider the disparity range, and at the same time to limit the volume of the graph, and therefore to reduce the compu- tation time. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ICIP.2007.4378935 | Image Processing, 2007. ICIP 2007. IEEE International Conference |
Keywords | Field | DocType |
graph theory,image matching,minimisation,stereo image processing,disparity range,global energy function minimisation,reduced-graph cut,stereo matching,Stereo vision,graph cut,matching | Graph theory,Cut,Template matching,Computer vision,Graph cuts in computer vision,Pattern recognition,Computer science,Stereopsis,Minimisation (psychology),Artificial intelligence,3-dimensional matching,Computer stereo vision | Conference |
Volume | ISSN | ISBN |
1 | 1522-4880 E-ISBN : 978-1-4244-1437-6 | 978-1-4244-1437-6 |
Citations | PageRank | References |
2 | 0.38 | 8 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ayman Zureiki | 1 | 2 | 0.72 |
| Michel Devy | 2 | 542 | 71.47 |
| Raja Chatila | 3 | 1018 | 422.56 |