| Title | Minimal Solutions for Panoramic Stitching with Radial Distortion |
| Authors | Martin Byröd, Matthew Brown, Karl Åström |
| Full-text | Available as PDF |
| Alternative Location | http://www.bmva.org/bmvc/20... |
| Publication | British Machine Vision Conference |
| Year | 2009 |
| Pages | 11 |
| Document type | Conference paper |
| Conference name | The 20th British Machine Vision Conference |
| Conference Date | 2009-09-07--2009-09-10 |
| Conference Location | London, UK |
| Status | Published |
| Quality controlled | Yes |
| Language | eng |
| Publisher | British Machine Vision Association (BMVA) |
| Abstract English | This paper presents a solution to panoramic image stitching of two images with co-<br> inciding optical centers, but unknown focal length and radial distortion. The algorithm<br> operates with a minimal set of corresponding points (three) which means that it is well<br> suited for use in any RANSAC style algorithm for simultaneous estimation of geometry<br> and outlier rejection. Compared to a previous method for this problem, we are able to<br> guarantee that the right solution is found in all cases. The solution is obtained by solving<br> a small system of polynomial equations. The proposed algorithm has been integrated in<br> a complete multi image stitching system and we evaluate its performance on real images<br> with lens distortion. We demonstrate both quantitative and qualitative improvements<br> compared to state of the art methods. |
| Keywords | minimal problems, pose, Computer vision, geometry, radial distortion , |
Questions: webmaster
Last update: 2013-04-11
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)