Abstract | ||
---|---|---|
Autocalibration algorithms based on the fundamental matrix must solve the problem of finding the global minimum of a cost function which has many local minima. We describe a new method of achieving this goal, which uses a stochastic optimization approach taken from the field of evolutionary algorithms. In theory, approaches that use the fundamental matrix for autocalibration are inferior to those based on a projective reconstruction. We argue that in practice if we use this new stochastic optimization approach this is not true. When autocalibrating focal length and aspect ratio both methods achieve comparable results. We demonstrate this experimentally using published image sequences for which the ground truth is known. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICPR.2002.1048302 | Pattern Recognition, 2002. Proceedings. 16th International Conference |
Keywords | Field | DocType |
calibration,evolutionary computation,image sequences,stochastic processes,aspect ratio,autocalibration algorithms,cost function,evolutionary algorithms,fundamental matrix,global minimum,image sequences,stochastic optimization | Stochastic optimization,Evolutionary algorithm,Computer science,Artificial intelligence,Fundamental matrix (computer vision),Computer vision,Mathematical optimization,Algorithm,Stochastic process,Evolutionary computation,Maxima and minima,Focal length,Ground truth | Conference |
Volume | ISSN | Citations |
2 | 1051-4651 | 9 |
PageRank | References | Authors |
0.59 | 5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gerhard Roth | 1 | 9 | 0.59 |
Anthony Whitehead | 2 | 143 | 20.84 |