Descripción
|
|
---|---|
We introduce a procedure for reducing the number of \ransac{} iterations necessary for fitting a homography to a set of noisy correspondences. This is achieved by means of a geometric constraint that detects invalid minimal sets. In the experiments conducted we show that this constraint lowers between 35% and 75% the number of required ransac iterations. | |
Internacional
|
Si |
DOI
|
10.1109/CVPRW.2008.4563138 |
Edición del Libro
|
0 |
Editorial del Libro
|
IEEE |
ISBN
|
978-1-4244-2340-8 |
Serie
|
|
Título del Libro
|
Computer Vision and Pattern Recognition Workshops, 2008. CVPR Workshops 2008. IEEE Computer Society Conference on |
Desde página
|
1 |
Hasta página
|
8 |