Descripción
|
|
---|---|
This paper presents a strategy for solving the feature matching problem in calibrated very wide-baseline camera settings. In this kind of settings, perspective distortion, depth discontinuities and occlusion represent enormous challenges. The proposed strategy addresses them by using geometrical information, specifically by exploiting epipolar-constraints. As a result it provides a sparse number of reliable feature points for which 3D position is accurately recovered. Special features known as junctions are used for robust matching. In particular, a strategy for refinement of junction end-point matching is proposed which enhances usual junction-based approaches. This allows to compute cross-correlation between perfectly aligned plane patches in both images, thus yielding better matching results. Evaluation of experimental results proves the effectiveness of the proposed algorithm in very wide-baseline environments. | |
Internacional
|
Si |
Nombre congreso
|
Int. Conf. on Emerging Security Technologies |
Tipo de participación
|
960 |
Lugar del congreso
|
Lisbon, Portugal |
Revisores
|
Si |
ISBN o ISSN
|
978-1-4673-2448-9 |
DOI
|
10.1109/EST.2012.34 |
Fecha inicio congreso
|
05/09/2012 |
Fecha fin congreso
|
07/09/2012 |
Desde la página
|
74 |
Hasta la página
|
77 |
Título de las actas
|
Proc. of Int. Conf. on Emerging Security Technologies, EST 2012 |