A higher order MRF-model for stereo-reconstruction
In: Pattern recognition (Tübingen, 30 August - 1 September 2004)Lecture notes in computer science :440-446
Konferenz
- print, 8 ref
Zugriff:
We consider the task of stereo-reconstruction under the following fairly broad assumptions. A single and continuously shaped object is captured by two uncalibrated cameras. It is assumed, that almost all surface points are binocular visible. We propose a statistical model which represents the surface as a triangular (hexagonal) mesh of pairs of corresponding points. We introduce an iterative scheme, which simultaneously finds an optimal mesh (with respect to a certain Bayes task) and a corresponding optimal fundamental matrix (in a maximum likelihood sense). Thus the surface is reconstructed up to a projective transform.
Titel: |
A higher order MRF-model for stereo-reconstruction
|
---|---|
Autor/in / Beteiligte Person: | SCHLESINGER, Dmitrij ; FLACH, Boris ; SHEKHOVTSOV, Alexander |
Link: | |
Quelle: | Pattern recognition (Tübingen, 30 August - 1 September 2004)Lecture notes in computer science :440-446 |
Veröffentlichung: | Berlin: Springer, 2004 |
Medientyp: | Konferenz |
Umfang: | print, 8 ref |
ISSN: | 0302-9743 (print) |
Schlagwort: |
|
Sonstiges: |
|