Stereo Ambiguity Index for Semi-Global Matching - Ifsttar Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Stereo Ambiguity Index for Semi-Global Matching

Résumé

Stereoscopic reconstruction is important to automatic vision systems. As an intermediate step, estimating this reconstruction is not enough for good performance of the whole system, and its uncertainty must be characterized. Several methods propose uncertainty indexes based on specific data features, thus incomplete, while others are based on learning. We propose a simple index, named ambiguity index, taking into account both data and regularization, and derived directly from the optimization process. Exploiting properties of dynamic programming, this index is related to the posterior variance of the solution when the Semi-Global Matching (SGM) algorithm is used for stereo reconstruction. To illustrate its interest, improvements in refining stereo reconstruction are shown on the KITTI datasets when the index is used.
Fichier principal
Vignette du fichier
doc00027715.pdf (2.22 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01592680 , version 1 (25-09-2017)

Identifiants

  • HAL Id : hal-01592680 , version 1

Citer

Mathias Paget, Jean Philippe Tarel, Pascal Monasse. Stereo Ambiguity Index for Semi-Global Matching. ICIP'17, IEEE International Conference on Image Processing, Sep 2017, PEKIN, China. 5p. ⟨hal-01592680⟩
481 Consultations
159 Téléchargements

Partager

Gmail Facebook X LinkedIn More