Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions

Yohann Salaün 1 Renaud Marlet 1, 2, 3 Pascal Monasse 1, 2, 3
1 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : Usual Structure from Motion techniques based on feature points have a hard time on scenes with little texture or presenting a single plane, as in indoor environments. Line segments are more robust features in this case. We propose a novel geometrical criterion for two-view pose estimation using lines, that does not assume a Manhattan world. We also define a parameterless (a contrario) RANSAC-like method to discard calibration outliers and provide more robust pose estimations, possibly using points as well when available. Last, we provide quantitative experimental data that illustrate failure cases of other methods and that show how our approach outperforms them, both in robustness and accuracy.
Type de document :
Communication dans un congrès
14th European Conference on Computer Vision (ECCV 2016), Oct 2016, Amsterdam, Netherlands. Springer, Lecture Notes in Computer Science 9911, pp.801 - 818, 2016, Lecture Notes in Computer Science. 〈10.1007/978-3-319-46478-7_49〉
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal-enpc.archives-ouvertes.fr/hal-01397813
Contributeur : Pascal Monasse <>
Soumis le : mercredi 16 novembre 2016 - 12:35:29
Dernière modification le : jeudi 5 juillet 2018 - 14:29:17
Document(s) archivé(s) le : jeudi 16 mars 2017 - 18:44:25

Fichier

eccv2016submission.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Yohann Salaün, Renaud Marlet, Pascal Monasse. Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions. 14th European Conference on Computer Vision (ECCV 2016), Oct 2016, Amsterdam, Netherlands. Springer, Lecture Notes in Computer Science 9911, pp.801 - 818, 2016, Lecture Notes in Computer Science. 〈10.1007/978-3-319-46478-7_49〉. 〈hal-01397813〉

Partager

Métriques

Consultations de la notice

243

Téléchargements de fichiers

194