End-to-end depth from motion with stabilized monocular videos

Clément Pinard 1, 2 Laure Chevalley 2 Antoine Manzanera 1 David Filliat 1, 3
3 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : We propose a depth map inference system from monocular videos based on a novel dataset for navigation that mimics aerial footage from gimbal stabilized monocular camera in rigid scenes. Unlike most navigation datasets, the lack of rotation implies an easier structure from motion problem which can be leveraged for different kinds of tasks such as depth inference and obstacle avoidance. We also propose an architecture for end-to-end depth inference with a fully convolutional network. Results show that although tied to camera inner parameters, the problem is locally solvable and leads to good quality depth prediction.
Type de document :
Communication dans un congrès
International Conference on Unmanned Aerial Vehicles in Geomatics, Sep 2017, Bonn, Germany. IV-2/W3, pp.67-74, 2017, 〈10.5194/isprs-annals-IV-2-W3-67-2017〉
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01587652
Contributeur : Clément Pinard <>
Soumis le : jeudi 14 septembre 2017 - 15:08:22
Dernière modification le : mercredi 6 juin 2018 - 10:02:55

Fichier

isprs-annals-IV-2-W3-67-2017.p...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Clément Pinard, Laure Chevalley, Antoine Manzanera, David Filliat. End-to-end depth from motion with stabilized monocular videos. International Conference on Unmanned Aerial Vehicles in Geomatics, Sep 2017, Bonn, Germany. IV-2/W3, pp.67-74, 2017, 〈10.5194/isprs-annals-IV-2-W3-67-2017〉. 〈hal-01587652〉

Partager

Métriques

Consultations de la notice

483

Téléchargements de fichiers

653