Efficient and Robust Alignment of Unsynchronized Video Sequences

Georgios Evangelidis 1 Christian Bauckhage 2
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper addresses the problem of aligning two unsynchronized video sequences. We present a novel approach that allows for temporal and spa- tial alignment of similar videos captured from independently moving cameras. The goal is to synchronize two videos of a scene such that changes between the videos can be detected automatically. This aims at applications in driver assis- tance or surveillance systems but we also envision applications in map building. Our approach is novel in that it adapts an efficient information retrieval frame- work to a computer vision problem. In addition, we extend the recent ECC image- alignment algorithm to the temporal dimension in order to improve spatial regis- tration and enable synchro refinement. Experiments with traffic videos recorded by in-vehicle cameras demonstrate the efficiency of the proposed method and verify its effectiveness with respect to spatio-temporal alignment accuracy.
Type de document :
Communication dans un congrès
Rudolf Mester and Michael Felsberg. DAGM 2011 - 33rd Annual Symposium of the German Association for Pattern Recognition, Aug 2011, Frankfurt, Germany. Springer, 6835, pp.286-295, 2011, Pattern Recognition. 〈10.1007/978-3-642-23123-0_29〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00864392
Contributeur : Team Perception <>
Soumis le : samedi 21 septembre 2013 - 11:57:18
Dernière modification le : mercredi 11 avril 2018 - 01:59:01
Document(s) archivé(s) le : dimanche 22 décembre 2013 - 02:45:17

Fichiers

DAGM2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Georgios Evangelidis, Christian Bauckhage. Efficient and Robust Alignment of Unsynchronized Video Sequences. Rudolf Mester and Michael Felsberg. DAGM 2011 - 33rd Annual Symposium of the German Association for Pattern Recognition, Aug 2011, Frankfurt, Germany. Springer, 6835, pp.286-295, 2011, Pattern Recognition. 〈10.1007/978-3-642-23123-0_29〉. 〈hal-00864392〉

Partager

Métriques

Consultations de la notice

701

Téléchargements de fichiers

200