From optical flow to dense long term correspondences - Université de Rennes Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

From optical flow to dense long term correspondences

Tomas Crivelli
  • Fonction : Auteur
  • PersonId : 936885
Philippe Robert
  • Fonction : Auteur
  • PersonId : 922657
Patrick Pérez
  • Fonction : Auteur
  • PersonId : 1022281

Résumé

Dense point matching and tracking in image sequences is an open issue with implications in several domains, from content analysis to video editing. We observe that for long term dense point matching, some regions of the image are better matched by concatenation of consecutive motion vectors, while for others a direct long term matching is preferred. We propose a method to optimally estimate the correspondence of a point w.r.t. a reference image from a set of input motion estimations over different temporal intervals. Results on texture insertion by point tracking in the context of video editing are presented and compared with a state-of-the-art approach.
Fichier principal
Vignette du fichier
ICIP2012V7.pdf (468.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00787772 , version 1 (13-02-2013)

Identifiants

  • HAL Id : hal-00787772 , version 1

Citer

Tomas Crivelli, Pierre-Henri Conze, Philippe Robert, Patrick Pérez. From optical flow to dense long term correspondences. IEEE International Conference on Image Processing, Sep 2012, Orlando, United States. pp.2680. ⟨hal-00787772⟩
124 Consultations
433 Téléchargements

Partager

Gmail Facebook X LinkedIn More