Automatic Line Matching across Views - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 1997

Automatic Line Matching across Views

Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154
Andrew Zisserman
  • Fonction : Auteur
  • PersonId : 878447

Résumé

The paper presents a new method for matching individual line segments between images. The method uses both grey-level information and the multiple view geometric relations between the images. For image pairs epipolar geometry facilitates the computation of a cross-correlation based matching score for putative line correspondences. For image triplets cross-correlation matching scores are used in conjunction with line transfer based on the trifocal geometry. Algorithms are developed for both short and long range motion. In the case of long range motion the algorithm involves evaluating a one parameter family of plane induced homographies. The algorithms are robust to deficiencies in the line segment extraction and partial occlusion. Experimental results are given for image pairs and triplets, for varying motions between views, and for different scene types. The three view algorithm eliminates all mismatches.
Fichier principal
Vignette du fichier
cvpr.pdf (296.5 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00548346 , version 1 (22-12-2010)

Identifiants

Citer

Cordelia Schmid, Andrew Zisserman. Automatic Line Matching across Views. International Conference on Computer Vision & Pattern Recognition, Jun 1997, San Juan, Puerto Rico. pp.666--671, ⟨10.1109/CVPR.1997.609397⟩. ⟨inria-00548346⟩
138 Consultations
711 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More