The Geometry and Matching of Lines and Curves Over Multiple Views

Cordelia Schmid 1 Andrew Zisserman 2
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper describes the geometry of imaged curves in two and three views. Multi-view relationships are developed for lines, conics and non-algebraic curves. The new relationships focus on determining the plane of the curve in a projective reconstruction, and in particular using the homography induced by this plane for transfer from one image to another. It is shown that given the fundamental matrix between two views, and images of the curve in each view, then the plane of a conic may be determined up to a two fold ambiguity, but local curvature of a curve uniquely determines the plane. It is then shown that given the trifocal tensor between three views, this plane defines a homography map which may be used to transfer a conic or the curvature from two views to a third. Simple expressions are developed for the plane and homography in each case. A set of algorithms are then described for automatically matching individual line segments and curves between images. The algorithms use both photometric information and the multiple view geometric relationships. For image pairs the homography facilitates the computation of a neighbourhood cross-correlation based matching score for putative line/curve correspondences. For image triplets cross-correlation matching scores are used in conjunction with line/curve transfer based on the trifocal geometry to disambiguate matches. Algorithms are developed for both short and wide baselines. The algorithms are robust to deficiencies in the 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 methods are applicable to line/curve matching in stereo and trinocular rigs, and as a starting point for line/curve matching through monocular image sequences.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2000, 40 (3), pp.199--233. 〈〉. 〈10.1023/A:1008135310502〉
Liste complète des métadonnées

Littérature citée [65 références]  Voir  Masquer  Télécharger
Contributeur : Thoth Team <>
Soumis le : mercredi 22 décembre 2010 - 09:18:06
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : mercredi 23 mars 2011 - 02:31:00


Fichiers produits par l'(les) auteur(s)





Cordelia Schmid, Andrew Zisserman. The Geometry and Matching of Lines and Curves Over Multiple Views. International Journal of Computer Vision, Springer Verlag, 2000, 40 (3), pp.199--233. 〈〉. 〈10.1023/A:1008135310502〉. 〈inria-00548301〉



Consultations de la notice


Téléchargements de fichiers