Robust Location based Partial Correlation

Zhong-Dan Lan 1 Roger Mohr 1
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 : The visual correspondence problem is a major issue in computer vision. Correlation is a common tool for this problem. Most classical correlation methods fail near the disparity discontinuities, which occur at the boundaries of objects. In this paper, a partial correlation technique is proposed to solve this problem. Robust location methods are used to perform this partial correlation. Comparisons are made with other techniques and experimental results validate the approach.
Type de document :
Communication dans un congrès
Gerald Sommer and Kostas Daniilidis and Josef Pauli. 7th International Conference on Computer Analysis of Images and Patterns (CAIP '97), Sep 1997, Kiel, Germany. Springer-Verlag, 1296, pp.313--320, 1997, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/dt64wp422220830r/〉. 〈10.1007/3-540-63460-6_132〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548352
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:43:39
Dernière modification le : mercredi 11 avril 2018 - 01:54:54

Lien texte intégral

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Zhong-Dan Lan, Roger Mohr. Robust Location based Partial Correlation. Gerald Sommer and Kostas Daniilidis and Josef Pauli. 7th International Conference on Computer Analysis of Images and Patterns (CAIP '97), Sep 1997, Kiel, Germany. Springer-Verlag, 1296, pp.313--320, 1997, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/dt64wp422220830r/〉. 〈10.1007/3-540-63460-6_132〉. 〈inria-00548352〉

Partager

Métriques

Consultations de la notice

47