Learning to Match Appearances by Correlations in a Covariance Metric Space

Abstract : This paper addresses the problem of appearance matching across disjoint camera views. Significant appearance changes, caused by variations in view angle, illumination and object pose, make the problem challenging. We propose to formulate the appearance matching problem as the task of learning a model that selects the most descriptive features for a specific class of objects. Learning is performed in a covariance metric space using an entropy-driven criterion. Our main idea is that different regions of the object appearance ought to be matched using various strategies to obtain a distinctive representation. The proposed technique has been successfully applied to the person re-identification problem, in which a human appearance has to be matched across non-overlapping cameras. We demonstrate that our approach improves state of the art performance in the context of pedestrian recognition.
Type de document :
Communication dans un congrès
Fitzgibbon, A. and Lazebnik, S. and Perona, P. and Sato, Y. and Schmid, C. 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. Springer, 7574, pp.806-820, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33712-3_58〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00731792
Contributeur : Slawomir Bak <>
Soumis le : jeudi 13 septembre 2012 - 14:12:50
Dernière modification le : jeudi 11 janvier 2018 - 16:19:44
Document(s) archivé(s) le : vendredi 14 décembre 2012 - 03:57:27

Fichiers

eccv2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Slawomir Bak, Guillaume Charpiat, Etienne Corvee, Francois Bremond, Monique Thonnat. Learning to Match Appearances by Correlations in a Covariance Metric Space. Fitzgibbon, A. and Lazebnik, S. and Perona, P. and Sato, Y. and Schmid, C. 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. Springer, 7574, pp.806-820, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33712-3_58〉. 〈hal-00731792〉

Partager

Métriques

Consultations de la notice

533

Téléchargements de fichiers

1249