Re-identification by Covariance Descriptors

Slawomir Bak 1 François Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This chapter addresses the problem of appearance matching, while employing the covariance descriptor. We tackle the extremely challenging case in which the same non-rigid object has to be matched across disjoint camera views. Covariance statistics averaged over a Riemannian manifold are fundamental for designing appearance models invariant to camera changes. We discuss different ways of extracting an object appearance by incorporating various training strategies. Appearance matching is enhanced either by discriminative analysis using images from a single camera or by selecting distinctive features in a covariance metric space employing data from two cameras. By selecting only essential features for a specific class of objects (\textit{e.g.} humans) without defining \textit{a priori} feature vector for extracting covariance, we remove redundancy from the covariance descriptor and ensure low computational cost. Using a feature selection technique instead of learning on a manifold, we avoid the over-fitting problem. The proposed models have been successfully applied to the person re-identification task in which a human appearance has to be matched across non-overlapping cameras. We carry out detailed experiments of the suggested strategies, demonstrating their pros and cons \textit{w.r.t.} recognition rate and suitability to video analytics systems.
Type de document :
Chapitre d'ouvrage
Gong, Shaogang and Cristani, Marco and Shuicheng, Yan and Loy, Chen Change. Person Re-Identification, Springer, 2013, Advances in Computer Vision and Pattern Recognition
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00907335
Contributeur : Slawomir Bak <>
Soumis le : jeudi 21 novembre 2013 - 10:25:45
Dernière modification le : jeudi 11 janvier 2018 - 16:21:02
Document(s) archivé(s) le : samedi 22 février 2014 - 04:32:53

Fichier

chap3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00907335, version 1

Collections

Citation

Slawomir Bak, François Bremond. Re-identification by Covariance Descriptors. Gong, Shaogang and Cristani, Marco and Shuicheng, Yan and Loy, Chen Change. Person Re-Identification, Springer, 2013, Advances in Computer Vision and Pattern Recognition. 〈hal-00907335〉

Partager

Métriques

Consultations de la notice

319

Téléchargements de fichiers

596