Person Re-identification for Real-world Surveillance Systems

Abstract : Appearance based person re-identification in a real-world video surveillance system with non-overlapping camera views is a challenging problem for many reasons. Current state-of-the-art methods often address the problem by relying on supervised learning of similarity metrics or ranking functions to implicitly model appearance transformation between cameras for each camera pair, or group, in the system. This requires considerable human effort to annotate data (see Section 1.1). Furthermore, the learned models are camera specific and not transferable from one set of cameras to another. Therefore, the annotation process is required after every network expansion or camera replacement, which strongly limits their applicability. Alternatively, we propose a novel mod-eling approach to harness complementary appearance information without supervised learning that significantly outperforms current state-of-the-art unsupervised methods on multiple benchmark datasets.
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger
Contributeur : Furqan Khan <>
Soumis le : lundi 21 novembre 2016 - 12:36:18
Dernière modification le : mardi 24 juillet 2018 - 15:48:19

Lien texte intégral


  • HAL Id : hal-01399939, version 1
  • ARXIV : 1607.05975



Furqan Khan, François Brémond. Person Re-identification for Real-world Surveillance Systems. 2016. 〈hal-01399939〉



Consultations de la notice