In this paper we introduce a method for person re-identification based on discriminative, sparse basis expansions of targets in terms of a labeled gallery of known individuals. We propose an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration. Our approach also leverages a novel visual descriptor which we show to be discriminative while remaining robust to pose and illumination variations. An extensive comparative evaluation is given demonstrating that our approach achieves state-of-the-art performance on single- and multi-shot person re-identification scenarios on the VIPeR, i-LIDS, ETHZ, and CAVIAR4REID datasets. The combination of our descriptor and iterative sparse basis expansion improves state-of-the-art rank-1 performance by six percentage points on VIPeR and by 20 on CAVIAR4REID compared to other methods with a single gallery image per person. With multiple gallery and probe images per person our approach improves by 17 percentage points the state-of-the-art on i-LIDS and by 72 on CAVIAR4REID at rank-1. The approach is also quite efficient, capable of single-shot person re-identification over galleries containing hundreds of individuals at about 30 re-identifications per second.

Person Re-identification by Iterative Re-weighted Sparse Ranking / G. Lisanti;I. Masi;A. Bagdanov;A. Del Bimbo. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - STAMPA. - 37:(2015), pp. 1629-1642. [10.1109/TPAMI.2014.2369055]

Person Re-identification by Iterative Re-weighted Sparse Ranking

LISANTI, GIUSEPPE;MASI, IACOPO;BAGDANOV, ANDREW DAVID;DEL BIMBO, ALBERTO
2015

Abstract

In this paper we introduce a method for person re-identification based on discriminative, sparse basis expansions of targets in terms of a labeled gallery of known individuals. We propose an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration. Our approach also leverages a novel visual descriptor which we show to be discriminative while remaining robust to pose and illumination variations. An extensive comparative evaluation is given demonstrating that our approach achieves state-of-the-art performance on single- and multi-shot person re-identification scenarios on the VIPeR, i-LIDS, ETHZ, and CAVIAR4REID datasets. The combination of our descriptor and iterative sparse basis expansion improves state-of-the-art rank-1 performance by six percentage points on VIPeR and by 20 on CAVIAR4REID compared to other methods with a single gallery image per person. With multiple gallery and probe images per person our approach improves by 17 percentage points the state-of-the-art on i-LIDS and by 72 on CAVIAR4REID at rank-1. The approach is also quite efficient, capable of single-shot person re-identification over galleries containing hundreds of individuals at about 30 re-identifications per second.
2015
37
1629
1642
G. Lisanti;I. Masi;A. Bagdanov;A. Del Bimbo
File in questo prodotto:
File Dimensione Formato  
LisantiTPAMI15.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 1.91 MB
Formato Adobe PDF
1.91 MB Adobe PDF   Richiedi una copia
Lisanti_ACCEPTED.pdf

accesso aperto

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Open Access
Dimensione 7.61 MB
Formato Adobe PDF
7.61 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/947563
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 282
  • ???jsp.display-item.citation.isi??? 212
social impact