In recent years, much effort has been put into the development of novel algorithms to solve the person re-identification problem. The goal is to match a given person's image against a gallery of people. In this paper, we propose a single-shot supervised method to compute a scoring function that, when applied to a pair of images, provides a score expressing the likelihood that they depict the same individual. The method is characterized by: (i) the usage of a set of local image descriptors based on Fisher vectors, (ii) the training of a pool of scoring functions based on the local descriptors, and (iii) the construction of a strong scoring function by means of an adaptive boosting procedure. The method has been tested on four data-sets and results have been compared with state-of-the-art methods clearly showing superior performance.

Boosting Fisher vector based scoring functions for person re-identification

Messelodi, Stefano;Modena, Carla Maria
2015-01-01

Abstract

In recent years, much effort has been put into the development of novel algorithms to solve the person re-identification problem. The goal is to match a given person's image against a gallery of people. In this paper, we propose a single-shot supervised method to compute a scoring function that, when applied to a pair of images, provides a score expressing the likelihood that they depict the same individual. The method is characterized by: (i) the usage of a set of local image descriptors based on Fisher vectors, (ii) the training of a pool of scoring functions based on the local descriptors, and (iii) the construction of a strong scoring function by means of an adaptive boosting procedure. The method has been tested on four data-sets and results have been compared with state-of-the-art methods clearly showing superior performance.
File in questo prodotto:
File Dimensione Formato  
MesMod_IVC_2015accepted.pdf

solo utenti autorizzati

Descrizione: Articolo principale
Tipologia: Documento in Pre-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 813.86 kB
Formato Adobe PDF
813.86 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/300996
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact