In this paper, we introduce a method to overcome one of the main challenges of person re-identification in multi-camera networks, namely cross-view appearance changes. The proposed solution addresses the extreme variability of person appearance in different camera views by exploiting multiple feature representations. For each feature, Kernel Canonical Correlation Analysis (KCCA) with different kernels is employed to learn several projection spaces in which the appearance correlation between samples of the same person observed from different cameras is maximized. An iterative logistic regression is finally used to select and weight the contributions of each projection and perform the matching between the two views. Experimental evaluation shows that the proposed solution obtains comparable performance on the VIPeR and PRID 450s datasets and improves on the PRID and CUHK01 datasets with respect to the state-of-the-art.

Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification / Lisanti, Giuseppe; Karaman, Svebor; Masi, Iacopo. - In: ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS. - ISSN 1551-6857. - ELETTRONICO. - 13:(2017), pp. 1-19. [http://doi.acm.org/10.1145/3038916]

Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification

LISANTI, GIUSEPPE;KARAMAN, SVEBOR;MASI, IACOPO
2017

Abstract

In this paper, we introduce a method to overcome one of the main challenges of person re-identification in multi-camera networks, namely cross-view appearance changes. The proposed solution addresses the extreme variability of person appearance in different camera views by exploiting multiple feature representations. For each feature, Kernel Canonical Correlation Analysis (KCCA) with different kernels is employed to learn several projection spaces in which the appearance correlation between samples of the same person observed from different cameras is maximized. An iterative logistic regression is finally used to select and weight the contributions of each projection and perform the matching between the two views. Experimental evaluation shows that the proposed solution obtains comparable performance on the VIPeR and PRID 450s datasets and improves on the PRID and CUHK01 datasets with respect to the state-of-the-art.
2017
13
1
19
Lisanti, Giuseppe; Karaman, Svebor; Masi, Iacopo
File in questo prodotto:
File Dimensione Formato  
TOMM-2016-0095.R1.final.pdf

solo utenti autorizzati

Tipologia: Altro
Licenza: Tutti i diritti riservati
Dimensione 2.03 MB
Formato Adobe PDF
2.03 MB Adobe PDF   Richiedi una copia

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/2158/1075962
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 47
  • ???jsp.display-item.citation.isi??? ND
social impact