Share Email Print

Proceedings Paper

Target re-identification in low-quality camera networks
Author(s): Federica Battisti; Marco Carli; Giovanna Farinella; Alessandro Neri
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Person re-identification through a camera network deals with finding a correct link between consecutive observations of the same target among different cameras in order to choose the most probable correspondence among a set of possible matches. This task is particularly challenging in presence of low-resolution camera networks. In this work, a method for people re-identification in a framework of low-resolution camera network is presented. The proposed approach can be divided in two parts. First, the illumination changes of a target while crossing the network is analyzed. The color structure is evaluated using a novel color descriptor, the Color Structure Descriptor, which describes the differences of dominant colors between two regions of interest. Afterwards, a new pruning system for the links, the Target Color Structure is proposed. Results shows that the improvements achieved applying Target Color Structure control are up to 4% for the top rank and up to 16% considering the first eleven more similar candidates.

Paper Details

Date Published: 19 February 2013
PDF: 9 pages
Proc. SPIE 8655, Image Processing: Algorithms and Systems XI, 865502 (19 February 2013); doi: 10.1117/12.2004470
Show Author Affiliations
Federica Battisti, Univ. degli Studi di Roma Tre (Italy)
Marco Carli, Univ. degli Studi di Roma Tre (Italy)
Giovanna Farinella, Univ. degli Studi di Roma Tre (Italy)
Alessandro Neri, Univ. degli Studi di Roma Tre (Italy)

Published in SPIE Proceedings Vol. 8655:
Image Processing: Algorithms and Systems XI
Karen O. Egiazarian; Sos S. Agaian; Atanas P. Gotchev, Editor(s)

© SPIE. Terms of Use
Back to Top