Multi-shot person re-identification via relational Stein divergence

Alavi, Azadeh, Yang, Yan, Harandi, Mehrtash and Sanderson, Conrad (2013). Multi-shot person re-identification via relational Stein divergence. In: 2013 IEEE International Conference on Image Processing ICIP 2013: Proceedings. 2013 IEEE International Conference on Image Processing (ICIP 2013), Melbourne, Australia, (3542-3546). 15-18 September 2013. doi:10.1109/ICIP.2013.6738731

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Alavi, Azadeh
Yang, Yan
Harandi, Mehrtash
Sanderson, Conrad
Title of paper Multi-shot person re-identification via relational Stein divergence
Conference name 2013 IEEE International Conference on Image Processing (ICIP 2013)
Conference location Melbourne, Australia
Conference dates 15-18 September 2013
Convener IEEE Signal Processing Society
Proceedings title 2013 IEEE International Conference on Image Processing ICIP 2013: Proceedings   Check publisher's open access policy
Journal name Proceedings of the International Conference on Image Processing   Check publisher's open access policy
Place of Publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Publication Year 2013
Sub-type Fully published paper
DOI 10.1109/ICIP.2013.6738731
Open Access Status
ISBN 9781479923410
ISSN 1522-4880
Start page 3542
End page 3546
Total pages 5
Collection year 2014
Language eng
Formatted Abstract/Summary
Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to reidentify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.
Keyword Surveillance
Person re-identification
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

Version Filter Type
Citation counts: Scopus Citation Count Cited 4 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 09 Jan 2014, 15:21:29 EST by Azadeh Alavi on behalf of School of Information Technol and Elec Engineering