Multi-shot person re-identification via relational Stein divergence

Azadeh Alavi, Yan Yang, Mehrtash Harandi, Conrad Sanderson

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

14 Citations (Scopus)

Abstract

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify 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.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages3542-3546
Number of pages5
ISBN (Print)9781479923410
DOIs
Publication statusPublished - 1 Dec 2013
Externally publishedYes
EventIEEE International Conference on Image Processing 2013 - Melbourne Convention and Exhibition Centre (MCEC), Melbourne, Australia
Duration: 15 Sep 201318 Sep 2013
Conference number: 20th
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6726158 (IEEE Conference Proceedings)

Publication series

Name2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Conference

ConferenceIEEE International Conference on Image Processing 2013
Abbreviated titleICIP 2013
CountryAustralia
CityMelbourne
Period15/09/1318/09/13
Internet address

Keywords

  • manifolds
  • person re-identification
  • surveillance

Cite this

Alavi, A., Yang, Y., Harandi, M., & Sanderson, C. (2013). Multi-shot person re-identification via relational Stein divergence. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 3542-3546). [6738731] (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2013.6738731