Person Reidentification Via Discrepancy Matrix And Matrix Metric

Keywords

Discrepancy matrix; matrix metric; metric projection; person reidentification (re-id)

Abstract

Person reidentification (re-id), as an important task in video surveillance and forensics applications, has been widely studied. Previous research efforts toward solving the person re-id problem have primarily focused on constructing robust vector description by exploiting appearance's characteristic, or learning discriminative distance metric by labeled vectors. Based on the cognition and identification process of human, we propose a new pattern, which transforms the feature description from characteristic vector to discrepancy matrix. In particular, in order to well identify a person, it converts the distance metric from vector metric to matrix metric, which consists of the intradiscrepancy projection and interdiscrepancy projection parts. We introduce a consistent term and a discriminative term to form the objective function. To solve it efficiently, we utilize a simple gradient-descent method under the alternating optimization process with respect to the two projections. Experimental results on public datasets demonstrate the effectiveness of the proposed pattern as compared with the state-of-the-art approaches.

Publication Date

10-1-2018

Publication Title

IEEE Transactions on Cybernetics

Volume

48

Issue

10

Number of Pages

3006-3020

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TCYB.2017.2755044

Socpus ID

85031769041 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85031769041

This document is currently not available here.

Share

COinS