Multi-view Based Pose Alignment Method for Person Re-identification

Yulei Zhang, Qingjie Zhao*, You Li

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

This paper proposes a Multi-View based Pose Alignment (MVPA) method for person re-identification (re-id). Most recent methods solve re-id as a matching process based on single image. However, when poses vary or viewpoints change, the performance seriously deteriorates. This paper aims to learn a representation insensitive to view and pose. Specifically, we establish a set of Multi-view based Person Pose Templates (MPPT) and propose a Pose-Guided Person image Generation (iPG2) model to synthesize multi-view and uniform-pose based images. The representation learned from multi-view images can significantly enhances the accuracy of re-id. We evaluate our method on two popular datasets, i.e., Market-1501 and DukeMTMC-reID. The results show that our framework promotes the performance of re-id a lot and surpass other methods.

Original languageEnglish
Title of host publicationProceedings of 2019 Chinese Intelligent Automation Conference
EditorsZhidong Deng
PublisherSpringer Verlag
Pages439-447
Number of pages9
ISBN (Print)9789813290495
DOIs
Publication statusPublished - 2020
EventChinese Intelligent Automation Conference, CIAC 2019 - Jiangsu, China
Duration: 20 Sept 201922 Sept 2019

Publication series

NameLecture Notes in Electrical Engineering
Volume586
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceChinese Intelligent Automation Conference, CIAC 2019
Country/TerritoryChina
CityJiangsu
Period20/09/1922/09/19

Keywords

  • Generative Adversarial Networks
  • Person re-identification
  • Pose Alignment

Fingerprint

Dive into the research topics of 'Multi-view Based Pose Alignment Method for Person Re-identification'. Together they form a unique fingerprint.

Cite this