Deep metric learning for video-based person re-identification

Naoki Kato, Kohei Hakozaki, Masamoto Tanabiki, Junko Furuyama, Yuji Sato, Yoshimitsu Aoki

Research output: Contribution to journalArticle

Abstract

This paper proposes a novel approach for video-based person re-identification that exploits deep convolutional neural networks to learn the similarity of persons observed from video camera. By Convolutional Neural Networks (CNN), each video sequence of a person is mapped to a Euclidean space where distances between feature embeddings directly correspond to measures of person similarity. By improved parameter learning method called Entire Triplet Loss, all possible triplets in the mini-batch are taken into account to update network parameters at once. This simple change of parameter updating method significantly improves network training, enabling the embeddings to be further discriminative. Experimental results show that proposed model achieves new state of the art identification rate on iLEDS-VID dataset and PRID-2011 dataset with 78.3%, 83.9% at rank 1, respectively.

Original languageEnglish
Pages (from-to)1117-1124
Number of pages8
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume83
Issue number12
DOIs
Publication statusPublished - 2017 Jan 1

Keywords

  • Computer vision
  • Convolutional neural networks
  • Machine learning
  • Metric learning
  • Pattern recognition
  • Person re-identification
  • Video recognition

ASJC Scopus subject areas

  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Deep metric learning for video-based person re-identification'. Together they form a unique fingerprint.

  • Cite this