Person re-identification by two-stream feature-fusion architecture utilizing a partial body image

Yuki Hiroi, Wataru Kameyama

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Because of the proliferation of surveillance camera and the wide range of its utilization, 'Person Re-identification' technology has been drawing attention. However, the issues such as differences in person's appearances depending on their wearing items, clothes and behaviors still remain. Therefore, in this paper, we propose a two-stream feature-fusion architecture to improve the re-identification accuracy, where spatio-temporal features of partial body images, that we conceive to represent person's individuality robust to such differences, and the corresponding entire images, by applying convolutional LSTM and 3D CNN. The evaluation using the MARS dataset shows that the feet features are most effective among the four horizontally-split partial body images. And the CMS (Cumulative Match Score) by convolutional LSTM applied to the feet features in the proposed architecture is higher than the existing method which applies CNN and temporal pooling only to the entire images. The results show that it is effective to additionally use spatio-temporal features of feet in the MARS dataset.

本文言語English
ホスト出版物のタイトル2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ399-400
ページ数2
ISBN(電子版)9781728198026
DOI
出版ステータスPublished - 2020 10 13
イベント9th IEEE Global Conference on Consumer Electronics, GCCE 2020 - Kobe, Japan
継続期間: 2020 10 132020 10 16

出版物シリーズ

名前2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

Conference

Conference9th IEEE Global Conference on Consumer Electronics, GCCE 2020
国/地域Japan
CityKobe
Period20/10/1320/10/16

ASJC Scopus subject areas

  • 信号処理
  • 電子工学および電気工学
  • メディア記述
  • 器械工学
  • コンピュータ ネットワークおよび通信
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Person re-identification by two-stream feature-fusion architecture utilizing a partial body image」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル