Person re-identification by shifting-subclip

Y. Hiroi, W. Kameyama

研究成果: Conference contribution

抄録

Because of the proliferation of surveillance camera and the wide range of its utilization, person re-identification (re-ID) technology has been drawing attention. Although video-based re-ID to extract spatial and temporal features has become the mainstream these days, the number of input frames for most of video-based re-ID architectures is usually fixed. Thus, frame looping or frame duplication is applied if the number of input frames is less than the specified value. However, by applying CNN to the entire looped frames, the temporal features cannot be well trained. Therefore, in this paper, we propose a method to apply CNN not to the entire looped frames but several times to the neighboring frames by shifting frames (shifting-subclip), then the average of each CNN output is processed for further temporal feature extraction. The evaluation using the MARS dataset shows that mAP (Mean Average Precision score) and CMC (Cumulative Match Curve) with the proposal is higher than that without it. It suggests that it is effective to apply the proposed shifting-subclip in the MARS dataset.

本文言語English
ホスト出版物のタイトルInternational Workshop on Advanced Imaging Technology, IWAIT 2021
編集者Masayuki Nakajima, Jae-Gon Kim, Wen-Nung Lie, Qian Kemao
出版社SPIE
ISBN(電子版)9781510643642
DOI
出版ステータスPublished - 2021
イベント2021 International Workshop on Advanced Imaging Technology, IWAIT 2021 - Kagoshima, Virtual, Japan
継続期間: 2021 1 52021 1 6

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
11766
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

Conference

Conference2021 International Workshop on Advanced Imaging Technology, IWAIT 2021
国/地域Japan
CityKagoshima, Virtual
Period21/1/521/1/6

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「Person re-identification by shifting-subclip」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