Learning Dense Correspondences via Local and Non-local Feature Fusion

Wen Chi Chin, Zih Jian Jhang, Yan Hao Huang, Koichi Ito, Hwann Tzong Chen

研究成果: Conference contribution

抄録

We present a learning-based method for extracting distinctive features on video objects. From the extracted features, we are able to derive dense correspondences between the objects in the current video frame and in the reference template. We train a deep-learning model with non-local blocks to predict dense feature maps for long-range dependencies. A new video object correspondence dataset is introduced for training and for evaluation. Further, we propose a new feature-aggregation technique that is based on the optical flow of consecutive frames and we apply it to the integration of multiple feature maps for alleviating uncertainties. We also use the local information provided by optical flow to evaluate the reliability of feature matching. The experimental results show that our local and nonlocal fusion approach can reduce unreliable correspondences and thus improve the matching accuracy.

本文言語English
ホスト出版物のタイトル2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1087-1095
ページ数9
ISBN(電子版)9789881476883
出版ステータスPublished - 2020 12 7
イベント2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Virtual, Auckland, New Zealand
継続期間: 2020 12 72020 12 10

出版物シリーズ

名前2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings

Conference

Conference2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020
国/地域New Zealand
CityVirtual, Auckland
Period20/12/720/12/10

ASJC Scopus subject areas

  • 人工知能
  • 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
  • ハードウェアとアーキテクチャ
  • 信号処理
  • 決定科学(その他)
  • 器械工学

フィンガープリント

「Learning Dense Correspondences via Local and Non-local Feature Fusion」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