カテゴリ: 論文誌(論文単位)グループ名: 【D】産業応用部門発行日: 2019/01/01タイトル(英語): Practical Algorithm Design for the FFT-based Robust Image Registration Method著者名: 李 尭希（東京大学工学系研究科），藤本 博志（東京大学工学系研究科）著者名(英語): Yoshi Ri (The University of Tokyo), Hiroshi Fujimoto (The University of Tokyo)キーワード: 画像レジストレーション，位相相関，回転不変離散フーリエ変換 image registration，phase correlaton，RIPOC要約(英語): Image registration plays a very important role in a camera-based remote sensing system. This paper discusses a 2D fast Fourier transform (FFT)-based method, which is well known for its easy implementation, accuracy, and robustness. The problem with the FFT-based method is that its robustness and accuracy highly depend on some preprocessing such as the design of a bandpass filter and subpixel estimation. This paper provided solutions for its algorithm design and tuning issues. Finally, the evaluation based on the image dataset and the actual images demonstrated its effectiveness.本誌: 電気学会論文誌D（産業応用部門誌） Vol.139 No.1 （2019）本誌掲載ページ: 22-29 p原稿種別: 論文／日本語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejias/139/1/139_22/_article/-char/ja/
