Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise

• Item type: SIG Technical Reports(1)
• 公開日: 2021-02-24
• タイトル: Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise
• タイトル / 言語: en
• タイトル: Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: SIP1
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: School of Computing, Tokyo Institute of Technology
• 著者所属: School of Computing, Tokyo Institute of Technology
• 著者所属: School of Computing, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): School of Computing, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): School of Computing, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): School of Computing, Tokyo Institute of Technology
• 著者名: Kazuki, Naganuma; Saori, Takeyama; Shunsuke, Ono
• 著者名(英): Kazuki, Naganuma; Saori, Takeyama; Shunsuke, Ono
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper proposes an effective and efficient restoration methods for remote sensing data by constraining the gradient of stripe noise. Stripe noise removal of remote sensing data is one of the essential restoration task because stripe noise affects not only the visual quality but also subsequent processing. For stripe noise removal, an optimization technique is often used. In this paper, we adopt the gradient constraints of stripe noise to the optimization problem because the stripe noise has the fact that the spatial and temporal gradients are equal to zero. Our method imposes strong constraints on stripe noise, and thus can fully capture stripe noise, leading to much effective stripe noise removal. Also, operations required for handling the constraints of gradient are simple, which enables us to develop an efficient algorithm for solving the problem by a primal-dual splitting method. We demonstrate the advantages of our method over existing methods on restoration experiments using remote sensing data.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper proposes an effective and efficient restoration methods for remote sensing data by constraining the gradient of stripe noise. Stripe noise removal of remote sensing data is one of the essential restoration task because stripe noise affects not only the visual quality but also subsequent processing. For stripe noise removal, an optimization technique is often used. In this paper, we adopt the gradient constraints of stripe noise to the optimization problem because the stripe noise has the fact that the spatial and temporal gradients are equal to zero. Our method imposes strong constraints on stripe noise, and thus can fully capture stripe noise, leading to much effective stripe noise removal. Also, operations required for handling the constraints of gradient are simple, which enables us to develop an efficient algorithm for solving the problem by a primal-dual splitting method. We demonstrate the advantages of our method over existing methods on restoration experiments using remote sensing data.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2021-SLP-136, 号 4, p. 1-4, 発行日 2021-02-24
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会