2026-04-16T11:24:38Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00209742 2025-01-19T18:24:19Z 1164:5159:10515:10530

Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise Kazuki, Naganuma Saori, Takeyama Shunsuke, Ono Kazuki, Naganuma Saori, Takeyama Shunsuke, Ono SIP1 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. 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. technical report 情報処理学会 2021-02-24 application/pdf 研究報告音声言語情報処理（SLP） 4 2021-SLP-136 1 4 2188-8663 AN10442647 https://ipsj.ixsq.nii.ac.jp/record/209742/files/IPSJ-SLP21136004.pdf eng