• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Video Component Separation Based on Compressed Robust Dynamic Mode Decomposition and Its Applications

Research Project

Project/Area Number 21K17767
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionThe University of Kitakyushu

Principal Investigator

Matsuoka Ryo  北九州市立大学, 国際環境工学部, 准教授 (40780391)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2023: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords動的モード分解 / スパースコーディング / 動画像復元 / 凸最適化 / DMD / ハイパースペクトル画像
Outline of Research at the Start

本研究課題では, 背景の動きや不要な映り込みに頑健な動画像成分分離技術の開発を目的とし, 圧縮センシングやスパースモデリング技術を動的モード分解法に高度に融合した超高効率な前景/背景分離アルゴリズムを確立する. また, 提案アルゴリズムを多様なシーンに適用し, その復元精度を定性的/定量的に評価し提案技術の有効性と性能限界について明らかにする. さらに, 実応用に向けて, 圧縮センシング理論に基づく計算効率の向上, 物体認識や動作予測への応用を検討する.

Outline of Final Research Achievements

With the advancement of digital camera technology and AI techniques, the ability to recognize objects such as people and cars in images captured by surveillance and in-vehicle cameras has rapidly evolved. Existing methods typically treat the background as static and roughly separate the moving components as the foreground. However, the camera viewpoint often moves, and noise from rain or snow streaks can be introduced, along with multiple subjects like people and cars, which have different motion characteristics.
This study proposes a video component separation algorithm that integrates dynamic mode decomposition, sparse modeling, and compressed sensing techniques to process high-dimensional data while efficiently being robust to background movement. Additionally, we explore the application of this algorithm to hyperspectral images and other ultra-high-dimensional data.

Academic Significance and Societal Importance of the Research Achievements

本研究の主要な成果は、既存の動画像成分分離技術に比べてノイズなどによる劣化にロバストな手法であるため、動画像の物体認識や動き予測の精度改善に貢献し、監視カメラ技術などの応用領域における飛躍的な技術発展が期待できる。さらに、動画像やその解析が重要な役割を果たす産業・サイエンス・工学の諸分野に大きく貢献するものである。また、ノイズなどによる劣化の観点から実現が困難であった画期的な動画像処理応用を切り開き、医療・農業・産業などの広範な分野に大きなインパクトを与えるものであると考えられる。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (16 results)

All 2024 2023 2022 2021 Other

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 2 results) Presentation (7 results) (of which Int'l Joint Research: 3 results) Remarks (4 results)

  • [Journal Article] Optimizing Dynamic Mode Decomposition for Video Denoising via Plug-and-Play Alternating Direction Method of Multipliers2024

    • Author(s)
      Yamamoto Hyoga、Anami Shunki、Matsuoka Ryo
    • Journal Title

      Signals

      Volume: 5 Issue: 2 Pages: 202-215

    • DOI

      10.3390/signals5020011

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Beyond Staircasing Effect: Robust Image Smoothing via ?0 Gradient Minimization and Novel Gradient Constraints2023

    • Author(s)
      Matsuoka Ryo、Okuda Masahiro
    • Journal Title

      Signals

      Volume: 4 Issue: 4 Pages: 669-686

    • DOI

      10.3390/signals4040037

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Weighted median based multiple exposure blending for rain streak removal2022

    • Author(s)
      Mishima Mio、Matsuoka Ryo
    • Journal Title

      Proceedings of 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)

      Volume: - Pages: 732-733

    • DOI

      10.1109/gcce56475.2022.10014341

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Reflection Removal Using Multiple Polarized Images with Different Exposure Times2022

    • Author(s)
      Takuma Aizu, Ryo Matsuoka
    • Journal Title

      Proceedings of 2022 30th European Signal Processing Conference (EUSIPCO)

      Volume: - Pages: 498-502

    • DOI

      10.23919/eusipco55093.2022.9909712

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] A Study on JPEG Artifact Removal by Four-Directional Difference-based ?<sub>0,1</sub> norm Regularization2022

    • Author(s)
      Kobayashi Iori、Matsuoka Ryo
    • Journal Title

      Proceedings of 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)

      Volume: - Pages: 724-725

    • DOI

      10.1109/gcce56475.2022.10014200

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Presentation] 局所テンソル核ノルムに基づくハイパースペクトルパンシャープニングに関する検討2024

    • Author(s)
      岡﨑圭哉, 松岡諒
    • Organizer
      電子情報通信学会総合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] JPEG Artifact Removal for Hyperspectral Images Based on Spatial-Spectral Regularization2023

    • Author(s)
      Ryunosuke Eguchi, Iori Kobayashi, Shunsuke Ono, Ryo Matsuoka
    • Organizer
      Asia-Pacific Signal and Information Processing Association, Annual Summit and Conference (APSIPA ASC)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Hyperspectral Anomaly Detection based on Local-Tensor-Nuclear-Norm2023

    • Author(s)
      Mio Mishima, Iori Kobayashi, Ryo Matsuoka
    • Organizer
      IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 多重露光偏光画像を用いたガラス面の映り込み除去2022

    • Author(s)
      會津巧真, 松岡諒
    • Organizer
      電子情報通信学会 SIPシンポジウム
    • Related Report
      2022 Research-status Report
  • [Presentation] テンソルロバストPCAを用いたノイズに頑健なハイパースペクトル画像の異常検知2022

    • Author(s)
      小林伊織, 枝光皓太郎, 松岡諒
    • Organizer
      電子情報通信学会 SIPシンポジウム
    • Related Report
      2022 Research-status Report
  • [Presentation] Noise Removal for Dynamic Mode Decomposition Based on Plug-and-Play ADMM2021

    • Author(s)
      Shunki Anami, Ryo Matsuoka
    • Organizer
      Asia-Pacific Signal and Information Processing Association, Annual Summit and Conference (APSIPA ASC)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] PnP-ADMMに基づく動的モード分解のためのノイズ除去に関する考察2021

    • Author(s)
      穴見駿樹, 松岡諒
    • Organizer
      電子情報通信学会信号処理シンポジウム
    • Related Report
      2021 Research-status Report
  • [Remarks] 研究者HP

    • URL

      https://sites.google.com/site/phdmatsuokadx/home

    • Related Report
      2022 Research-status Report
  • [Remarks] 所属機関が作成した研究者紹介ページ

    • URL

      https://www.kitakyu-u.ac.jp/env/faculty/d-media/introduction/ryo-matsuoka.html

    • Related Report
      2022 Research-status Report
  • [Remarks] 研究者HP

    • URL

      https://sites.google.com/site/phdmatsuokadx

    • Related Report
      2021 Research-status Report
  • [Remarks] 業績紹介HP

    • URL

      https://sites.google.com/site/phdmatsuokadx/achievements

    • Related Report
      2021 Research-status Report

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi