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

Next generation video coding algorithm using machine learning and its hardware implementation

Research Project

Project/Area Number 19K24347
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund
Review Section 1001:Information science, computer engineering, and related fields
Research InstitutionThe University of Tokushima

Principal Investigator

KATAYAMA Takafumi  徳島大学, 大学院社会産業理工学研究部(理工学域), 助教 (70848522)

Project Period (FY) 2019-08-30 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
KeywordsImage processing / Versatile video coding / Machine learning / 動画像符号化 / 機械学習 / Versatile Video Coding
Outline of Research at the Start

AI・IoT環境が普及される中、動画像は情報伝達の方法として、今後も大きな役割を担っています。そして、正確かつ精細な動画像を提供するために、符号化技術は身近にある様々なデバイスに実装されています。次世代の符号化技術では、並列処理が困難であることから、超高解像度への応用が益々難題となっており、特にハードウェア実装容易度の面から抜本的な解決方法が必要です。本研究では、ハードウェア実装の容易化を達成しつつ、高圧縮な新規符号化構造を確立するために、分析回路と符号化回路の二つに分けて符号化を行うことで解決します。本研究を完遂することで、AI・IoT・5Gと呼ばれる次世代の社会基盤環境へ大きく貢献します。

Outline of Final Research Achievements

With the spread of edge environments for AI and IoT, moving images will continue to play a major role as a method of information transmission. Recently, codec technology is implemented to various devices around us in order to provide accurate and detailed moving images. In the next-generation coding technology, parallel processing and application to ultra-high resolution are difficult. Therefore, a drastic solution is required especially from the viewpoint of hardware implementation.
By completing this work, it will be possible to design a dedicated IC chip that combines the technologies of the next-generation coding method and artificial intelligence.

Academic Significance and Societal Importance of the Research Achievements

先行研究では、動画像符号化と人工知能を組み合わせた手法は提案されていた。しかし、先行研究で提案された方法は、動画像符号化の効率を向上する半面、人工知能回路がより複雑になることからハードウェアへの実装が困難となっていた。本課題に対して、本研究では人工知能回路の提案と動画像符号化に対する親和性の評価を実施した。この課題を解決することで、社会で利用される電子デバイスの映像処理が、今後さらに効率的に実現できることが期待される。

Report

(3 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • Research Products

    (19 results)

All 2021 2020 2019

All Journal Article (4 results) (of which Int'l Joint Research: 4 results,  Peer Reviewed: 4 results,  Open Access: 4 results) Presentation (15 results) (of which Int'l Joint Research: 7 results)

  • [Journal Article] Maximum-Entropy-Model-Enabled Complexity Reduction Algorithm in Modern Video Coding Standards2020

    • Author(s)
      Jiang Xiantao、Song Tian、Katayama Takafumi
    • Journal Title

      Symmetry

      Volume: 12 Issue: 1 Pages: 113-113

    • DOI

      10.3390/sym12010113

    • NAID

      120007037465

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Low-Complexity and Hardware-Friendly H.265/HEVC Encoder for Vehicular Ad-Hoc Networks2019

    • Author(s)
      Jiang Xiantao、Feng Jie、Song Tian、Katayama Takafumi
    • Journal Title

      Sensors

      Volume: 19 Issue: 8 Pages: 1927-1927

    • DOI

      10.3390/s19081927

    • NAID

      120007141565

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Quality-Oriented Perceptual HEVC Based on the Spatiotemporal Saliency Detection Model2019

    • Author(s)
      Jiang Xiantao、Song Tian、Zhu Daqi、Katayama Takafumi、Wang Lu
    • Journal Title

      Entropy

      Volume: 21 Issue: 2 Pages: 165-165

    • DOI

      10.3390/e21020165

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Spatial Correlation-Based Motion-Vector Prediction for Video-Coding Efficiency Improvement2019

    • Author(s)
      Jiang Xiantao、Song Tian、Katayama Takafumi、Leu Jenq-Shiou
    • Journal Title

      Symmetry

      Volume: 11 Issue: 2 Pages: 129-129

    • DOI

      10.3390/sym11020129

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] A Study of Smoothness in Neural ODEs2021

    • Author(s)
      X. K. Sigalingging, S. Jules, J. S. Leu, T. Katayama 2 , and T. Song
    • Organizer
      The 6th International Forum on Advanced Technologies 2020 (IFAT2020)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Reference Frame Generation Algorithm using Dynamical Learning PredNet for VVC2021

    • Author(s)
      Takafumi Katayama, Tian Song, Takashi Shimamoto, Xiantao Jiang
    • Organizer
      IEEE International Conference on Consumer Electronics 2021(ICCE 2021)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] VVCにおける特徴マップを応用した色差成分予測手法に関する研究2020

    • Author(s)
      北脇 郁弥, 片山 貴文, 宋 天, 島本 隆
    • Organizer
      画像符号化シンポジウム(PCSJ2020)
    • Related Report
      2020 Annual Research Report
  • [Presentation] InstaGANを用いた学習ライブラリ構築に関する研究2020

    • Author(s)
      大上 剛, 宋 天, 片山 貴文, 島本 隆
    • Organizer
      画像符号化シンポジウム(PCSJ2020)
    • Related Report
      2020 Annual Research Report
  • [Presentation] 昼夜変換画像による夜間物体検出精度向上に関する研究2020

    • Author(s)
      中島 快人, 片山 貴文, 宋 天, 島本 隆
    • Organizer
      画像符号化シンポジウム(PCSJ2020)
    • Related Report
      2020 Annual Research Report
  • [Presentation] An Adaptive Selection Method of Screen Content Coding Tools for Educational Video System2020

    • Author(s)
      Zhang Hongyi, Tian Song, Takafumi Katayama, Takashi Shimamoto and Zhao Liping
    • Organizer
      The 6th International Forum on Advanced Technologies 2020 (IFAT2020)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Low Bitrate VVC-based Drone Video Coding System2020

    • Author(s)
      Soichiro Iino, Tian Song, Takafumi Katayama and Takashi Shimamoto
    • Organizer
      The 6th International Forum on Advanced Technologies 2020 (IFAT2020)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Bitrate Fluctuation Control Method for VVC-based Drone Video Coding System2020

    • Author(s)
      Soichiro Iino, Tian Song, Takafumi Katayama and Takashi Shimamoto
    • Organizer
      Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'20)
    • Related Report
      2019 Research-status Report
  • [Presentation] GAN-based Color Correction for Underwater Object Detection2019

    • Author(s)
      Takafumi Katayama, Tian Song, Takashi Shimamoto and Xiantao Jiang
    • Organizer
      OCEANS19 MTS/IEEE Seattle
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Proposal-Aware Visual Saliency Detection with Semantic Attention2019

    • Author(s)
      Lu Wang, Tian Song, Takafumi Katayama and Takashi Shimamoto
    • Organizer
      International Conference on Intelligence Science and Big Data Engineering (IScIDE 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Improvement of Cross Component Prediction by Multiple Liner Prediction for HEVC2019

    • Author(s)
      Fumiya Kitawaki, Tian Song, Takafumi Katayama, Xiantao Jiang and Takashi Shimamoto
    • Organizer
      Proceedings of International Technical Conference on Circuits/Systems, Computers and Communications(ITC-CSCC2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] VVCイントラ予測残差における変換係数予測手法に関する研究2019

    • Author(s)
      岡久 奈留, 宋 天, 片山 貴文, 島本 隆
    • Organizer
      電気関係学会四国支部連合大会講演論文集
    • Related Report
      2019 Research-status Report
  • [Presentation] オブジェクト検出の高速化アルゴリズムに関する研究2019

    • Author(s)
      中川 靖之, 宋 天, 片山 貴文, 島本 隆
    • Organizer
      電気関係学会四国支部連合大会講演論文集
    • Related Report
      2019 Research-status Report
  • [Presentation] CNNを用いたHEVCのイントラ符号化効率向上に関する研究2019

    • Author(s)
      山崎 凌佑, 宋 天, 片山 貴文, 島本 隆
    • Organizer
      電気関係学会四国支部連合大会講演論文集
    • Related Report
      2019 Research-status Report
  • [Presentation] VVCの画面間符号化におけるベイジアンネットワークを用いた高速モード決定手法に関する研究2019

    • Author(s)
      長崎 舜, 宋 天, 片山 貴文, 島本 隆
    • Organizer
      電気関係学会四国支部連合大会講演論文集
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-09-03   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi