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

Dynamical systems approach to optical flow estimation

Research Project

Project/Area Number 18H01463
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 21040:Control and system engineering-related
Research InstitutionKyushu Institute of Technology

Principal Investigator

Sebe Noboru  九州工業大学, 大学院情報工学研究院, 教授 (90216549)

Co-Investigator(Kenkyū-buntansha) 齊藤 剛史  九州工業大学, 大学院情報工学研究院, 教授 (10379654)
榎田 修一  九州工業大学, 大学院情報工学研究院, 教授 (40346862)
延山 英沢  九州工業大学, 大学院情報工学研究院, 教授 (50205291)
Project Period (FY) 2018-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥15,860,000 (Direct Cost: ¥12,200,000、Indirect Cost: ¥3,660,000)
Fiscal Year 2021: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2020: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2019: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2018: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Keywordsオプティカルフロー / 動画像処理 / 状態推定 / 非線形オブザーバ / 無限次元系 / スパースモデリング / 非線形系
Outline of Final Research Achievements

Optical flow is a vector that represents the motion of objects in images and is an important characteristic of video images. One of the significant difficulties in optical flow estimation is occlusion, as occlusion varies the intensity of the image discontinuously. Based on the dynamical systems approach, we have developed a novel estimation method that estimates not only the optical flow but also the intensity variation affected by occlusions. The proposed method improves the estimation accuracy near the region where occlusions occur.

Academic Significance and Societal Importance of the Research Achievements

オプティカルフローは,画像処理に基づく物体認識に用いられていますが,その応用として動画の圧縮にも用いられています.この推定精度を向上することで,物体認識の精度を向上させることができ,例えば車載カメラによる歩行者の認識精度を向上させることができます.本研究課題は,背景とは違う動きをする物体のオプティカルフローの精度を向上させようとするものであり,このような目的に大きく貢献するものです.

Report

(5 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • 2018 Annual Research Report
  • Research Products

    (23 results)

All 2022 2021 2020 2019 2018

All Presentation (23 results) (of which Int'l Joint Research: 9 results)

  • [Presentation] 3D Map Generation with Shape and Appearance Information2022

    • Author(s)
      Taro Yamada and Shuichi Enokida
    • Organizer
      17th International Conference on Computer Vision Theory and Applications (VISAPP2022)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Robust 3D Object Detection for Moving Objects Based on PointPillars2022

    • Author(s)
      Ryota Nakamura and Shuichi Enokida
    • Organizer
      2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] M2DetにおけるBackbone Networkの特徴拡張2022

    • Author(s)
      齊藤紘哉,大塚祐輝,榎田修一
    • Organizer
      動的画像処理実利用化ワークショップ2022
    • Related Report
      2021 Annual Research Report
  • [Presentation] A Dense Optical Flow Estimation Based on Dynamical System Approach under Intensity Variation Violating the Conservation Law2021

    • Author(s)
      Aki Nakamura, Noboru Sebe, Shuichi Enokida, and Eitaku Nobuyama
    • Organizer
      Proceedings of the SICE Annual Conference 2021
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 3DCNN-based mouth shape recognition for patient with intractable neurological diseases2021

    • Author(s)
      Yuya Nakamura, Takeshi Saitoh and Kazuyuki Itoh
    • Organizer
      Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Handcrafted Featuresにより拡張された PointCNNの識別性能に関する研究2021

    • Author(s)
      郷原武尊,中村亮太,榎田修一
    • Organizer
      第26回知能メカトロニクスワークショップ
    • Related Report
      2021 Annual Research Report
  • [Presentation] A New Optical Flow Estimation Based on Dynamical System Approach with Intensity Variation Violating the Conservation Law2020

    • Author(s)
      Aki Nakamura, Noboru Sebe, Shuichi Enokida, and Eitaku Nobuyama
    • Organizer
      Proceedings of SICE Annual Conference 2020
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 3D-CNNを用いた神経難病患者の口形認識に関する研究2020

    • Author(s)
      中村祐哉,齊藤剛史,伊藤和幸
    • Organizer
      電子情報通信学会福祉情報工学研究会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 形状情報と外観情報を用いたロボット周辺の走行可能領域推定2020

    • Author(s)
      山田 太郎,榎田 修一
    • Organizer
      ビジョン技術の実利用ワークショップ2020
    • Related Report
      2020 Annual Research Report
  • [Presentation] VoxelNetに基づく深層学習による位置変化に頑健な3次元物体検出2020

    • Author(s)
      中村 亮太,榎田 修一
    • Organizer
      ビジョン技術の実利用ワークショップ2020
    • Related Report
      2020 Annual Research Report
  • [Presentation] x-means法を用いた三次元点群に対する歩行者群自動分割2020

    • Author(s)
      大谷駿介,榎田修一
    • Organizer
      動的画像処理実利用化ワークショップ2020
    • Related Report
      2019 Annual Research Report
  • [Presentation] Real AdaBoostを用いた特徴選択に基づく車載LIDARによる車両検出の高精度化に関する研究2020

    • Author(s)
      大岩根拓馬,榎田修一
    • Organizer
      動的画像処理実利用化ワークショップ2020
    • Related Report
      2019 Annual Research Report
  • [Presentation] 拡大・回転が推定可能なオプティカルフロー推定モデルへの逐次最小二乗法の適用2019

    • Author(s)
      中村翔太,瀬部昇,延山英沢,榎田修一
    • Organizer
      第38回計測自動制御学会九州支部学術講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 神経難病患者の口形認識に関する研究2019

    • Author(s)
      中村祐哉,齊藤剛史,伊藤和幸
    • Organizer
      電子情報通信学会2019年10月福祉情報工学研究会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Research on Feature descriptors for vehicle detection by LIDAR2019

    • Author(s)
      Takuma Oiwane, Priscilla Indira Osa, Shuichi Enokida
    • Organizer
      5th International Conference on Machine Vision and  Machine Learning (MVML 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 並列処理を用いたサイズ分布による 歩行者3次元点群の特徴記述2019

    • Author(s)
      丸山健太,藤尾光彦,榎田修一
    • Organizer
      第22回画像の認識・理解シンポジウム (MIRU2019)
    • Related Report
      2019 Annual Research Report
  • [Presentation] LIDARによる歩行者検出のためのk-means++ 法を用いた歩行者群分割2019

    • Author(s)
      大谷駿介,榎田修一
    • Organizer
      第25回画像センシングシンポジウム
    • Related Report
      2019 Annual Research Report
  • [Presentation] Improving the Accuracy of Dynamical System Based Optical Flow Estimation by Central Difference Discretization of Time Derivative2018

    • Author(s)
      Yuta Akiyoshi, Noboru Sebe, Shuichi Enokida and Eitaku Nobuyama
    • Organizer
      4th International Conference on Machine Vision and Machine Learning (MVML'18)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] SSSD: Speech Scene Database by Smart Device for Visual Speech Recognition2018

    • Author(s)
      Takeshi Saitoh and Michiko Kubokawa
    • Organizer
      24th International Conference on Pattern Recognition (ICPR2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Image-based Attention Level Estimation of Interaction Scene by Head Pose and Gaze Information2018

    • Author(s)
      Rinko Komiya, Takeshi Saitoh, and Kazutaka Shimada
    • Organizer
      17th IEEE/ACIS International Conference on Computer and Information Science (ICIS2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 再帰型ニューラルネットワークを用いた動き特徴量による単語読唇システムの開発2018

    • Author(s)
      齊藤剛史,窪川美智子
    • Organizer
      ビジョン技術の実利用ワークショップ(ViEW2018)
    • Related Report
      2018 Annual Research Report
  • [Presentation] SSSDを用いた深層学習による読唇精度に関する検討2018

    • Author(s)
      窪川美智子,齊藤剛史
    • Organizer
      第21回画像の認識・理解シンポジウム(MIRU2018)
    • Related Report
      2018 Annual Research Report
  • [Presentation] 再帰型深層学習を用いたドライブレコーダ記録映像の自動解析2018

    • Author(s)
      甲斐夕登,榎田修一, 本村太一
    • Organizer
      自動車技術会学術講演会2018秋季大会
    • Related Report
      2018 Annual Research Report

URL: 

Published: 2018-04-23   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi