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

Research on Maintenance Support for Large Structures Using Knowledge-Based Point Cloud Processing

Research Project

Project/Area Number 20H02052
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 18030:Design engineering-related
Research InstitutionThe University of Electro-Communications

Principal Investigator

Masuda Hiroshi  電気通信大学, 大学院情報理工学研究科, 教授 (40302757)

Co-Investigator(Kenkyū-buntansha) 遊佐 泰紀  電気通信大学, 大学院情報理工学研究科, 助教 (70756395)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥18,200,000 (Direct Cost: ¥14,000,000、Indirect Cost: ¥4,200,000)
Fiscal Year 2022: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2021: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2020: ¥10,920,000 (Direct Cost: ¥8,400,000、Indirect Cost: ¥2,520,000)
Keywords点群処理 / 機械学習 / 設備保全 / 物体認識 / 形状モデリング / 劣化検出 / 3次元計測 / 構造解析 / 工業設備 / 3次元計測 / 深層学習
Outline of Research at the Start

生産設備や大型構造物などの人工物の保全作業を計算機で支援するためには,高密度に計測された点群データが有用である.しかし,その処理には,対象物や計測環境の知識を織り込んだ点群処理手法の開発が必要である.これまで専門家が対象物ごとにカスタマイズしたシステムを開発してきたが,本研究では,この作業を機械学習によって吸収し,汎用化するための方法論について研究する.その実現のために,点群処理と深層学習を組み合わせた,知的点群処理基盤を確立することを目指す.また,その基盤をベースとして,形状再構成,知的自動計測ロボット,高精度の劣化検出手法,不完全な点群からの構造解析手法について研究を行う.

Outline of Final Research Achievements

In recent years, the aging of large structures has become a major problem. In order to improve the efficiency of maintenance work, this research aims to investigate point cloud processing methods using machine learning and engineering knowledge. In this research, we developed five point processing methods for large-scale point clouds of enginnering facilities; (1) point cloud segmentation and object recognition methods using deep learning, (2) shape reconstruction methods from incomplete point clouds, (3) method for calculating optimal measurement positions for mobile robots,, (4) deterioration detection methods from point clouds using deep learning, and (5) structural analysis methods from incomplete point clouds.

Academic Significance and Societal Importance of the Research Achievements

本研究は,測量用のレーザスキャナで得られた点群を用いて,大規模な設備保全を効率的に行うための手法である.近年,機械学習が進歩しているが,点群の利用や設備保全への応用においては,必ずしも有効な手法とはなっていない.本研究では,機械学習を工業設備の保全に利用するために,5つの課題を設定して点群処理手法を開発し,その有効性を検証している.本研究は,工学的に新しい手法を提案するとともに,実際の大規模点群にも活用できるという点で実用的にも有用なものである.

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (44 results)

All 2023 2022 2021 2020

All Journal Article (10 results) (of which Peer Reviewed: 10 results,  Open Access: 10 results) Presentation (34 results) (of which Int'l Joint Research: 8 results)

  • [Journal Article] Shape Reconstruction of Structural Members of Steel Tower Considering Symmetrical Relationships2023

    • Author(s)
      Kota Kawasaki, Hiroshi Masuda
    • Journal Title

      Computer-Aided Design and Applications

      Volume: 20(5) Pages: 814-825

    • DOI

      10.14733/cadaps.2023.814-825

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Point Cloud Segmentation for Pipelines in Industrial Facilities Using Recurrent Networks2022

    • Author(s)
      Kohei Shigeta, Takuma Nagumo and Hiroshi Masuda
    • Journal Title

      Computer-Aided Design & Applications

      Volume: 20(4) Pages: 786-796

    • DOI

      10.14733/cadaps.2023.786-796

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Extraction of Guardrails from MMS Data Using Convolutional Neural Network2021

    • Author(s)
      Hiroki Matsumoto, Yuma Mori, Hiroshi Masuda
    • Journal Title

      International Journal of Automation Technology

      Volume: 15 Issue: 3 Pages: 258-267

    • DOI

      10.20965/ijat.2021.p0258

    • NAID

      130008034746

    • ISSN
      1881-7629, 1883-8022
    • Year and Date
      2021-05-05
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Data Augmentation of Classifiers for Components in Industrial Plants Using CAD Models2021

    • Author(s)
      K. Shigeta, D. Hanai, H. Masuda
    • Journal Title

      Computer-Aided Design & Applications

      Volume: 19(5) Issue: 5 Pages: 913-923

    • DOI

      10.14733/cadaps.2022.913-923

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Roadside Tree Extraction and Diameter Estimation with MMS Lidar by Using Point-Cloud Image2021

    • Author(s)
      G. Takahashi, H. Masuda
    • Journal Title

      ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

      Volume: V-2-2021 Pages: 67-74

    • DOI

      10.5194/isprs-annals-v-2-2021-67-2021

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Efficient Calculation Method for Tree Stem Traits from Large-Scale Point Clouds of Forest Stands2021

    • Author(s)
      H. Masuda, Y. Hiraoka, K. Saito, S. Eto, M. Matsushita, M. Takahashi
    • Journal Title

      Remote Sensing

      Volume: 13(13) Issue: 13 Pages: 2476-2485

    • DOI

      10.3390/rs13132476

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Point cloud features suitable for automatic labeling of MMS point cloud data2021

    • Author(s)
      高橋元気,増田 宏
    • Journal Title

      Journal of the Japan society of photogrammetry and remote sensing

      Volume: 60 Issue: 5 Pages: 266-275

    • DOI

      10.4287/jsprs.60.266

    • NAID

      40022748263

    • ISSN
      0285-5844, 1883-9061
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Extraction and Recognition of Components from Point Clouds of Industrial Plants2020

    • Author(s)
      Kohei Shigeta, Hiroshi Masuda
    • Journal Title

      Computer-Aided Design & Applications

      Volume: 18(5) Issue: 5 Pages: 890-899

    • DOI

      10.14733/cadaps.2021.890-899

    • Related Report
      2021 Annual Research Report 2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Detection of Steel Materials and Bolts from Point-Clouds of Power Transmission Pylon2020

    • Author(s)
      Iku Yoshiuchi, Yuki Shinozaki, Hiroshi Masuda
    • Journal Title

      Computer-Aided Design & Applications

      Volume: 17(3) Issue: 3 Pages: 575-584

    • DOI

      10.14733/cadaps.2020.575-584

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Extraction of Road-Crossing Power and Communication Lines from Mobile Mapping Data2020

    • Author(s)
      Kota Tajima, Hiroshi Masuda
    • Journal Title

      ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

      Volume: V-2-2020 Pages: 297-304

    • DOI

      10.5194/isprs-annals-v-2-2020-297-2020

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 機械学習を用いた点群からの幾何曲面検出(第2報)2023

    • Author(s)
      武田 駆, 河 浩大, 増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 点群からの工業設備の部材認識の高精度化2023

    • Author(s)
      大谷昂星, 南雲拓真, 増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Detection of Multiscale Deterioration from Point-Clouds of Furnace Walls2022

    • Author(s)
      T. Aoki, E. Yamamoto, H. Masuda
    • Organizer
      The 19th International Conference on Precision Engineering
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] レーザ計測点群を用いた構造物の変形解析手法の改良2022

    • Author(s)
      原木響也, 遊佐泰紀, 増田 宏
    • Organizer
      日本機械学会 第35 回計算力学講演会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 機械学習を用いた大型構造物の点群からの劣化検出2022

    • Author(s)
      青木智子, 山本恵里佳, 増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 統合特徴量による点群からの工業設備の部材認識2022

    • Author(s)
      大谷昂星, 南雲拓真, 増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 機械学習を用いた点群からの幾何曲面検出2022

    • Author(s)
      武田駆, 河 浩大, 川崎春菜, 増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 点群と画像の特徴量を用いた道路周辺地物の抽出と分類2022

    • Author(s)
      平岡慶太,峯村晃平,河 浩大,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Accurate Calculation of Tree Stem Traits in Forests by Local Correction of Point Cloud Registration2022

    • Author(s)
      Haruna Kawasaki, Hiroshi Masuda
    • Organizer
      Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Point Cloud Segmentation for Pipelines in Industrial Facilities Using Recurrent Networks2022

    • Author(s)
      Kohei Shigeta, Takuma Nagumo, Hiroshi Masuda
    • Organizer
      Proceedings of CAD'22
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Shape Reconstruction of Structural Members of Steel Tower Considering Symmetrical Relationships2022

    • Author(s)
      Kota Kawasaki, Hiroshi Masuda
    • Organizer
      Proceedings of CAD'22
    • Related Report
      2022 Annual Research Report
  • [Presentation] Deformation analysis of realistic structure using virtually laser-scanned point cloud on partial surface2022

    • Author(s)
      Hibiya Haraki, Yasunori Yusa, Hiroshi Masuda
    • Organizer
      15th World Congress on Computational Mechanics and 8th Asian Pacific Congress on Computational Mechanics
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 点群の深層学習のためのCADモデルからの学習データ生成(第2報)2022

    • Author(s)
      南雲 拓真,花井 大輝,重田 航平,増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 大規模点群の立体視による大型構造物の劣化検証システム(第2報)2022

    • Author(s)
      青木智子,山本恵里佳,増田宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 点群画像を用いた MMS 点群の構造化2022

    • Author(s)
      高橋元気, 増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 点群の深層学習のためのCADモデルからの学習データ生成2021

    • Author(s)
      南雲拓真,花井大輝,重田航平,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 移動計測による点群と画像を用いた物体の抽出と分類 (第2報)2021

    • Author(s)
      峯村晃平,増田宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 寸法計測に適した点群レジストレーション手法の検討2021

    • Author(s)
      川崎春菜,山本恵里佳, 青木智子, 増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 部材間の関係を考慮した大型構造物の形状再構成2021

    • Author(s)
      河崎浩大,峯村晃平,増田宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 自律移動ロボットによる工業設備の点群自動計測 ~点群計測のための経路計画~2021

    • Author(s)
      細田大貴,増田宏,石川貴一朗
    • Organizer
      精密工学会秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 構造物表面の部分的なレーザ計測点群を用いた変形解析の検討2021

    • Author(s)
      原木響也, 遊佐泰紀, 増田宏
    • Organizer
      日本機械学会計算力学講演会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 構造形状の計測データを活用した有限要素法解析のための計算手法の開発2021

    • Author(s)
      遊佐泰紀, 増田宏
    • Organizer
      計算工学講演会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Shape Reconstruction from Point Clouds for Supporting Maintenance of Power Transmission Pylons2021

    • Author(s)
      I. Yoshiuchi, H. Masuda
    • Organizer
      10th International Conference on Bridge Maintenance, Safety and Management
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 工業設備の点群からの部材認識における学習データの検討2021

    • Author(s)
      花井大輝, 重田航平, 増田宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 工業設備の大規模点群からの部材形状の認識と形状再構成2021

    • Author(s)
      重田航平, 増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 大規模点群の立体視による大型構造物の劣化検証システム2021

    • Author(s)
      青木智子, 山本恵里佳, 増田宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 構造物の不完全な as-built モデルを用いた応力解析法の検討2021

    • Author(s)
      遊佐泰紀, 増田 宏
    • Organizer
      精密工学会春季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] Scanline Normalization for MMS Data Measured under Different Conditions2020

    • Author(s)
      G. Takahashi, H. Masuda
    • Organizer
      Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Extraction and Recognition of Components from Point Clouds of Industrial Plants2020

    • Author(s)
      K. Shigeta, H. Masuda
    • Organizer
      The 17th Annual International CAD Conference
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 機械学習を用いたガードレールの抽出と形状再構成 (第2報)2020

    • Author(s)
      峯村 晃平,松本 裕稀,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 移動計測による点群と画像を用いた線状物体検出(第4報)2020

    • Author(s)
      田島 晃太,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 大規模点群を用いた大型構造物の壁面上の劣化検出2020

    • Author(s)
      山本 恵里佳,葭内 郁,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] 工業設備の大規模点群からの部材形状の抽出と認識(第3報)2020

    • Author(s)
      重田航平,増田 宏
    • Organizer
      精密工学会秋季大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] Deterioration Detection for Wall Surfaces of Large-Scale Structure Using Dense Point Cloud2020

    • Author(s)
      E. Yamamoto, I. Yoshiuchi, H. Masuda
    • Organizer
      The 18th International Conference on Precision Engineering
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi