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

Prediction of road damage based on low-cost, high-volume, and high-frequency data accumulation using deep learning

Research Project

Project/Area Number 20K14799
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 22010:Civil engineering material, execution and construction management-related
Research InstitutionThe University of Tokyo

Principal Investigator

Maeda Hiroya  東京大学, 生産技術研究所, 特任研究員 (90853200)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords土木 / 舗装 / 画像処理 / AI / インフラメンテナンス / 舗装点検 / 道路損傷検知 / 深層学習 / データセット / ひび割れ検出 / 地理空間情報
Outline of Research at the Start

道路路面の簡易な点検手法に関する研究は盛んに行われているが、予防保全に基づくメンテナンスサイクルの確立のためには、点検だけではなく損傷箇所の将来予測が重要である。 しかし、自然環境が常に変化する現場では、高い検出精度を維持し、損傷箇所を一意に特定しつつ点検データを蓄積することが難しいため、損傷箇所の時系列データを蓄積できず将来予測をする研究が行われていない。そこで、本研究では深層学習と画像処理手法等を用いることで道路損傷箇所を網羅的に、かつ正確に把握し、損傷データを蓄積する手法を構築する。 さらに、蓄積したデータを元に、道路路面の損傷箇所の時系列変化を予測する手法を構築する。

Outline of Final Research Achievements

In this research, we conducted research to automatically detect road damage locations such as cracks and holes using only widely used hardware such as smartphones and drive recorders. Furthermore, we collected road damage data not only in Japan but also in India and the Czech Republic, and built an automatic detection model that can be applied in any country. At that time, by tuning the automatic detection model created with Japanese road data, it was shown that the automatic detection model in India and the Czech Republic can be created with a small amount of training data.

Academic Significance and Societal Importance of the Research Achievements

道路メンテナンスは人手不足、予算不足が深刻であり、従来のように人手や高価な専用車両を用いた点検を継続的、網羅的に実施していくことが難しくなっている。このような状況で、本研究ではスマートフォンやドライブレコーダーといった比較的安価な機材のみを用いて、低廉迅速に道路損傷データを収集できることを示し、社会的な意義が大きいと考えている。また、日本国内で作成した損傷の自動検出モデルを海外で適用することができる可能性を示し、複数の国における道路損傷データを整備、公開したことは学術的な意義が大きいと考える。

Report

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

    (10 results)

All 2022 2021 2020 Other

All Int'l Joint Research (2 results) Journal Article (6 results) (of which Int'l Joint Research: 5 results,  Open Access: 5 results,  Peer Reviewed: 3 results) Presentation (1 results) (of which Int'l Joint Research: 1 results) Remarks (1 results)

  • [Int'l Joint Research] Indian Institute of Technology Roorkee(インド)

    • Related Report
      2021 Research-status Report
  • [Int'l Joint Research] Indian Institute of Technology Roorkee(インド)

    • Related Report
      2020 Research-status Report
  • [Journal Article] Crowdsensing-based Road Damage Detection Challenge (CRDDC-2022)2022

    • Author(s)
      Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Hiroshi Omata, Takehiro Kashiyama, Yoshihide Sekimoto
    • Journal Title

      arXiv preprint arXiv:2211.11362

      Volume: -

    • Related Report
      2022 Annual Research Report
    • Open Access / Int'l Joint Research
  • [Journal Article] Road Rutting Detection using Deep Learning on Images2022

    • Author(s)
      Saha Poonam Kumari、Arya Deeksha、Kumar Ashutosh、Maeda Hiroya、Sekimoto Yoshihide
    • Journal Title

      2022 IEEE International Conference on Big Data (Big Data)

      Volume: - Pages: 1362-1368

    • DOI

      10.1109/bigdata55660.2022.10020458

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Deep learning-based road damage detection and classification for multiple countries2021

    • Author(s)
      Arya Deeksha、Maeda Hiroya、Ghosh Sanjay Kumar、Toshniwal Durga、Mraz Alexander、Kashiyama Takehiro、Sekimoto Yoshihide
    • Journal Title

      Automation in Construction

      Volume: 132 Pages: 103935-103935

    • DOI

      10.1016/j.autcon.2021.103935

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Generative adversarial network for road damage detection2020

    • Author(s)
      Maeda Hiroya、Kashiyama Takehiro、Sekimoto Yoshihide、Seto Toshikazu、Omata Hiroshi
    • Journal Title

      Computer-Aided Civil and Infrastructure Engineering

      Volume: 36 Issue: 1 Pages: 47-60

    • DOI

      10.1111/mice.12561

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Transfer learning-based road damage detection for multiple countries2020

    • Author(s)
      Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Alexander Mraz, Takehiro Kashiyama, Yoshihide Sekimoto
    • Journal Title

      arXiv preprint arXiv:2008.13101

      Volume: -

    • Related Report
      2020 Research-status Report
    • Open Access / Int'l Joint Research
  • [Journal Article] Global Road Damage Detection: State-of-the-art Solutions2020

    • Author(s)
      Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Hiroshi Omata, Takehiro Kashiyama, Yoshihide Sekimoto
    • Journal Title

      arXiv preprint arXiv:2011.08740

      Volume: -

    • Related Report
      2020 Research-status Report
    • Open Access / Int'l Joint Research
  • [Presentation] Global Road Damage Detection: State-of-the-art Solutions2020

    • Author(s)
      Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Hiroshi Omata, Takehiro Kashiyama, Yoshihide Sekimoto
    • Organizer
      IEEE BigData2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Remarks] Road Damager Detector

    • URL

      https://github.com/sekilab/RoadDamageDetector

    • Related Report
      2021 Research-status Report 2020 Research-status Report

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi