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

Development of a self-learning in-vehicle smart vision system for road damage detection and map updating

Research Project

Project/Area Number 21K11949
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionKurume National College of Technology

Principal Investigator

Matsushima Kousuke  久留米工業高等専門学校, 制御情報工学科, 准教授 (60413879)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2023: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Keywords道路損傷認識 / 地図作成 / 道路損傷検出 / 自己学習機能 / 自己位置推定 / 車載スマートビジョン / 地図更新
Outline of Research at the Start

道路損傷の簡易的な点検手法に関する研究が盛んに行われている。しかし,様々な要因により教師データに存在しない現象が出現するため,高い検出精度を維持することは難しい。さらに,検出された損傷箇所の保存法や運転への利活用も課題となっている。
そこで,本研究では,道路の損傷情報をダイナミックマップに反映させることのできるスマートビジョンシステムを開発する。このシステムは,損傷箇所の経年変化や環境変化に対応するため,既存のラベル付き教師データを活用しつつ,損傷箇所の検出結果を新たに学習して教師データとして活用する機能を備えたものである。

Outline of Final Research Achievements

The objective of this study was to develop a smart vision system capable of reflecting road damage information in dynamic maps. First, we developed a system that performs road damage recognition by automatically labeling unknown captured data while utilizing existing labeled road damage training data. Next, we developed a system that improves the accuracy of mapping by removing moving objects when using Visual SLAM technology. We also developed a method to improve the accuracy of object detection by improving unsupervised learning for detecting candidate object regions, and a method to solve PnP problems using orientation information.

Academic Significance and Societal Importance of the Research Achievements

道路損傷の点検手法において,既存のラベル付き教師データを活用しつつ,検出結果の新規のラベル付けデータを次学習の教師データとして活用する方法は,他のパターン認識研究でも応用できるため,重要な研究となる。これにより,交通量や自然環境が常に変化する環境においても,車両に搭載されたスマートフォンやドライブレコーダなどで道路を撮影することにより,道路損傷の簡易的な点検が可能となる。また,普段の防災・維持管理にも努めることができ,自然災害発生直後にも情報を迅速かつ的確に収集し,復旧や支援に必要不可欠な道路交通網を確保することが可能となる。

Report

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

    (7 results)

All 2024 2023 2022

All Journal Article (7 results) (of which Peer Reviewed: 7 results)

  • [Journal Article] DETReg Incorporating Semi-Supervised Learning for Object Detection in the Advanced Driver-Assistance Systems2024

    • Author(s)
      Keita Nakano and Kousuke Matsushima
    • Journal Title

      International Conference on Robotics, Engineering, Science, and Technology

      Volume: - Pages: 123-128

    • DOI

      10.1109/restcon60981.2024.10463586

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Multi-Lens Visual SLAM with Integrated Moving Object Removal using Unsupervised Models2024

    • Author(s)
      Ryoichirou Hara and Kousuke Matsushima
    • Journal Title

      International Conference on Robotics, Engineering, Science, and Technology

      Volume: - Pages: 90-95

    • DOI

      10.1109/restcon60981.2024.10463585

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Classification of Road Damage Images Considering the Discovery of Unknown Classes2023

    • Author(s)
      Hiroki Nagamatsu and Kousuke Matsushima
    • Journal Title

      International Conference on Automation, Control and Robots

      Volume: - Pages: 73-77

    • DOI

      10.1109/icacr59381.2023.10314607

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A Method for Solving Camera Pose Estimation Problems Considering the Pairwise Constraints and Polar Coordinates2023

    • Author(s)
      Kohta Uematsu and Kousuke Matsushima
    • Journal Title

      International Conference on Computer and Communication Systems

      Volume: -

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Automatic Pavement Type Recognition based on Mobile Deep Learning2022

    • Author(s)
      Reiya Murasaki and Kousuke Matsushima
    • Journal Title

      IEEE Global Conference on Life Sciences and Technologies

      Volume: - Pages: 370-374

    • DOI

      10.1109/lifetech53646.2022.9754920

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Image Classification for Advanced Driving Assistant System in Electric Wheelchair2022

    • Author(s)
      Masahiro Yamawaki and Kousuke Matsushima
    • Journal Title

      IEEE Global Conference on Life Sciences and Technologies

      Volume: - Pages: 349-353

    • DOI

      10.1109/lifetech53646.2022.9754888

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Visual SLAM in Dynamic Environments using Multi-lens Omnidirectional Camera2022

    • Author(s)
      Shoya Yamasaki and Kousuke Matsushima
    • Journal Title

      IEEE Global Conference on Life Sciences and Technologies

      Volume: - Pages: 465-469

    • DOI

      10.1109/lifetech53646.2022.9754868

    • Related Report
      2021 Research-status Report
    • Peer Reviewed

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi