2021 Fiscal Year Final Research Report
Large-scale construction of road surface and geospatial information using vehicle-mounted high-speed ground-penetrating radar measurements and DSP/AI processing
Project/Area Number |
19H02221
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Review Section |
Basic Section 22020:Structure engineering and earthquake engineering-related
|
Research Institution | The University of Tokyo |
Principal Investigator |
|
Project Period (FY) |
2019-04-01 – 2022-03-31
|
Keywords | 車載型地中レーダー / 埋設管 / 空洞 / 三次元位置推定 / ディジタル信号処理 / AI / 三次元地中・地表空間構造 / 模擬フィールド |
Outline of Final Research Achievements |
In the field of infrastructure, the mainstream of research has been the development of measurement and analysis technology related to "visible space information" such as the state of the infrastructure surface that can be seen directly by the eye. However, we believe that it is the construction technology of "invisible spatial information" such as underground and the inside of structures that is not directly visible that will bring about innovation in the next era. In this research, we measure the inside of the ground on a large scale while driving on-board an underground radar that has become capable of high-speed measurement in recent years, and developed a technology to automatically detect buried pipes and cavities in the ground by processing the data using digital signal processing (DSP) and AI.
|
Free Research Field |
リアルタイム空間解析工学
|
Academic Significance and Societal Importance of the Research Achievements |
本研究では,道路面下の透視技術として,車載型の高速地中レーダーにより三次元空間データを計測し,そのデータをディジタル信号処理と深層学習モデルにより分析することで,橋埋設管・空洞の三次元位置を推定する技術を開発している.カメラや測距レーザーを活用した目視可能なインフラ表面の状態評価技術に比べて,目視不可能なインフラ内部の状態の推定技術の開発はアルゴリズム構築からその有効性の検証まで各段に難しい.しかし,第三者被害を引き起こす空洞由来の陥没の低減,埋設管位置の詳細な把握による建設工事の効率化などを考えると,道路路面下の異常や構造物の三次元情報を自動で構築する技術の開発は必須である.
|