2021 Fiscal Year Final Research Report
Development of an environment design support mixed reality system capable of estimating the environment using deep learning
| Project/Area Number |
19K12681
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 90010:Design-related
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | 設計支援 / 複合現実 / 深層学習 / 動的オクルージョン処理 / ドローン / 隠消現実 / 景観シミュレーション / インスタンスセグメンテーション |
|---|
| Outline of Final Research Achievements |
This research aimed to realize mixed reality (MR) for the urban and architectural fields, in which 3D virtual models of environmental design are visualized by merging them with the real world, and the environment can be automatically estimated and examined objectively by the stakeholders.
To this end, this research achieves that the methods of MR occlusion of real space for each object (accurate representation of the back and forth relationship between the virtual model and the real world), an integrated drone and MR that enables MR from the sky, advanced DR (diminished reality) that virtually eliminates the real world, a reflection representation for MR to design near water, and an automatic sample generation for deep learning of building planes and facades were developed, implemented, and validated.
|
| Free Research Field |
環境設計情報学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は，Society5.0すなわち「超スマート社会」の構築に向けて，深層学習とMRの統合を中心として現況と将来の環境認識と設計検討を高度に可能とするシステムを新たに開発した．研究を進める中で，ドローンとMRの統合や深層学習のデータセット生成法の開発へと発展させた．
建築・都市設計分野では，正確な情報公開や説明責任，参加型まちづくりへのニーズは益々高まっており，建設DX（デジタルトランスフォーメーション）の中で，計画・設計内容を直感的，客観的に評価でき合意形成のコストを低減するシステムは必要とされており，本研究の意義は高い．
|
