メタバースマップの継続的更新のための差分検出

• Item type: SIG Technical Reports(1)
• 公開日: 2024-01-18
• タイトル: メタバースマップの継続的更新のための差分検出
• タイトル / 言語: en
• タイトル: Change Detection for Constantly Maintaining Up-to-date Metaverse Maps
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: 慶應義塾大学
• 著者所属: 慶應義塾大学
• 著者所属: 慶應義塾大学
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者名: 松原, 智也; 杉本, 麻樹; 斎藤, 英雄
• 著者名(英): Tomoya, Matsubara; Maki, Sugimoto; Hideo, Saito
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Metaverse has been attracting more and more attention because of its potential for various use cases. In metaverse applications, the seamless integration of digital and physical worlds is vital for synchronizing information from one world to another. One way to achieve this is to reconstruct 3D environmental maps every time, which is not feasible due to computational complexity. In this paper, we propose a change detection method, combined with object classification, designed for efficiently updating the existing 3D environmental map as little as possible. Despite its simplicity, the experiment shows promising results with an object detector fine-tuned with data from the target environment.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Metaverse has been attracting more and more attention because of its potential for various use cases. In metaverse applications, the seamless integration of digital and physical worlds is vital for synchronizing information from one world to another. One way to achieve this is to reconstruct 3D environmental maps every time, which is not feasible due to computational complexity. In this paper, we propose a change detection method, combined with object classification, designed for efficiently updating the existing 3D environmental map as little as possible. Despite its simplicity, the experiment shows promising results with an object detector fine-tuned with data from the target environment.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2024-CVIM-236, 号 42, p. 1-6, 発行日 2024-01-18
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8701
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会