Development of point cloud processing technology for digital archeology in archeology

2020 Fiscal Year Final Research Report

• Project/Area Number: 17K13571
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Archaeology
• Research Institution: Osaka Institute of Technology
• Principal Investigator: Muraki Yuta 大阪工業大学, 情報科学部, 講師 (60710077)
• Project Period (FY): 2017-04-01 – 2021-03-31
• Keywords: 三次元計測 / デジタルアーカイブ / 位置合わせ / 欠損検出 / 欠損補間 / 機械学習 / 点群

Outline of Final Research Achievements

In this research, we have developed a system for advanced defect detection, advanced defect interpolation, texture interpolation using machine learning, and 3D shape generation for measurement points. In defect detection and interpolation, a highly accurate method was established by dynamically determining the evaluation value and the weight from the information around the defect. We also worked on 3D shape generation using machine learning, and conducted verification and generation experiments on effective learning data. Furthermore, we also examined the exhibition method by displaying the three-dimensional shape generated by this research on a normal display or a head-mounted display such as VR or MR.

Free Research Field

コンピュータグラフィックス

Academic Significance and Societal Importance of the Research Achievements

本システムは，高速かつ高精度な点群処理技術であることに加え，遺物のデジタルアーカイブ化のボトルネックとなるユーザ負担を低減するといった特色がある．これまでユーザが手動で決定していたパラメータを，コンピュータ側で自動決定する仕組みを提案しており，遺物のデジタルアーカイブ化の更なる促進が予想される．また，提案する機械学習を用いた3次元形状生成手法を用いることで，大きな欠損領域に対する補間手法へと応用が期待できる．