Preprint / Version 1

Segmentation of Stone Walls from 3D Models for Stone Wall BIM Creation

##article.authors##

  • Kenta Itakura ImVisionLabs, Inc.
  • Takuya Hayashi ImVisionLabs, Inc.
  • Yuichi Takata Nara National Research Institute for Cultural Properties Department of Planning and Coordination

DOI:

https://doi.org/10.51094/jxiv.1260

Keywords:

castle, heritage documentation, dxf export, segment anything model (SAM), stone segmentation

Abstract

Traditionally, the mapping of stone walls has relied on two-dimensional drawings and photographs, which present challenges such as the lack of three-dimensional information, dependence on individual skills, and significant labor demands. This study aims to enhance the efficiency of creating "Ishigaki Karte" for systematically recording and managing the current state and structure of cultural heritage stone walls. We propose a method to generate line drawings from high-density 3D mesh models created using Structure- from Motion Multi-View Stereo (SfM-MVS). By applying the Segment Anything Model (SAM) to the texture images of the 3D models, we automatically segment individual stone wall regions and extract boundary information, which is then exported in DXF format. To verify accuracy, we compared the automatically generated boundaries with manually delineated boundaries in a selected area of Nagoya Castle. The results showed a precision of 0.90 and a recall of 0.79, confirming that the segmentation of each stone wall was achieved with high accuracy.

Conflicts of Interest Disclosure

No potential conflicts of interest were disclosed.

Downloads *Displays the aggregated results up to the previous day.

Download data is not yet available.

References

史跡広島城跡に係る石垣カルテの作成について,URL:https://www.city.hiroshima.lg.jp/_res/projects/default_project/_page_/001/020/581/226947.pdf, 最終閲覧日:2025年 4 月 23 日.

特別史跡名古屋城跡保存活用計画 第 6 章保存,URL:https://www.city.nagoya.jp/kankobunkakoryu/cmsfiles/contents/0000105/105368/6shou.pdf, 最終閲覧日2025 年5月 9 日

野口淳:文化機関における 3 次元計測・記録データの管理・公開の意義と課題. カレントアウェアネス/国立国会図書館関西館図書館協力課 編, (351), pp18-22, 2022.

高田 祐一:UAV-LiDAR による小豆島加藤家石丁場の高精度地形計測,小豆島石丁場調査委員会 2023,『小豆島石のシンポジウム2023 資料集「日本遺産の石の島,新たな発見と保存をめざして!」』小豆島石丁場調査委員会, pp. 20-25, 2023.

高田 祐一, 大村 陸, 林 瑞樹:城郭石垣の記録・管理における技術革新:石垣 BIM の開発と実験的応用. 名古屋城調査研究センター研究紀要, pp.149-158, 2025.

He, K., Gkioxari, G., Dollar, P. and Girshick, R.: Mask R-CNN, Proc. ICCV2017, pp.2961-2969, 2017.

Montes, K., Taher, S. S. A. D., Dang, J. and Chun, P.-J.:Semi-autopilot UAV flight path control for bridgestructural health monitoring under GNSS-denied environment, Artif. Intell. Data Sci., Vol. 2, No. 2, pp. 19-26, 2021.

叶井 和樹,山根 達郎,石黒 聡士,全 邦釘:Semantic Segmentation を用いた斜面崩壊領域の自動検出,AI・データサイエンス論文集, Vol. 1, No. 1, pp.421-428, 2020.

立石 良,西嶋 音々, 東川 創,牧野 幹太:Mask R-CNN による道路カメラ画像の路面積雪判定モデル,AI・データサイエンス論文集, Vol. 5, No. 3, pp. 376-381, 2024.

Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C.,Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo,W.-Y., Dollár, P. and Girshick, R.: Segment Anything,arXiv:2304.02643 [cs.CV], pp. 1-14, 2023.

板倉 健太,林 拓哉, 上脇 優人,全 邦釘:セマンティックセグメンテーションやセンサーフュージョンを利用した橋梁の構造情報の推定のための点群処理手法の開発,AI・データサイエンス論文集, Vol. 5,No. 3, pp. 10-21, 2024.

板倉健太,林拓哉,斎藤嘉人,全邦釘:センサーフュージョンを利用した 3 次元点群からの錆の検出,Jxiv,doi: https://doi.org/10.51094/jxiv.1160.

Itakura, K. and Hosoi, F.: Three-dimensional treemonitoring in urban cities using automatic tree detection method with mobile LiDAR data, Artif. Intell. Data Sci.,Vol. 2, No. 2, pp. 1-10, 2021.

Itakura, K., and Hosoi, F.: Automated tree detection from 3D lidar images using image processing and machine learning. Appl. Opt., Vol. 58, No. 14, pp. 3807-3811, 2019.

稲富 翔伍, 全 邦釘:点群の画像化とディープラーニングを用いた橋梁点群のセグメンテーション,AI・データサイエンス論文集, Vol. 2, No. 2, pp. 418-427,2021.

Kong, Q., Liao, L., and Yuan, C.: Rapid generation of editable engineering drawings from 3D point cloud reconstruction for large-scale buildings. J. Building Eng, 63, 105486, 2023.

Fang, Y., Mitoulis, S. A., Boddice, D., Yu, J., & Ninic, J.: Scan-to-BIM-to-Sim: Automated reconstruction of digital and simulation models from point clouds with applications on bridges. Results Eng., 104289, 2025.

Torr, P. H., and Zisserman, A., MLESAC.: A new robust estimator with application to estimating image geometry,Comput. Vis. Image Und.,Vol. 78, Issue 1, pp. 138-156, 2000.

Zhao, X., Ding, W., An, Y., Du, Y., Yu, T., Li, M., ... & Wang, J.: Fast segment anything. arXiv preprint arXiv:2306.12156, 2023.

Pingel, T. J., Clarke, K. C., & McBride, W. A.: An improved simple morphological filter for the terrain classification of airborne LIDAR data. ISPRS journal of photogrammetry and remote sensing, Vol. 77, pp.21-30, 2013.

Zhang W, Qi J, Wan P, Wang H, Xie D, Wang X, Yan G.: An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation. Remote Sensing.; Vol. 8, No.6, 501, 2016.

大村陸,浅岡優,高田祐一,田ロ一男,二橋慶太郎, 井口喜景,小山圭嗣:西尾市前島石丁場跡調査報告.名古屋城調査研究センター研究紀要. pp.119-148.2025.

Posted


Submitted: 2025-05-14 04:15:11 UTC

Published: 2025-05-16 10:51:42 UTC
Section
Information Sciences