研究生: |
楊旻蓉 MIN-JUNG YANG |
---|---|
論文名稱: |
變異構件識別演算法於時變 BIM 模型更新 Changed Component Identification Algorithm for Time-variant BIM Model Renewal |
指導教授: |
陳鴻銘
Hung-Ming Chen 莊子毅 Tzu-Yi Chuang |
口試委員: |
謝佑明
Yo-Ming Hsieh 紀乃文 Nai-Wen Chi 陳鴻銘 Hung-Ming Chen 莊子毅 Tzu-Yi Chuang |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 營建工程系 Department of Civil and Construction Engineering |
論文出版年: | 2022 |
畢業學年度: | 110 |
語文別: | 中文 |
論文頁數: | 69 |
中文關鍵詞: | BIM 、變異識別 、點雲 、Scan-vs-BIM 、BIM-vs-BIM |
外文關鍵詞: | BIM, change identification, point clouds, Scan-vs-BIM, BIM-vs-BIM |
相關次數: | 點閱:204 下載:1 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
建築資訊模型(Building Information Modeling, BIM)在建築生命週期(Building Lifecycle Management, BLM)的應用上展現了的價值,然而,實務上,BIM模型經常因為設計變更或整合困難,導致BIM模型常有與現地狀況不符或產生錯誤的情況發生。如何使建築生命週期各階段之BIM模型與實際場景一致,目前仍然缺乏一個標準化的處理機制,為此,本研究建立BIM vs BIM (BvB)與Scan vs BIM (SvB)兩種檢測任務之作業流程,提出能針對不同類別的構件進行變異識別之演算法,以輔助各階段中的BIM模型更新。為完備擬議之框架,本研究採用移動式平台搭載深度相機蒐集現地點雲資料,以及實現模型產製點雲(BIM-to-Point clouds)策略,產出無誤差BIM構件點雲及繼承構件之語意資訊,並且提出變異構件識別演算法(Changed Component Identification, CCI),識別兩數據集中所有構件之狀態類別,包括存在、移動、新增、缺失及待定物件五種類別,同時記錄變異構件之語意標籤及位置。最後,研究使用現地點雲與時變BIM模型針對整體框架進行測試,其中BvB與SvB任務中的評估指標分別達到約93%與80%的準確率,顯示良好的預測成果。研究中除了驗證研擬框架的可行性,也針對CCI演算法的相似度檢查進行深入探討,測試不同搜尋半徑、點密度及點雲品質等因素對於相似度檢查上之影響,提供演算法在實務應用上的參數設置依據。研究成果能減少BIM模型在更新作業上所耗費的人力及時間成本,進而推動BIM於建築生命週期上的應用與發展。
This study presents an automatic framework for both Scan-vs-BIM and BIM-vs-BIM model renewal. To this end, a hybrid simultaneous localization and mapping (SLAM), a BIM-to-point cloud strategy, and object-based changed component identification (CCI) are proposed to complete the framework. The hybrid SLAM enhances robustness to the limitations of indoor environments while the CCI cooperating with the BIM-to-point cloud strategy can identify five changing states along with locations and semantic information of the changed components. Besides, experiments with different variables were conducted to gain insight into the effectiveness of dealing with various point cloud quality and explore the similarity level of corresponding components under different point densities and quality for the reference of parameter configuration. Finally, validations of the BIM-vs-BIM and Scan-vs-BIM cases achieved an accuracy of 93% and 80%, respectively. The framework is expected to improve the automated level of practical BIM model renewal.
[1] S. Bonandrini, C. Cruz, C. Nicolle, Building lifecycle management, in: Proceedings of the International Conference on Product Lifecycle Management, Lyon, France, Citeseer, 2005.
[2] 芬蕭玉, 公有建築工程導入BIM現況之問題與對策探討, Master’s Thesis, 國立臺灣大學, 2019. https://doi.org/10.6342/NTU201903158.
[3] 應用BIM輔助建築設施管理之國內案例探討, (n.d.). https://www.abri.gov.tw/News_Content_Table.aspx?n=807&s=39197 (accessed August 17, 2022).
[4] 斌楊智, 青李怡, 國內不同類型私部門應用BIM現況調查之比較研究, 營建管理季刊. (2016) 1–12. https://doi.org/10.6505/CMJ-2016-106-1-12.
[5] I.F. Smith, Outcomes of the joint international conference on computing and decision making in civil and building engineering, montreal 2006, in: Workshop of the European Group for Intelligent Computing in Engineering, Springer, 2006: pp. 1–6.
[6] Y.-S. Jeong, C.M. Eastman, R. Sacks, I. Kaner, Benchmark tests for BIM data exchanges of precast concrete, Automation in Construction. 18 (2009) 469–484.
[7] V. Moayeri, O. Moselhi, Z. Zhu, Design change management using a BIM-based visualization model, (2015).
[8] S. Daum, A. Borrmann, Enhanced differencing and merging of IFC data by processing spatial, semantic and relational model aspects, in: Proc. of the 23rd International Workshop of the European Group for Intelligent Computing in Engineering, 2016.
[9] X. Shi, Y.-S. Liu, G. Gao, M. Gu, H. Li, IFCdiff: A content-based automatic comparison approach for IFC files, Automation in Construction. 86 (2018) 53–68.
[10] S. Park, S. Ju, S. Yoon, M.H. Nguyen, J. Heo, An efficient data structure approach for BIM-to-point-cloud change detection using modifiable nested octree, Automation in Construction. 132 (2021) 103922.
[11] H. Tran, K. Khoshelham, Building change detection through comparison of a LIDAR scan with a Building Information Model., International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences. (2019).
[12] T. Meyer, A. Brunn, U. Stilla, Change detection for indoor construction progress 64 monitoring based on BIM, point clouds and uncertainties, Automation in Construction. 141 (2022) 104442. https://doi.org/10.1016/j.autcon.2022.104442.
[13] L. Ma, R. Sacks, R. Zeibak-Shini, S. Filin, A computational procedure for generating specimens of bim and point cloud data for building change detection, in: Congress on Computing in Civil Engineering, Proceedings, American Society of Civil Engineers (ASCE), 2015: pp. 684–691.
[14] J. Chen, Y.K. Cho, Point-to-point comparison method for automated scan-vs-bim deviation detection, in: Proceedings of the 2018 17th International Conference on Computing in Civil and Building Engineering, Tampere, Finland, 2018: pp. 5–7.
[15] F. Bosché, M. Ahmed, Y. Turkan, C.T. Haas, R. Haas, The value of integrating Scan-to-BIM and Scan-vs-BIM techniques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components, Automation in Construction. 49 (2015) 201–213.
[16] R.B. Rusu, N. Blodow, M. Beetz, Fast point feature histograms (FPFH) for 3D registration, in: 2009 IEEE International Conference on Robotics and Automation, IEEE, 2009: pp. 3212–3217.
[17] R.B. Rusu, Z.C. Marton, N. Blodow, M. Beetz, Learning informative point classes for the acquisition of object model maps, in: 2008 10th International Conference on Control, Automation, Robotics and Vision, IEEE, Hanoi, Vietnam, 2008: pp. 643–650. https://doi.org/10.1109/ICARCV.2008.4795593.
[18] D. Chetverikov, D. Svirko, D. Stepanov, P. Krsek, The trimmed iterative closest point algorithm, in: 2002 International Conference on Pattern Recognition, IEEE, 2002: pp. 545–548.
[19] K. Baker, Singular value decomposition tutorial, The Ohio State University. 24 (2005).
[20] Z. Yaniv, Random sample consensus (RANSAC) algorithm, a generic implementation, Imaging. (2010).
[21] T.-Y. Chuang, C.-C. Sung, Learning-guided point cloud vectorization for building component modeling, Automation in Construction. 132 (2021) 103978.
[22] T.-Y. Chuang, C.-C. Sung, Learning and SLAM based decision support platform for sewer inspection, Remote Sensing. 12 (2020) 968.
[23] C.R. Qi, H. Su, K. Mo, L.J. Guibas, Pointnet: Deep learning on point sets for 3d classification and segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: pp. 652–660.
[24] R.B. Rusu, S. Cousins, 3D is here: Point Cloud Library (PCL), in: 2011 IEEE International Conference on Robotics and Automation, 2011: pp. 1–4. https://doi.org/10.1109/ICRA.2011.5980567.
[25] Q.-Y. Zhou, J. Park, V. Koltun, Open3D: A modern library for 3D data processing, ArXiv Preprint ArXiv:1801.09847. (2018).