進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1608201810485700
論文名稱(中文) 由散亂點雲自動辨識結構基本物件–辨識率與精確度
論文名稱(英文) Structural Element Recognition Directly from Scattered Point Cloud Data – Recognition Rate and Dimension Accuracy
校院名稱 成功大學
系所名稱(中) 土木工程學系
系所名稱(英) Department of Civil Engineering
學年度 106
學期 2
出版年 107
研究生(中文) 吳承晏
研究生(英文) Cheng-Yan Wu
學號 N66054475
學位類別 碩士
語文別 中文
論文頁數 75頁
口試委員 口試委員-黃忠信
口試委員-王雲哲
口試委員-蘇育民
指導教授-侯琮欽
中文關鍵字 三維雷射掃描  點雲資料  點雲模型建立  邊界提取演算法  資料分群演算法  物件辨識  辨識率  精確度 
英文關鍵字 laser scanning  point cloud data  model reconstruction  boundary extraction algorithm  clustering algorithm  object recognition  recognition rate  dimension accuracy 
學科別分類
中文摘要 近年來結構物三維模型成為能夠進行資料保存、結構分析及結構健康檢測之重要儲存形式,隨著三維雷射掃描(laser scanning)技術進步,應用掃描取得之點雲資料(point cloud data, PCD)重建三維模型(reconstruction)之相關研究成為重要的研究方向,然龐大且散亂之點雲資料多以費工又耗時之人工方式進行處理,因此本研究提出一套半自動化提取點雲特徵及辨識結構物件之演算流程,降低點雲模型重建時之時間與人力成本。本研究核心步驟可分為兩個部分:第一部分為自動化點雲邊界特徵提取及分群,使用Sun邊界提取演算法及Bazazian邊界提取演算法對結構物件進行邊界提取,再以具噪密度基礎分群法(DBSCAN)及交角分群法對邊界特徵點雲進行資料分群,取得分析成果並選擇較適用之演算法進行演算;第二部分為半自動化物件辨識,建立一套半自動化演算邏輯與流程,對第一部分所得成果進行誤差修正,再提出結構物件之判定邏輯與演算,分析其辨識率(recognition rate)及精確度(dimension accuracy)表現。由本研究所得之成果可得知,使用Bazazian邊界提取演算法及具噪密度基礎分群法能取得較佳之邊界提取與資料分群成果,演算時間較短且不易受雜訊影響產生誤差;半自動化物件辨識後取得80%以上之邊界特徵辨識率及100%完全準確之結構物件辨識率,結構物之物理三維資訊及斷面資訊精確度平均達95%,顯示本研究所提出之演算法具一定可信度與正確性,能夠快速且有效率地取得高辨識率及高精確度之成果。
英文摘要 In recent years, three-dimensional model of structures has become as the most important way for information storage, structural analysis and structural health monitoring. With the progress of laser scanning, reconstruction from point cloud data is a major field of study. However, the most process for huge and unorganized point clouds works manually, it takes much time and consume a lot of manpower. Therefore, this study establishes a process of semi-automatic extraction of boundary characteristic point cloud and structural object recognition. This study is divided into two major topics, namely “Automatic extraction and clustering of boundary characteristic point cloud” and “Semi-automatic structural object recognition”. The first theme applies boundary extraction algorithms and data clustering algorithms to point cloud data of structures, then compare each results of algorithms to find the most suitable algorithm for analysis; The second theme proposed semi-automatic process and logic of structural object recognition. It contains error correction of the result of the first theme and establish the object recognition logic and process, then calculates the recognition rate and dimension accuracy. The results showed that applying boundary extraction algorithms from Bazazian and density-based spatial clustering as data clustering algorithms can take less time and produce fewer errors from noise of point cloud data. The recognition rate of boundary lines and structural objects are respectively 80% and 100% on average, and the dimension accuracy is 95% on average. This study obtains good performance with reliability and efficiency because of high recognition rate and dimension accuracy.
論文目次 摘要 III
目錄 XIV
圖目錄 XVII
表目錄 XIX
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究內容 2
1.3 研究流程 3
第二章 文獻回顧 4
2.1 三維雷射掃描儀系統 4
2.1.1 雷射掃描儀種類 4
2.1.2 光達掃描測距 7
2.1.3 光達掃描定位 9
2.1.4 座標轉換 10
2.1.5 點雲結合 11
2.1.6 本研究使用之儀器及軟體資源 12
2.2 結構物點雲模型建立 14
2.2.1 邊界特徵點雲提取 15
2.2.2 點雲資料分群 16
2.2.3 結構物件辨識 17
第三章 數據演算方法 19
3.1 自動化點雲邊界特徵提取及分群 22
3.1.1 邊界特徵點雲提取演算法 22
3.1.1.1 kd-tree 22
3.1.1.2 主成分分析法 26
3.1.1.3 Sun邊界提取演算法 27
3.1.1.4 Bazazian邊界提取演算法 28
3.1.2 資料分群演算法 30
3.1.2.1 最小二乘法(least mean square, LMS) 30
3.1.2.2 具噪密度基礎分群法(DBSCAN) 31
3.1.2.3 交角分群法 32
3.2 半自動化物件辨識 33
3.2.1 半自動化誤差修正 33
3.2.1.1 適應性網格 33
3.2.1.2 半自動化誤差修正 35
3.2.2 結構物件辨識 36
第四章 演算成果分析 38
4.1 自動化點雲邊界特徵提取及分群成果 41
4.1.1 邊界特徵點雲提取 41
4.1.2 邊界點雲分群 46
4.2 半自動化物件辨識成果 50
4.2.1 半自動化誤差修正 54
4.2.2 結構物件辨識率 57
4.2.3 結構物資訊精確度 61
第五章 結論與建議 67
5.1 結論 67
5.2 建議 68
參考文獻 70
參考文獻 [1]. 王鵬圖(2016),「以空間點雲進行鋼筋混凝土梁構件之一維擬合」,國立成功大學土木工程研究所碩士論文。
[2]. 吳天佑(2016),「以空間點雲進行鋼筋混凝土版結構之二維擬合」,國立成功大學土木工程研究所碩士論文。
[3]. 林耿帆、徐百輝(2015),「以物件為基礎之光達點雲分類」,國立臺灣大學土木工程學研究所碩士論文。
[4]. 侯琮欽、蔡家修、劉任偉(2016),「地面雷射掃描於震後災損勘查之應用初探」,地工技術,148,81-90。
[5]. 侯琮欽(2016),「軌道線形變化與沉陷檢測」,中聯資源計畫編號104S193結案報告。
[6]. 劉任偉(2015),「點雲分群與邊界提取辨識建物損傷及變形」,國立成功大學土木工程研究所碩士論文。
[7]. 劉昱緯(2015),「地面雷射掃描於結構幾何辨識與損傷檢測之應用」,國立成功大學土木工程研究所碩士論文。
[8]. 蔡家修(2016),「點雲分析應用於物件辨識與地震災後勘查」,國立成功大學土木工程研究所碩士論文。
[9]. 羅仕東,2011,「整合八分樹結構與適應性網格於光達資料重建室內建物三維模型之研究」,國立中央大學土木工程研究所碩士論文。
[10]. A. Pesci, G.Teza, E. Bonali, G. Casula, E. Boschi, 2013,A laser scanning-based method for fast estimation of seismic-induced building deformations. ISPRS J. Photogrammetry Remote Sensing, 79 (2013), pp. 185-198.
[11]. Armesto-González, J., Riveiro-Rodríguez, B., González-Aguilera, D., Rivas-Brea, M. T., 2010, Terrestrial laser scanning intensity data applied to damage detection for historical buildings. Journal of Archaeological Science, 37(12): p. 3037-3047.
[12]. A. Baik,2017, From point cloud to jeddah heritage BIM nasif historical house–case study. Digital Applications in Archaeology and Cultural Heritage4, 1–18.
[13]. Ariyasu, E., Koizumi, M., Ikubo, M., Hatake, S., 2012, Application of Mobile LIDAR Mapping for Damage Survey after Great East Japan Earthquake. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, p. 573-576.
[14]. Al-Kheder, S., Al-Shawabkeh, Y., Haala, N., 2009, Developing a documentation system for desert palaces in Jordan using 3D laser scanning and digital photogrammetry. Journal of Archaeological Science, 36(2): p. 537-546.
[15]. Barazzetti, L, 2016, Parametric as-built model generation of complex shapes from point clouds. Advanced Engineering Informatics, 30(3), 298-311.
[16]. Bazazian, D., Casas, J. R., & Ruiz-Hidalgo, J., 2015, Fast and robust edge extraction in unorganized point clouds. In Digital Image Computing: Techniques and Applications (DICTA), 2015 International Conference on (pp. 1-8). IEEE.
[17]. Beckmann, N., Kriegel, H. P., Schneider, R., & Seeger, B., 1990, The R*-tree: an efficient and robust access method for points and rectangles. In Acm Sigmod Record (Vol. 19, No. 2, pp. 322-331). Acm.
[18]. Bentley, J. L., 1975, Multidimensional binary search trees used for associative searching. Communications of the ACM, 18(9), 509-517.
[19]. Biosca, J. M., & Lerma, J. L. (2008). Unsupervised robust planar segmentation of terrestrial laser scanner point clouds based on fuzzy clustering methods. ISPRS Journal of Photogrammetry and Remote Sensing, 63(1), 84-98.
[20]. Bloch, T., Sacks, R., & Rabinovitch, O., 2016, Interior models of earthquake damaged buildings for search and rescue. Advanced Engineering Informatics, 30(1), 65-76.
[21]. Bizjak, M, 2015, 3D Reconstruction of Buildings from LiDAR Data. In The 19th Central European Seminar on Computer Graphics.
[22]. Crespo, C., Armesto, J., González-Aguilera, D., Arias, P., 2010, Damage detection on historical buildings using unsupervised classification techniques. Internation Archives of Photogrammetry.
[23]. Chen, J., Fang, Y., & Cho, Y. K. Unsupervised Recognition of Volumetric Structural Components from Building Point Clouds. In Computing in Civil Engineering 2017 (pp. 34-42).
[24]. Ester, M., Kriegel, H. P., Sander, J., Xu, X., 1996, A density-based algorithm for discovering clusters in large spatial databases with noise. in Kdd.
[25]. Farid, R., & Sammut, C., 2012, July, A relational approach to plane-based object categorization. In Robotics Science and Systems Workshop on RGB-D Cameras.
[26]. Fang, T. P., & Piegl, L. A., 1995, Delaunay triangulation in three dimensions. IEEE Computer Graphics and Applications, 15(5), 62-69.
[27]. González-Aguilera, D., Gómez-Lahoz, J., Sánchez, J., 2008, A new approach for structural monitoring of large dams with a three-dimensional laser scanner. Sensors, 8(9): p. 5866-5883.
[28]. Gonzalez-Aguilera, D., Gomez-Lahoz, J., Munoz-Nieto, A., Herrero-Pascual, J., 2008, Monitoring the health of an emblematic monument from terrestrial laser scanner. Nondestructive Testing and Evaluation, 23(4): p. 301-315.
[29]. González-Jorge, H., Gonzalez-Aguilera, D., Rodriguez-Gonzalvez, P., Arias, P., 2012, Monitoring biological crusts in civil engineering structures using intensity data from terrestrial laser scanners. Construction and Building Materials, 31: p. 119-128.
[30]. H.S. Park, H.M. Lee, H. Adeli, I. Lee, 2007, A new approach for health monitoring of structures: terrestrial laser scanning. Computer-Aided Civil and Infrastructure Engineering, 22 (1) , pp. 19-30.
[31]. Jennifer, W., 2013, Using LiDAR to Assess Storm Damage Caused by Hurricane Sandy. LiDAR Magazine, 3(2).
[32]. Ke, Y. L., Shan, D. R., 2005, Edge-based segmentation of point cloud data. Zhejiang Daxue Xuebao(Gongxue Ban)/Journal of Zhejiang University(Engineering Science), 9(3): p. 377-380.
[33]. Lambers, K., Eisenbeiss, H., Sauerbier, M., Kupferschmidt, D., Gaisecker, T., Sotoodeh, S., Hanusch, T., 2007, Combining photogrammetry and laser scanning for the recording and modelling of the Late Intermediate Period site of Pinchango Alto, Palpa, Peru. Journal of archaeological science, 34(10): p. 1702-1712.
[34]. Li, J. X., 2000, A Method for Extract Boundary of Complex Surface in Reverse Engineering. Machine Design and Manufacturing Engineering.
[35]. Lin, J. B., Zhou, M. Q., & Wu, Z. K., 2013, Smooth edge feature lines extraction from point clouds of eroded fractured fragments. In Advanced Materials Research (Vol. 756, pp. 4026-4030). Trans Tech Publications.
[36]. Mills, J., & Barber, D., 2004, Geomatics techniques for structural surveying. Journal of Surveying Engineering, 130(2), 56-64
[37]. Moertini, V, 2002, Introduction to five data clustering algorithm. Integral, 7(2), 87-96.
[38]. Pearson, K., 1901, Principal components analysis. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 6(2), 559.
[39]. Rusu, R. B., Marton, Z. C., Blodow, N., Dolha, M., & Beetz, M, 2008, Towards 3D point cloud based object maps for household environments. Robotics and Autonomous Systems, 56(11), 927-941.
[40]. Sun, D. Z., Zhu, C. Z., Li, Y. R., 2009, An improved extraction of boundary characteristic from scattered data. Journal of Shandong University (Engineering Science), 1: p. 014.
[41]. Tang, P., Huber, D., Akinci, B., Lipman, R., & Lytle, A., 2010, Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniques. Automation in construction, 19(7), 829-843.
[42]. Wu Z. , Heikkinen V., Hauta-Kasari M., Parkkinen J., Tokola T., 2014 ALS data based forest stand delineation with a coarse-to-fine segmentation approach. In IEEE International Congress on Image and Signal Processing (CISP), pp. 547–552.
[43]. Wehr A, Lohr U ,1999, Airborne laser scanning–an introduction and overview. ISPRS J Photogrammetry and Remote Sensing 54:68–82.
[44]. Walsh, S. B., Borello, D. J., Guldur, B., & Hajjar, J. F., 2013, Data processing of point clouds for object detection for structural engineering applications. Computer‐Aided Civil and Infrastructure Engineering, 28(7), 495-508.
[45]. Weber, C., Hahmann, S., & Hagen, H., 2010, June, Sharp feature detection in point clouds. In Shape Modeling International Conference (SMI), 2010 (pp. 175-186). IEEE.
[46]. Wang, C., Cho, Y. K., & Kim, C., 2015, Automatic BIM component extraction from point clouds of existing buildings for sustainability applications. Automation in Construction, 56, 1-13.
[47]. Zeibak-Shini, R., Sacks, R., Ma, L., & Filin, S., 2016, Towards generation of as-damaged BIM models using laser-scanning and as-built BIM: First estimate of as-damaged locations of reinforced concrete frame members in masonry infill structures. Advanced Engineering Informatics, 30(3), 312-326.
[48]. Zhang, X. Y., Zhou, M. Q., Geng, G. H., 2003, A Method of Detecting the Edge of Triangular Mesh Surface. Journal of Image and Graphics, 10: p. 022.
[49]. 中興測量有限公司,光達技術。Retrieved December 2016, from http://www.chsurvey.com.tw/page04.html
[50]. 汪群超,2006,「主成份分析的原理 」from http://web.ntpu.edu.tw/~ccw/statmath/M_pca.pdf
[51]. Fraunhofer IOSB, Change Detection in Urban Area. Retrieved December 2016, from http://www.iosb.fraunhofer.de/
[52]. Ioannis, T., 2015, March 6. The 5 most viewed terrestrial Laser Scanners on Geo-matching. GISBlog, Retrieved December 2016, from www.gisblog.com
[53]. Leica Geosystems, Retrieved December 2016, from http://hds.leica-geosystems.com/en/index.htm
[54]. TopScan, Mobile Laser Scanning. Retrieved December 2016, from http://www.topscan.de/
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-08-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2023-08-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw