進階搜尋


 
系統識別號 U0026-2901201000380000
論文名稱(中文) 多尺度張量應用於3D點雲套合之研究
論文名稱(英文) 3D Point Cloud Registration Using Multi-scale Tensors
校院名稱 成功大學
系所名稱(中) 測量及空間資訊學系碩博士班
系所名稱(英) Department of Geomatics
學年度 98
學期 1
出版年 99
研究生(中文) 王名玉
研究生(英文) Ming-Yu Wang
學號 p6696410
學位類別 碩士
語文別 中文
論文頁數 84頁
口試委員 口試委員-張智安
口試委員-饒見有
指導教授-林昭宏
中文關鍵字 點雲特徵擷取  點雲套合  張量分析 
英文關鍵字 Point cloud feature extraction  point cloud registration  ensor analysis 
學科別分類
中文摘要 光達雷射掃瞄儀(Light Detection and Ranging, LiDAR)目前被普遍應用在各個領域中,例如:場景建模、古蹟復原、藝術保存與地表高程測量等,皆可運用光達快速且大量的空間資訊收集能力。在測量領域中常使用的光達分為空載式及地面式光達。使用空載光達掃瞄地表資訊時,由於掃瞄範圍寬闊,因而需要掃瞄多個航帶才能拼接出一個完整的地表資料;地面光達同樣需要設置多個測站掃瞄地表目標物,因此多測站之點雲資料套合是有其研究之必需與必要性。本論文以朝向自動化點雲套合演算法為目標,主要是利用多尺度張量投票法選取出位於高曲率之點雲特徵點,並進一步利用多尺度張量決定兩個測站之共軛特徵點。相對於以共軛特徵體、面或線為基礎的套合方法而言,本論文以單點特徵進行匹配提高了匹配全自動化之可能性,本研究以張量投票法其旋轉不變量之特性解決測站間旋轉角度差異問題,提出多尺度概念克服點雲測站間疏密度不同以及雜訊之影響,進而提高特徵點匹配穩定性。本研究先利用所找出之共軛特徵點進行六參數轉換,完成點雲資料初步套合,接著利用Iterative Closest Point(ICP)演算法提高套合精度,在此流程下達到自動化套合的目標。
英文摘要 LiDAR (Light Detection and Ranging) is an optical remote sensing technology that acquires spatial information. It has the ability of acquiring high-accuracy and high-resolution point clouds, and thus has received increasing attention and has become important surveying equipment with many applications such as urban/terrain modeling, 3D digital archiving, historic monument restoration and geography surveying. Therefore, register point clouds acquired from different scanning sites plays an important role in the aforementioned applications. In this paper, a toward automatic point cloud registration algorithm is proposed. The main ideas are to utilize a tensor voting approach to extract high-curvature feature points from point cloud, and adopt multi-scale tensors to match the extracted feature points. Compared to the previous registration approaches which are based on line, plane or object matching, the proposed approach has a good chance to fully automatic align two point clouds. It is because that the complex process of feature lines, planes or objects extraction is avoided. Compared to the approaches which are based on feature point matching, the proposed approach which is based on multi-scale tensors can significantly improve the matching accuracy.
After the extracted feature points are matched, to increase the registration precision, an iterative closest point (ICP) algorithm is adopted following a standard transformation optimization process.
論文目次 摘要 I
Abstract II
目錄 IV
表目錄 VI
圖目錄 VII
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
第二章 相關研究 6
2.1 共軛特徵之型態 6
2.2 特徵值計算方式 8
第三章 研究方法 13
3.1 三維網格化及特徵萃取 15
3.2 法向量計算 18
3.2.1 利用二為影像獲得法向量 18
3.2.2 利用張量計算獲得法向量 23
3.3 多尺度張量投票法 26
3.4 應用多尺度張量進行點特徵匹配 29
3.5 ICP演算法套合 33
第四章 研究成果 38
4.1 介紹模擬點雲資料的建立 38
4.2 旋轉角度對多尺度張量之影響 40
4.3 雜訊對多尺度張量及單一尺度張量之影響 49
4.4 測站點數不同對多尺度張量及單一尺度張量之影響 53
4.5 真實點雲資料套合成果展示 60
4.6 成果分析 73
第五章 結論與未來工作 81
第六章 參考文獻 83
參考文獻 Akca, D. (2003). Full automatic registration of laser scanner point clouds. Optical 3D Measurement Techniques VI: 330-337.
Alliez, P., Cohen-Steiner, D., Devillers, O., Levy, B. &Desbrun, M. (2003). Anisotropic polygonal remeshing. ACM Transactions on Graphics 22(3): 485-493.
Almhdie, A., Leger, C., Deriche, M. &Ledee, R. (2007). 3D registration using a new implementation of the ICP algorithm based on a comprehensive lookup matrix: Application to medical imaging. Pattern Recognition Letters 28(12): 1523-1533.
Arun, K., Huang, T. &Blostein, S. (1987). Least-squares fitting of two 3-D point sets. IEEE TRANS. PATTERN ANAL. MACH. INTELLIG. 9(5): 698-700.
Besl, P. &McKay, H. (1992). A method for registration of 3-D shapes. IEEE Transactions on pattern analysis and machine intelligence 14(2): 239-256.
Brown, B. &Rusinkiewicz, S. (2007). Global non-rigid alignment of 3-D scans. ACM Trans. Graph 26.
Castellani, U., Cristani, M., Fantoni, S. &Murino, V. (2008).Sparse points matching by combining 3D mesh saliency with statistical descriptors. In EuroGraphics, 27: 643-652: Blackwell Publishing.
Cohen-Steiner, D. &Morvan, J. (2003).Restricted delaunay triangulations and normal cycle. In Proceedings of the Ninteenth Annual Symposium on Computational Geometry, 312-321: ACM New York, NY, USA.
Gelfand, N., Ikemoto, L., Rusinkiewicz, S. &Levoy, M. (2003).Geometrically stable sampling for the ICP algorithm. In Proc. Fourth International Conference on 3D Digital Imaging and Modeling, 260-267.
Gruen, A. &Akca, D. (2005). Least squares 3D surface and curve matching. ISPRS Journal of Photogrammetry and Remote Sensing 59(3): 151-174.
Habib, A., Ghanma, M., Morgan, M. &Al-Ruzouq, R. (2005). Photogrammetric and LiDAR data registration using linear features. Photogrammetric Engineering and Remote Sensing 71(6): 699-707.
Horn, B. (1987). Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America A 4(4): 629-642.
Jaw, J.-J. &Chuang, T.-Y. (2008). Registration of Ground-based Lidar Point Clouds by Means of 3D Line Features. Journal of the Chinese Institute of Engineers 31: 15.
Kass, M., Witkin, A. &Terzopoulos, D. (1988). Snakes: Active contour models. International journal of computer vision 1(4): 321-331.
Lee, C., Varshney, A. &Jacobs, D. (2005). Mesh saliency. ACM Transactions on Graphics 24(3): 659-666.
Lowe, D. (1999).Object recognition from local scale-invariant features. In Proc. Seventh Int'l. Conf. Computer Vision, 2: 1150-1157.
Medioni, G., Lee, M. &Tang, C. (2000). A computational framework for segmentation and grouping. Elsevier Science.
Pauly, M., Gross, M. &Kobbelt, L. (2002).Efficient simplification of point-sampled surfaces. In Proc. of IEEE Visualization, 163-170.
Pauly, M., Keiser, R. &Gross, M. (2003).Multi-scale feature extraction on point-sampled surfaces. In Eurographics, 22: 281-289: Blackwell Publishing, Inc.
Rabbani, T., Dijkman, S., van den Heuvel, F. &Vosselman, G. (2007). An integrated approach for modelling and global registration of point clouds. ISPRS Journal of Photogrammetry and Remote Sensing 61(6): 355-370.
Rusinkiewicz, S. &Levoy, M. (2001).Efficient variants of the ICP algorithm. In Proc. Third International Conference on 3D Digital Imaging and Modeling, 145–152.
Schnabel, R., Wahl, R. &Klein, R. (2007).Efficient ransac for point-cloud shape detection. In Computer Graphics Forum, 26: 214-226: Blackwell Publishing.
Schuster, H. (2004). Segmentation of lidar data using the tensor voting framework. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 35: 1073-1078.
Taubin, G. (1995). Estimating the tensor of curvature of a surface from a polyhedral approximation. Proceedings of the Fifth International Conference on Computer Vision: 902-907.
Wolf, P. &Dewitt, B. (2000). Elements of Photogrammetry: with applications in GIS. McGraw-Hill New York.
You, R. &Lin, B. (2007).Building feature extraction from airborne lidar data using tensor voting algorithm. review.
王偉立 (2008). "光達點雲平面特徵自動化匹配與航帶平差之研究" 國立成功大學測量及空間資訊學系碩士論文.
陳英鴻 (2004). "光達點雲資料連結點匹配之研究" 國立成功大學測量及空間資訊學系碩士論文.
葉炘 (2008). "Tensor Voting演算法應用於光達數值地形結構線萃取之可行性研究" 國立成功大學測量及空間資訊學系碩士論文.
賴志恆 (2003). "雷射掃瞄點雲資料八分樹結構化之研究" 國立成功大學測量與空間資訊學系研究所碩士論文.
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2010-02-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2010-02-01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