論文顯示區塊
論文名稱:使用轉角偵測與虛擬網格法重建三維模型
3D Object Model Recovery from 2D Images Utilizing Corner Detection and Virtual Mesh Grid
研究生:黃盈源 Ying-Yuan Huang
指導教授:陳美勇 Mei-Yung Chen
    學位類別:碩士(Master)
    學校名稱:國立臺灣師範大學
    記錄編號:GN0698730231
系所名稱:機電科技研究所
畢業學年度:99
      語文別:中文
關鍵字:三維重建 3D reconstruction
立體視覺法 Stereo vision
轉角偵測 Corner detection
虛擬網格 Virtual mesh grid
全文說明:電子全文
    論文頁數:80
摘要:本研究主要之研究目標為使用二維影像重建三維物件模型。一般研究上所使用的方法為非接觸式系統中的立體視覺法，此方法模擬人類雙眼感知影像進而推算物體與雙眼間之深度，因此系統需要使用兩隻攝影機進行影像的擷取，擷取後的兩張影像進行匹配找出現實空間中一點分別投影至二維影像的投影點，之後利用現實空間與相機座標系統彼此間的幾何轉換關係，藉由兩張影像上的投影點計算出此一點於現實空間中之深度資訊，如此一來即可重建出物體的三維模型。然而立體視覺法中困難之處在於如何從左右兩影像準確地找出相對應的投影點進行深度計算，因此針對此問題在過去的研究提出從外部投影一結構光至物件表面，藉由結構光協助系統定位左右兩影像中相對應的投影點，然而此法受限於物體表面之顏色。故本研究提出之三維重建方法無須藉由投影結構光即可重建出物件之三維模型，針對簡單幾何物件以及曲面物件分別使用轉角偵測以及虛擬網格協助系統定義左右兩影像中相對應的投影點重建出物件之三維模型，簡單幾何物件之特徵點通常出現於輪廓之轉角處，因此系統透過轉角偵測找出左右兩影像中物件輪廓之特徵點，藉由立體視覺法重建起特徵點之深度資訊將特徵點重建至三維座標空間中，再根據重建之特徵點還原出物件之三維模型。在另一方面，由於曲面物件不同於簡單幾何物件在轉角處有明顯之特徵點，因此本研究先於左物件影像建立起虛擬網格，藉由極線幾何原理估測曲面物件左右兩影像中相對應的投影點，於右物件影像建立起相對應的虛擬網格，根據左右兩物件影像之虛擬網格以立體視覺法成功地重建出曲面物件之三維模型。
This research proposes a new method to reconstruct the 3D object model from 2D images. One type of the non-contact scanning measurement for the stereo vision algorithm is used in this research. The stereo vision simulates human’s eyes to capture the depth information of the object. Therefore, this research uses two CCD Cameras to capture two images of the object. Then, find out the match points from the two images. Using the match points and combine 1)the parameters of the two CCD Cameras and 2)transform matrix between the world coordinate and camera coordinate to get the depth information of each point in the space. Finally, the object’s 3D model can be reconstructed. The important issue of the stereo vision theorem is how to find out the match points from the two images accurate. For solving this issue in the past researches, many articles used a projected structure light on the object’s surfaces to measure the match points. In this research, the proposed system is able to find out the match points from the two images by the structure light. But this method will be restricted by the color of the object surface. This research proposes a method to reconstruct the 3D model without projecting the structure light. The system uses corner detection and virtual mesh grid to reconstruct the simple geometry and curved the surface of object. The feature points of the simple geometry object are usually on the corner of the contour. So we can find out the feature points by doing the corner detection, and then the system would calculate the depth of the feature points to project the feature points in the 3D coordinated space. And then, the simple geometry object’s 3D model would be reconstructed from these feature points. But the curved surface object doesn’t have the visible feature points, therefore, this paper build up the virtual mesh grid from the left image. Then, the system would estimate the match points by the epipolar geometry theorem and builds up the virtual mesh grid on the right image. Finally system reconstructs the 3D model by the stereo vision theorem and virtual mesh grid of the two images successfully.
    論文目次:摘要.......................................................Ⅰ
Abstrcat.................................................. Ⅱ
誌謝.......................................................IV
目錄........................................................V
圖目錄.....................................................Ⅶ
表目錄.....................................................Ⅹ
第一章 緒論.................................................1
1.1前言..........................................................1
1.2文獻回顧..........................................................7
1.3研究動機與目的..........................................10
1.4本論文之貢獻............................................12
1.5論文架構................................................12
第二章 理論基礎............................................13
2.1數位影像基本定義........................................13
2.2鄰域處理................................................14
2.3影像邊緣偵測(Edge detection)............................16
  2.3.1 Canny邊緣偵測.....................................18
2.4影像二值化..............................................18
2.5形態學影像處理(morphology)..............................19
      2.5.1膨脹(Dilation)與侵蝕(Erosion)...................20
2.6轉角偵測(corner detection)..............................22
  2.6.1Harris 轉角偵測....................................23
2.7 透視投影法.............................................23
2.8 立體視覺法(Stereo vision)..............................25
2.9 Fundamental matrix.....................................26
第三章 系統設計概念與配置..................................29
3.1三維重建系統設計實現目標................................29
3.2三維重建系統架構........................................29
3.3三維重建系統架設概念....................................30
3.4三維重建系統配置........................................30
3.5本重建系統之特色........................................33
3.5重建系統流程描述........................................33
第四章 三維模型重建系統設計原理............................35
4.1系統前處理..............................................35
4.2影像前處理..............................................36
4.3搜尋match points........................................38
4.3.1epipolar line.........................................38
4.3.2簡單幾何物件搜尋match point...........................39
4.3.3曲面物件搜尋match point...............................42
4.4建立虛擬三維空間座標....................................50
4.5重建三維模型............................................53
4.6結合運動模型............................................54
第五章 實驗結果與討論......................................56
5.1系統設備描述.........................................................56
5.2三維模型重建系統架設操作流程............................58
5.3三維模型重建流程........................................59
5.3.1相機參數與求解Fundamental matrix......................59
5.3.2重建簡單之幾何物件....................................62
5.3.3重建曲面物件..........................................67
5.4三維模型重建結果分析....................................72
第六章 結論及未來展望......................................76
參考文獻...................................................77
    參考文獻:[1]    Q. Zhao, D. Zhang, L. Zhang and N. Luo, “High resolution partial fingerprint alignment using pore–valley descriptors,” Pattern Recognition, vol. 43, pp. 1050-1061, March 2010.
[2]    C. N. E. Anagnostopoulos, V. Loumos and E. Kayafas, “License Plate Recognition From Still Images and Video Sequences: A Survey,” IEEE, Transactions on Intelligent Transportation Systems, vol. 9, pp. 377-391, September 2008.
[3]    J. Y. Choi, Y. M. Ro and K. N. Plataniotis,“Boosting Color Feature Selection for Color Face Recognition,”IEEE, Transactions on Image Processing, vol. 20, pp. 1425-1434, May 2011.
[4]    W. Wei, G. Wang and H. Chen, “3D reconstruction of a femur shaft using a model and two 2D X-ray images, ” IEEE, International Conference on Computer Science & Education, pp. 720-722, 2009.
[5]    P. Gamage, S. Q. Xie , P. Delmas, P. Xu, “ 3D reconstruction of patient specific bone models from 2D radiographs for image guided orthopedic surgery, ” IEEE, 2009 Digital Image Computing: Techniques and Applications, pp. 212 – 216, 2009.
[6]    M.J. Clarkson, D. Rueckert, D.L.G. Hill and D.J. Hawkes, “ Using photo-consistency to register 2D optical images of the human face to a 3D surface model, ” IEEE, Transactions on pattern analysis and machine intelligence, vol. 23, no. 11, pp. 1266 -1280, 2001.
[7]    T. Hassner and R. Basri, “ Example based 3D reconstruction from single 2D images, ” IEEE, Computer vision and pattern recognition workshop, pp. 15 -15, 2006.
[8]    M. Strand and R. Dillmann, “ Using an attributed 2D-grid for next-best-view planning on 3D environment data for an autonomous robot, ” IEEE, International conference on information and automation, pp. 314-319, 2008.
[9]    G. M. Bone, A. Lambert and M. Edwards, “Automated Modeling and Robotic Grasping of Unknown Three-Dimensional Objects,” IEEE International Conference on Robotics and Automation Pasadena, pp. 292-298, May 2008.
[10]    T. Tasic and B. Acko,“Integration of a laser interferometer and a CMM into a measurement system for measuring internal dimensions”Measurement, vol. 44, pp. 426-433, February 2011.
[11]    M. Strand and R. Dillmann, “Using an attributed 2D-grid for next-best-view planning on 3D environment data for an autonomous robot,” IEEE, International Conference on Information and Automation, pp. 314-319, June 2008.
[12]    M. Kimura and H. Saito, “3D reconstruction based on epipolar geometry,” IEICE, Transactions on Information and Systems, pp. 1690-1697, 2001.
[13]    S. Prakoonwit and R. Benjamin, “Optimal 3D surface reconstruction from multiview photographic images,” International Conference on Cyber Worlds, pp. 126-131, Sep 2009.
[14]    R. T. Frankot and R. Chellappa, “A Method for Enforcing Integrability in Shape from Shading Algorithms,” IEEE, Transactions on Pattern Analysis and Machine Intelligence, vol. 10, pp. 439-451, Jul 1988.
[15]    D.G. Aliaga and Y. Xu, “A Self-Calibrating Method for Photogeometric Acquisition of 3D Objects,” IEEE, Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 747-754, April 2010.
[16]    P. Lavoie, D. Ionescu and E.M. Petriu,“3-D Object Model Recovery From 2-D Images Using Structured Light,”IEEE, Transactions on Instrumentation and Measurement, vol. 53 pp. 377- 382, 2004.
[17]    L.M. Song and D.N. Wang, “A novel grating matching method for 3D reconstruction,” NDT & E International, vol. 39, pp. 282-288, Jun 2006.
[18]    J. D. Zheng, L. Y. Zhang, X. Y. Du and Z. A. Ding, “3D curve structure reconstruction from a sparse set of unordered images,”Computers in Industry, vol. 60, pp. 126-134, Feb 2009.
[19]    J. Canny, “A computational approach to edge detection, ” IEEE, Transaction on Pattern Analysis and Machine Intelligence, vol. PAMI-8, pp. 679-698, Nov 1986.
[20]    C. Harris and M. Stephens, “A combined corner and edge detector, ” Alvey Vision Conference, pp. 147-152, 1988.
[21]    Z. Wang and B. Boufama, “Using stereo geometry towards accurate 3D reconstruction, ” IEEE International Conference on Electro/Information Technology, pp. 134-140, June 2009.
[22]    G. L. Mariottini and D. Prattichizzo, “EGT for multiple view geometry and visual servoing: robotics vision with pinhole and panoramic cameras, ”IEEE, Robotics & Automation Magazine, vol. 12, pp. 26-39, Dec 2005.
[23]    P. K. Ho and R. Chung, “Stereo-motion with stereo and motion in complement, ” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 215-220, Feb 2000.
[24]    洪維恩 編著，「Matlab 7 程式設計」，旗標出版股份有限公司，中華民國95年。
[25]    繆紹綱 編著，「數位影像處理：運用matlab」，台灣東華書局股份有限公司，中華民國94年。
[26]    http://www.vision.caltech.edu/bouguetj/calib_doc/index.html---2010.07.09