近幾年，三維虛擬實境應用於網路遊戲與網路社群之風行，三維模型重建技術逐漸成為相當受到重視的課題。因此，本論文希望提出一套完整流程，在增加重建精確度以及方便性的前提下，從靜態彩色物件之多重影像中自動提取所需的三維資訊，重建出具紋理的三維模型。
三維模型重建的流程包括，取得相機的內部參數後，用KLT演算法從影像序列中篩選不同角度的影像，再經由多校正板之間的連結性，解決特徵點被遮蔽的問題並取得校正參數。利用RANSAC取得適當的特徵匹配點，從相鄰影像的平面轉移矩陣資訊，將物件從多塊校正板和背景中分離切割。從實驗結果顯示我們可成功重建正確三維模型及其表面紋理。

Due to applications of virtual reality in on-line games and social networking, the 3D model reconstruction becomes an important topic in recent years. In this thesis, in order to increase the accuracy of reconstruction and the premise of convenience, we propose a system which automatically extracts the 3D information and reconstructs a textured 3D model from multiple images of a static color object.
For the 3D model reconstruction, the calibration of the camera intrinsic parameters should be conducted first. Then, we select the images from different angles by Kanade-Lucas-Tomasi (KLT) algorithm and use the link between multiple calibration boards to solve the problem of covered feature points and finally to estimate the camera parameters. After filtering out incorrect feature points by RANSAC method, the homography matrix of adjacent images can be computed. By homography matrix and background subtraction technique, we can separate the object of multiple calibration boards and segment it from background. To verify the proposed reconstruction procedure, the experiments show that we can successfully estimate the 3D model reconstruction and surface texture mapping.

[1]K. Forbes, A. Voight, and N. Bodika, ”An inexpensive automatic and accurate camera calibration method,” in Proceedings of the Thirteenth Annual Symposium of the Pattern Recognition Association of South Africa, Langebaan, South Africa, Nov. 2002, pp. 100-106 .

[2]V. Douskos, I. Kalisperakis, and G. Karras ”Automatic calibration of digital cameras using planar chess-board patterns,” in Proceedings of the 8th Conference on Optical 3-D Measurement Techniques, ETH Zurich, Switzerland, July 2007, pp. 132–140.

[3]Z. Zhang, “A flexible new technique for camera calibration,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.1330–1334, Dec. 2000.

[4]L. Wang, W. Tsai, “Camera calibration by vanishing lines for 3-D computer vision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vo1. 13, pp. 370-376, Apr. 1991.

[5]K. Y. K. Wong and R. Cipolla, “Reconstruction of sculpture from its profiles with unknown camera positions,” IEEE Transactions Image Processing, vol. 13, pp. 381-389, Mar. 2004.

[6]K. Y. K. Wong, P. R. S. Mendonca, and R. Cipolla, “Camera calibration from surfaces of revolution,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 147–161, Feb. 2003.

[7]H. Zhang, K.-Y. K. Wong, “Self-Calibration of Turntable Sequences from Silhouettes”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, pp. 5-14, 2009.

[8]S. J. Ahn, W. Rauh, and S. I. Kim, “Circular coded target for automation of optical and 3D-measurement camera calibration,” International Journal of Pattern Recognition and Artificial Intelligence, vol.15, pp. 905-919, 2001.

[9]C. Shu, Brunton, and M. AFiala, “Automatic grid finding in calibration patterns using delaunay triangulation,” Technical Report NRC-46497/ERB-1104; National Research Council, Institute for Information Technology: Ottawa, Ontario, Canada, 2003.

[10]A. Laurentini, “The Visual Hull Concept for Silhouette Based Image Understanding,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.16, pp. 150-162, Feb. 1994.

[11]W. Matusik, ”Image based visual hulls,” Master of Science Thesis, MIT, 2001.

[12]K. N. Kutulakos, and S. M. Seitz, ” A theory of shape by space carving”, in Proceedings of the 7th IEEE International Conference on Computer Vision, 1999, pp. 307- 314.

[13]S. Srivastava, and N. Ahuja, “Octree generation from object silhouettes in perspective views,” Computer Vision, Graphics, and Image Processing, vol. 49, pp. 68-84, Jan. 1990.

[14]R. Klette, K. Schluns, adn A. Koschan, “Computer vision three-dimensional data from images,” Springer Publishing, Aug. 1980, pp. 148-149.

[15]S. Birchfield, “Derivation of Kanade-Lucas-Tomasi tracking equation,” http://www.ces.clemson.edu/~stb/klt/birchfield-klt-derivation.pdf.

[16]D. Lowe, “Distinctive image features from scale-invariant keypoints,” Journal of Computer Vision, vol. 60, pp. 91-110, Nov. 2004.

[17]M. A. Fischler, and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the Association for Computing Machinery, vol. 24, pp. 381-395, 1981.

[18]A. O. Balan, “Voxel carving and coloring –constructing a 3D model an object from 2D images,” Brown University, Providence RI, December 2003.

[19]J. Bloomenthal, “Polygonization of Implicit Surfaces,” Computer Aided Geometric Design, pp. 341-355, Nov. 1988.

[20]A. Y. Mülayim, U. Yilmaz, and V. Atalay, “Silhouette-based 3-D model reconstruction from multiple images,” IEEE Transactions System, Man, Cybernetics B, vol. 33, pp. 582-591, Aug. 2003.

[21]M. PollefeysH, and HS. N. SinhaH, “Multi-View reconstruction using photo-consistency and exact silhouette constraints: a maximum-flow formulation,” in Proceedings of IEEE International Conference on Computer Vision, 2005, pp. 349-356.

[22]Z. Zhang , R. Deriche , O. Faugeras , and Q. T. Luong, “A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the unknown Epipolar Geometry,” Artificial Intelligence Journal,vol . 78, pp. 87-119, Oct. 1995.