在三維物體重建中，若能掌握其外型、邊界，重建後的資訊才會有應用的價值。重建策略為利用兩張平面影像去量測特徵點三維資料，期望能得到快速且精確的結果。常見的方式為利用雙眼架構，在左右影像中搜尋比對相同特徵點，再利用攝影機校正參數推得特徵點的空間座標。其中，必須進行的對應點比對為重建過程中最困難的問題，在物件相互遮掩、鏡面反射、透視投影形變及不同攝影機對亮度的敏感度不同等因素影響下，使得重建系統更容易產生出許多不正確的對應。
　　本文的主要目的為發展單眼模擬雙眼立體視覺系統的三維影像重建理論，並將其應用到逆向工程。提出一個新的方法來將雙眼視覺對應成單眼視覺，對物件做不同角度的取像，以取得完整的量測資料，並建立出特徵對應矩陣簡化特徵搜尋過程。為求增加系統強健性，利用交越相關性來減少近似的對應點，以增加對應點的正確性。最後使用透視投射法求得其三維空間座標，透過資料座標整併、平滑化構成點雲資料。運用曲面擬合技術，以插補法或近似法所建構的曲面來建構三維實體。
　　經由實驗驗證，本文提出的方法，能有效解決特徵點對應的問題，在三維物體重建上具有不錯的成果及應用潛力。

　　In three dimensional object reconstructions, if the feature of its shape and corresponding edges can be extracted, the coordinate information can then be obtained in a efficient manner and the data will be useful to further applications. A non-touching approach to obtain three dimensional coordinate information of an object is to utilize Laser measurement system. The use of two images provided by the so called binocular vision mechanism with CCD cameras can also be applied. Through searching and comparing procedures, the projection images of interesting points can be correlated properly. The coordinate information then can be determined by calibrated camera parameters and coordinate transformation matrix. The success of this reconstruction procedure strongly depends on influences of cross coverage of object parts, perspective projection deformation and luminance sensitivity.
　　In this dissertation, a virtual binocular vision system, which was composed of a CCD camera and a spin platform, is proposed to obtain three dimensional information of an object. In associated with a CAD software, say CATIA or Pro-E, a solid model can be reconstructed accurately and efficiently. The results showed that feature correlation can be processed successfully by the proposed fundamental matrix of the virtual binocular vision system. It has good potentiality to three dimensional object reconstructions.

Altschuler, M. D., and Posdamer, J. L. , 1982, Surface Measurement by Space-encoded Projected Beam Systems, Computer Graphics and Image Processing, 18, 1-17.

Arun, K. S., Huang, T. S., and Blostein, S. D. , 1987, Least-Squares Fitting of Two 3-D Point Sets, IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(5), 698-700.

Beeker, E. , 1986, Smoothing of Shapes Designed with Free-form Surfaces, Computer-Aided Design, 18(4), 224-232.

Benjemaa, R., and Schmitt, F. , 1997, Fast Global Registration of 3D Sample Surfaces Using a Multi-Z-Buffer Technique, Proceeding of International Conference on 3-D Digital Imaging and Modeling, 113-120.

Besl, P. J., and McKay, D. , 1992, A Method for Registration of 3-D Shapes, IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239-256.

Chen, C. S., Hung, Y. P., Cheng, J. B., and Ouhyoung, M., 1997, Registration and Integration of Multi-view Range Images, Conference on Computer Vision, Graphics and Image Processing, 376-383.

Chen, C. S., Hung, Y. P., and Cheng, J. B. , 1998, A Fast Automatic Method for Registration of Partially-Overlapping Range Images, Proceeding of International Conference on Computer Vision, 242-248.

Chen, Y., and Medioni, G. , 1992, Object Modelling by Registration of Multiple Range Images, Image Vision Computer, 10, 145-155.

Chua, C. S., and Jarvis, R. , 1996, 3D Free-Form Surface Registration and Object Recognition, International Journal of Computer Vision, 17, 77-99.

Cipolla, R., and Giblin, P. , 2000, Visual Motion of Curves and Surfaces, Cambridge University Press.

Covell, M. , 1995, Autocorrespondence：Feature-Based Match Estimation and Image Metamorphosis, IEEE International Conference on Systems, Man, and Cybernetics Vancouver, Canada.

Di Zenzo, S. , 1986, A Note on the Gradient of a Multi-Image, Computer Vision, Graphics, and Image Processing, 33,116-125.

Feldmar, J., and Ayache, N. , 1996, Rigid, Affine and Locally Affine Registration of Free-Form Surface, International Journal of Computer Vision, 18(2), 99-119.

Fusiello, A., Trucco, E., and Verri, A. , 2000, A Compact Algorithm for Rectification of Stereo Pairs, Machine Vision and Applications, 16-22.

Harris, C. J., and Stephens, M. , 1988, A Combined Corner and Edge Detector, In Proc. 4th Alvey Vision Conf., Manchester, 147-151.

Hoppe, H., DeRose, T., and Duchamp, T. , 1992, Surface Reconstruction from Unorganized Points, SIGGRAPH ’92 Proceedings, 71-78.

Hugli, H., and Schutz, C. , 1997, Geometric Matching of 3D Objects : Assessing the Range of Successful Initial Configurations, International Conference on Recent Advances in 3-D Digital Imaging and Modeling , 101-106.

Johnson, A. E., and Hebert, M. , 1997, Surface Registration by Matching Oriented Points, Proceeding of International Conference on 3-DDigital Imaging and Modeling, 121-128.

Johnson, A. E., and Kang, S. B. , 1997, Registration and Integration of Textured 3-D Data, Proceeding of International Conference on 3-DDigital Imaging and Modeling, 234-241.

Klette, R. , 1998, Computer Vision Three-Dimensional Data From Images, Singapore: Springer.

Lee, N. L., and Menq, C. H. , 1995, Segmentation of Scanned Data Points for Reverse Engineering, Proceeding of ASME International Computers in Engineering Conference, 1-12.

Mouaddib, E., Batlle, J., and Salvi, J. , 1997, Recent Progress in Structured Light in Order to Solve the Correspondence Problem in Stereovision, International Conference on Robotics and Automation, 130-136.

Pieg, L., and Tiller, W., 1997, The NURBS Book, Springer.

Pollefeys, M., and Van Gool, L. , 2002, From Images to 3D Models, Communications of the ACM, 45(7), 50-55.

Roberts, L. G. , 1963, Machine Perception of Three-dimensional Solids, Optical and Electro-Optical Information Processing, MIT Press, Cambridge, MA. 159-197.

Sapidis, N., and Farin, G. , 1990, Automatic Fairing Algorithm for B-spline Curves, Computer-Aided Design, 22(2), 121-129.

Sahoo, K. C., and Menq, C. H. , 1991, Localization of 3-D Object Having Complex Sculptured Surfaces Using Tactile Sensing and Surface Description, ASME, Journal of Engineering for Industry, 113, 85-92.

Sobel, I. E. , 1970, Camera Models and Machine Perception, Ph.D. dissertation, Stanford University, Palo Alto, Calif.

Sonka, M., Hlavac, V., and Boyle, R. , 1998, Image Processing, Analysis, and Machine Vision, second edition, PWS, Pacific Grove California.

Tsai, R. Y. , 1987, A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses, IEEE Journal of Robotics and Automation, 3(4),323–344.

Varady, T., Martin, R. R. ,and Cox, J. , 1997, Reverse Engineering of Geometric Models - An Introduction, IEEE, Computer Graphics and Applications, 29(4), 255-268.

Wei, G., and Ma, S. , 1994, Implicit and Explicit Camera Calibration: Theory and Experiments, IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5), 469-480.

Will, P. M., and Pennington, K. S. , 1971, Grid Coding: A Preprocessing Technique for Robot and Machine Vision, Int. Joint Conf. On Artificial Intelligence, 66-70.

Yau, H. T. , 2000, Registration and Integration of Multiple Laser Scanned Data for Reverse Engineering of Complex 3D Models, INT. J. PROD., 38(2), 269-285.

Yoshiaki Shirai , 1987, Three-Dimensional Computer Vision, Springer-Verlag.

Zhang, Z. , 1994, Iterative Point Matching for Registration of Free-Form Curves and Surfaces, International Journal of Computer Vision, 13(2),119-152.

Zhang, Z. , 2002, Camera Calibration with One-Dimensional objects, Technical Report MSR-TR-2001-120, Microsoft Research.

何宜達 , 2002, 視覺伺服技術於三維目標軌跡預測與攔截之應用, 國立成功大學航空太空科學研究所碩士論文.

范光照,章明,姚宏宗,許智欽 , 1999, 逆向工程技術及應用, 高立圖書有限公司.

姚宏宗 , 2001, 對合環上的導算, 國立清華大學數學研究所碩士論文.

莊俊德 , 2004, 針孔成像系統三維量測之誤差分析及系統校正, 國立成功大學航空太空科學研究所碩士論文.

莊峻超 , 2003, 逆向工程Imageware功能剖析, 全華科技圖書股份有限公司.

賴朝鍵 , 2002, 逆向工程重建CAD模型之研究與實例探討, 國立成功大學機械工程研究所碩士論文.

戴文智 , 1996, 三維輪廓影像視覺掃瞄量測技術之研究, 私立中原大學機械工程研究所碩士論文.