早在1795年就有醫學內視鏡的應用。最近三十年來，隨著光學與資訊電子技術的發展與進步，內視鏡之於內、外科醫學已成為密不可分的一部分。臨床應用的領域越來越大，到最近幾年之中，甚至已成為一個專科領域。
　　相對的電腦影像分析，也提供內視鏡影像重要的臨床輔助分析工具。傳統的內視鏡影像分析，以二維影像校正及量測為重點。在本研究中，我們採用內視鏡的影像序列，將所觀察管道區域，直接以電腦視覺校正方式，做三維立體成像，並可達到即時真實貼圖呈現，以增加視覺真實感。
　　在狹小的管道中，為了取得大面積的影像，內視鏡大多使用廣角度鏡頭（魚眼鏡頭）。因此所取進來的影像，皆有一定程度的變形失真。故在三維重構之前，本系統提出使用快速的廣角鏡頭變形影像校正機制，利用簡單的校正板與數學校正模型，對一組內視鏡儀器進行形變影像校正。而只需對同一台內視鏡，進行一次校正，爾後便可利用所得到的鏡頭校正參數進行重構，而不需重複校正。
　　另一方面，影響重構結果的重要因素，即為影像對應點的取得與追蹤。本系統採用高通濾波器偵測特徵點，並且使用Kanade-Lucas-Tomasi (KLT)特徵追蹤演算法，作為重構影像對應點的追蹤。同時把生理組織的色彩因子，加入到KLT特徵追蹤演算法。另外，也根據內視鏡影像的縮放特性，改良KLT特徵追蹤演算法，以適應縮放型式的影像序列。並且加入廣角鏡頭所造成的形變因素考量，以增加特徵追蹤的穩定性與一致性。
　　最後的三維重構部分，我們利用多重影像序列自動校正機制，計算多張影像間，特徵點的三維位置，將所觀察的管道重構出來，並貼以真實影像貼圖。對於特定病變區域，亦提供了細部重構的機制，並做真實大小校正，以提供觀測者數值上的參考。

　　In the last 30 years, the progresses in optical engineering, computer science and electronic techniques have made the endoscopy an invaluable tool in both internal clinics and surgical operations. As its applications increase exponentially, it has even become a specialized division in the clinical medicine.
　　The image analysis technique provides important aids to the processing of clinical endoscopic images. However, traditional image analyses emphasize the 2-D image distortion calibration and assessment for endoscopic images. In this thesis, we use the computer vision algorithm to reconstruct the 3-D model from the endoscopic image sequence, texture mapping with real images are then employed to enhance the visualization of the reconstructed tubular scene.
　　For obtaining a larger field of view inside a small and narrow pipeline, the endoscope is usually equipped with wide-angle lens. Therefore, the acquired images are often with certain degrees of shape distortion. Before 3-D reconstruction, our system provides a fast mechanism for correcting the wide-angle lens distortion. Using a calibration pattern, the nonlinear distortion is corrected with a simple mathematic model for the endoscopic images. Once the endoscopic lens is calibrated, the same calibration parameters can be utilized repeatedly for the calibrated instrument.
　　On the other hand, how to extract and track the correspondent features from the image sequence is one of the most important tasks in 3-D reconstruction. Our systems use the high-pass filter to extract the edge feature and the Kanade-Lucas-Tomasi (KLT) feature tracking algorithm to obtain the feature correspondences. The color information, zoom-out characteristic and distortion factor of endoscope image sequence are all taken into account for improving the feature tracking results.
　　Thereafter, the multiple frame auto-calibration is used to obtain the camera parameters. The 3-D coordinates of the detected feature points are then computed from the multiple images to reconstruct the 3D scene inside the tubular structure. At last, texture mapping with real endoscopic images is adopted to visualize the realistic 3D scene inside the reconstructed tubular structure of the observed organ.

[1] James P. Helferty, Chao Zhang, Geoffrey McLennan, and William E. Higgins, “Videoendoscopic Distortion Correction and Its Application to Virtual Guidance of Endoscopy”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 20, NO. 7, Jul. 2001.

[2] Christian Stern, “Non-Invasive Virtual Endo- and Exoscopic Screening for Arterial and Colonic Disease Based on Ultrafast 3D MRI”, The Institute of Diagnostic Radiology of the Zurich University Hospital, Multi-Media Laboratory. http://www.ifi.unizh.ch/mml/people/stern/stern.html

[3] “Multislice CT Colonography”
TOSHIBA VISIONS Magazine No 2 · Volume 2 · 2002.
http://www.toshiba-europe.com/medical/medicallr.asp?PageID=3

[4] Huaibin Zhao; Aggarwal, J.K. “3D reconstruction of an urban scene from synthetic fish-eye images”, Image Analysis and Interpretation, 2000. Proceedings. 4th IEEE Southwest Symposium , 2000 Page(s): 219 -223

[5] Warren E. Smith,Nimish Vakil, and Seth A. Maislin, “Correction of Distortion in Endoscope Images”, IEEE TRANSACTION ON MEDICAL IMAGING, VOL.11, NO. 1, Mar. 1992.

[6] Hideaki Haneishi, Yutaka Yagihashi, and Yoichi Miyake, “ A New Method for Distortion Correction of Electronic Endoscope Images”, IEEE TRANSACTION ON MEDICAL IMAGING, VOL.14, NO. 3, Sep. 1995.

[7] K. Vijayan Asari, Sanjiv Kumar, and D. Radhakrishnan, “A New Approach for Nonlinear Distortion Correction in Endoscopic Images Based on Least Squares Estimation”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL.18, NO. 4, Apr. 1999.

[8] Bruce D. Lucas and Takeo Kanade., “An Iterative Image Registration Technique with an Application to Stereo Vision”, International Joint Conference on Artificial Intelligence, pages 674-679, 1981.

[9] Carlo Tomasi and Takeo Kanade., “Detection and Tracking of Point Features.”, Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.

[10] Jianbo Shi and Carlo Tomasi., “Good Features to Track.”, IEEE Conference on Computer Vision and Pattern Recognition, pages 593-600, 1994.

[11] Stan Birchfield., ”Derivation of Kanade-Lucas-Tomasi Tracking Equation.”, Unpublished, May 1996.

[12] Tommasini, T.; Fusiello, A.; Trucco, E.; Roberto, V., “Making good features track better”, Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on , 1998. Page(s): 178 –183

[13] Reinhard Klette, Karsten Schluns, Andreas Koschan, “Computer Vision , Three-Dimensional Data from Images”, Springer Publishing , P148~149.

[14] P. Montesinosa,*, V. Goueta, R. Dericheb, D. Pele´ c , “Matching color uncalibrated images using differential invariants”, ELSEVIER Image and Vision Computing 18 (2000) 659–671.

[15] P. Montesinos, V. Gouet, R. Deriche, D. Pelé, “Differential Invariants for Color Images”, Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on , Volume: 1 , 1998, Page(s): 838 -840 vol.1

[16] Gouet, V.; Montesinos, P.; Pelc, D., “Stereo matching of color images using differential invariants”, Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on , Volume: 2 , 1998. Page(s): 152 -156 vol.2

[17] Richard Hartley, Andrew Zisserman, “Multiple View Geometry in Computer Vision”, CAMBRIDGE UNIVERSITY PRESS Publishing, Page(s):217-241

[18] M. A. Fischler and R. C. Bolles. “Random sample consensus: A paradigm for model fitting with application to image anaysis and automated cartography.”, Comm. Assoc. Comp. Mach., 24(6):381-395, 1981

[19] Richard Hartley, Andrew Zisserman, “Multiple View Geometry in Computer Vision”, Publisher CAMBRIDGE UNIVERSITY PRESS, Page(s):568-582

[20] Pollefeys, M.; Koch, R.; Van Gool, L., “Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters”, Computer Vision, 1998. Sixth International Conference on , 1998 , Page(s): 90 –95

[21] R. A. Dwyer. A Faster “Divide-and-Conquer Algorithm for Constructing Delaunay Triangulations.” Algorithmica, 2:137-151,1987.

[22] Ｆ. Dehne and R. Klein. “A Sweepcircle Algorithm for Voronoi Diagrams.” Proceedings of Graph-Theoretical Concepts in Computer Science, published as Lecture Notes in Computer Science Page(s) 59-69, Springer-Verlag, 1987.

[23] Milan Sonka, Vaclav Hlavac, Roger Boyle., “Image Processing Analysis, and Machine Vision”, Second Edition, PWS Publishing, 1999

[24] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, Addison Wesley Publishing, 1992.