電腦視覺的技術目前已經被廣泛的應用在各方面，特別在工業檢測、醫療影像處理、搖測系統、軌跡追尋、微科技等均有相當好的成果。藉由分析影像可重建三維世界座標的真實資訊。取得的影像失真度越低，才足以確保所得資訊的可信度。然而，常因攝影機鏡頭或儀器本身的精度不足及外界環境的干擾，難以避免地會出現失真的情形，此時，攝影機的校正便成了改善誤差的重要方法。可以說攝影機校正是所有電腦視覺工作的重要前期處理工作。
本論文依據Zhang的校正技術，同時對左右兩台攝影機的進行校正。此方法不必知道攝影機或校正板擺設的姿態只要依要求擷取兩張不同的影像，即可求出相對於攝影機姿態的外部參數、內部參數與兩個透鏡扭曲參數。研究得到的實驗誤差均可在次像素以內。校正完之後利用Epipolar Geometry 的條件限制式找出左右攝影機的對應關係，再利用所找到的攝影機內外參數去求三維世界座標。實驗結果顯示，增長兩攝影機之間的基礎線，可有效改善離攝影機較遠處的景深誤差。

The technology of computer vision is broadly applied in many aspects such as industrial inspection, medical image processing, remote sensing and nanotechnology. By analyzing the images provided by two difference cameras, the desired target position corresponding to the world coordinate can be obtained. Due to the image distortion, abd quantization error of the processing algorithm, the required information may not be obtained straightforward. Therefore, the camera calibration is important to 3D information reconstruction.
In the thesis, Zhang’s calibration applied to calibration the camera system parameters. This method only requires the camera to observe a planar pattern from a few different orientations. Either the camera or the planar pattern attitude can be altered. The corresponding motion need not be available. The camera intrinsic parameters, extrinsic parameters, and the parameters of radial lens distortion can be obtained under a systematic procedure. The experimental error is constrained to sub-pixel scale. Associating with camera calibration, the constraints of Epipolar Geometry is applied to obtain the mapping of two different images, and to reconstruct the world coordinate. From the experimental results, it reveals that the increase of baseline can improve the error of depth effectively.

[1] Birchfield, S., & Tomasi, C.(1998). Depth Discontinuities by Pixel-to pixel Stereo. Proceedings of 1998 IEEE International Conference on Computer Vision, 4(7), 1073-1080.
[2] Bougnoux, S.(1998). From projective to Euclidean space under any practical situation, a criticism of self-calibration. In Proceeding of the 6th International Conference on Computer Vision, 4(7), 790-796.
[3] Hutchison, S., Hager, G.D., & Corke, P.I.(1996). A Tutorial on Visual Servo Control. IEEE Transaction on Robotics and Automation, 12(5), 651-668.
[4] Kanade, T., & Okutomi, M.(1994). A stereo matching algorithm with an adaptive window: theory and experiment. IEEE trans. on Pattern Analysis and Machine Intelligence, 16(9), 920-932.
[5] Kweon, J.J., Jang, D.K., & Kim, J.D.(1989). A stereo matching algorithm using line segment feature. TENCON’89 Fourth IEEE Region 10 International Conference, 22(24), 589-592.
[6] Maybank, S.J., & Faugeras, O.D.(1992). A theory of self-calibration of a moving camera . The international Journal of Computer Vision,8(2),123-152.
[7] Papadimitrion, D.V., & Dennis, T.J.(1994). Stereo Disparity Analysis using Phase Correlation. Electronics Letters, 30(18), 1475-1477.
[8] Sanderson, A.C., & Weiss, L.E.(1980). Image-based visual servo control using relational graph error signals. Proc. IEEE, (pp.1074-1077).
[9] Sonka, M., Hlavac, V., & Boyle,R.(1998). Image Processing, Analysis, and Machine Vision. second edition, PWS, Pacific Grove, California.
[10] Tsai, R. (1987). A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses. IEEE Trans. Robot. Automat, 3(4), 323-344.
[11] Tsai’s, R. Tsai’s camera calibration technique source code
URL:http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/rgw/www/TsaiCode.html
[12] Wei, G., Arbter, K, & Hizinger, G.(1998). Active Self Calibration of Robotic Eyes and Hand-Eye Relationships with Model Identification. IEEE Trans. On Robotics and Automation, 40(1), 158-166.
[13] Weng, J., Ahuja, N., & Huang, T.S.(1992). Matching Two Perspective View. IEEE Trans. on Pattern analysis and Machine Intelligence, 14(8), 806-825.
[14] Zhang Z.(1996). Determining the epipolar geometry and it uncertainty: a review.
[15] Zhang, Z.(2000). A Flexible New Technique for Camera Calibration. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 22(11) ,1330-1334.
[16] 吳承科, 帶善榮,程湘君, 雲立實, 民(83), 數位影像處理, 儒林.
[17] 何宜達, 民(92), 視覺伺服技術於三維目標軌跡預測與攔截之應用, 碩士論文, 國立成功大學航空太空工程研究所.