臺灣博碩士論文加值系統

常見的魚眼鏡頭校正方法是根據其光學模型，以數學函數為基礎建立其變形函數。雖然調整變形函數的參數可得到不同的校正結果，然而這樣的數學函數模型在適應性上往往不足以應付各種不同的魚眼鏡頭。本論文基於B-spline函數，發展出一個具有適應性的建構變形函數機制。
本論文運用粒子群最佳化演算法於B-spline函數的控制點調整，同時加入初始控制點調整機制來抑制粒子群最佳化演算法的變異數問題。在調整過程中，本論文依據校正樣板中的線條資訊做為還原效能的依據。
由實驗結果證明，本論文提出的機制所建構的變形函數模型能夠有效地使校正樣板中的線條變回直線，並且相較於傳統多項式函數與等距離投影公式有更佳的還原效果。

Common methods for calibrating fish-eye lenses are to construct distortion function based on mathematical method that is used to model the optical system. Adjusting parameters of distortion function can make various calibrated results; however, the distortion function based on polynomial function is insufficient to deal with all fish-eye lenses. This thesis develops an adaptive mechanism to establish distortion function based on B-spline function.
This thesis presents a Particle Swarm Optimization (PSO) approach for adjusting the control points of B-spline function. Furthermore, this thesis also uses initial adjustment mechanism to restrain the variance of PSO. In adjusting process, this thesis employs the line data in correction pattern as the reconstruction performance.
The experiment results in this thesis showed that the proposed method for establishing distortion function can effectively reconstruct the lines in correction pattern, and also has better reconstruction performance than polynomial function and equidistance projection equation.

摘要 I
ABSTRACT II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VI
符號表 X
第一章 緒論 1
1-1 前言 1
1-2 文獻回顧 2
1-3 研究動機 4
1-4 研究方法與貢獻 4
1-5 論文架構 5
第二章 魚眼鏡頭變形影像校正概述 7
2-1 魚眼鏡頭變形影像的特性 7
2-2 魚眼鏡頭變形影像的校正方式 9
2-3 變形函數模型 14
2-4 相關理論 21
2-4-1 B-spline曲線 21
2-4-2 細線化 24
2-4-3 粒子群最佳化演算法 32
第三章 變形函數模型建模方式 37
3-1 校正樣板影像前處理 37
3-2 魚眼鏡頭校正影像還原效果評估 43
3-3 控制點調整機制 50
3-3-1 建立初始控制點分佈 52
3-3-2 控制點初始調整機制 58
3-3-3 運用粒子群最佳化演算法於控制點調整 63
第四章 實驗模擬 69
4-1 控制點調整機制相關實驗 69
4-1-1 實驗說明 70
4-1-2 初始控制點數目和B-spline曲線階數 73
4-1-3 PSO控制點調整機制 76
4-1-4 PSO參數調整 79
4-2 其它函數以及不同校正樣板還原效果比較 81
4-2-1 實驗說明 82
4-2-2 樣板1 82
4-2-3 樣板2 87
4-2-4 樣板3 91
4-3 其它魚眼鏡頭之校正效果 95
4-4 實驗討論 98
第五章 結論與未來工作 101
5-1 結論 101
5-2 未來工作 101
參考文獻 103
作者簡歷 106

[1] C. Hughes, M. Glavin, E. Jones, and P. Denny, “Wide-angle camera technology for automotive applications: a review,” IEEE Trans. Intelligent Transport Systems, IET, vol. 3, issue: 1, pp. 19-31, 2009.
[2] K. Miyamoto, “Fish eye lens,” Journal of the Optical Society of America, vol. 54, issue: 8, 1964, pp. 1060-1061.
[3] R. Y. Tsai, “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, vol. 3, issue: 4, pp.323-344, 1987.
[4] C. C. Slama, Manual of photogrammetry. American Society of Photogrammetry, 4th edition, 1980.
[5] F. Devernay, and O. Faugeras, “Automatic calibration and removal of distortion from scenes of structured environments,” in SPIE Proc. Investigate and Trial Image Processing, vol. 2567, San Diego, USA: SPIE, 1995.
[6] M. Ahmed, and A. Farag, “Nonmetric calibration of camera lens distortion: differential methods and robust estimation,” IEEE Trans. Image Processing, vol. 14, issue: 8, pp.1215-1230, 2005.
[7] A. Basu, and S. Licardie, “Alternative models for fish-eye lenses,” in Pattern Recognition Letters, vol. 16, issue: 4, pp.433-441, 1995.
[8] R. Hartley, and S. B. Kang, “Parameter-Free Radial Distortion Correction with Center of Distortion Estimation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, issue: 8, pp. 1309-1321, 2007.
[9] J. Wang, F. Shi, J. Zhang, and Y. Liu, “A New Calibration Model and Method of Camera Lens Distortion,” in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5713-5718, 2006.
[10] W. Yu, “An embedded camera lens distortion correction method for mobile computing applications,” IEEE International Conference on Consumer Electronics, pp. 400-401, 2003.
[11] W. Yu, “Image-based lens geometric distortion correction using minimization of average bicoherence index,” in Pattern Recognition, vol. 37, issue: 6, pp. 1175-1187, 2004.
[12] S. W. Park, and K. S. Hong, “Practical ways to calculate camera lens distortion for real-time camera calibration,” in Pattern Recognition, vol. 34, issue: 6, pp. 1199-1206, 2001.
[13] X. Armangué, J. Salvi, and J. Batlle, “A Comparative Review of Camera Calibrating Methods with Accuracy Evaluation,” in Pattern Recognition, vol. 35, issue: 7, pp. 1617-1635, 2002.
[14] A.W. Fitzgibbon, “Simultaneous linear estimation of multiple view geometry and lens distortion,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I-125 - I-132, 2001.
[15] M. Friel, C. Hughes, P. Denny, E. Jones, and M. Glavin, “Automatic calibration of fish-eye cameras from automotive video sequences,” IEEE Trans. Intelligent Transport Systems, vol.4, issue: 2, pp. 136-148, 2010.
[16] A. McAndrew, Introduction to digital image processing with MATLAB, Course Technology, 2004.
[17] C. Brauer-Burchardt, and K. Voss, “A new algorithm to correct fish-eye and strong wide-angle-lens-distortion from single images,” in Proc. IEEE Int. Conf. on Image Processing, Thessaloniki, Greece, vol. 1, pp. 225-228, 2001.
[18] M. Friel, C. Hughes, P. Denny, E. Jonse, and M. Glavin, “Automatic calibration of fish-eye cameras from automotive video sequences,” IEEE Trans. Intelligent Transport Systems, IET, vol. 4, issue: 2, pp.136-148, 2010.
[19] I. K. Nikolos, K. P. Valavanis, N. C. Tsourveloudis, and A. N. Kostaras, “Evolutionary algorithm based offline/online path planner for UAV navigation,” IEEE Trans. on Systems, Man and Cybernetics, Part B, vol. 33, issue: 6, pp. 898-912, 2003.
[20] T. Y. Zhang, and C. Y. Suen, “A Fast Parallel Algorithm for Thinning Digital Patterns,” Communications of the ACM, vol. 27, issue: 3, pp. 236-239, 1984.
[21] J. Kennedy, and R. C. Eberhart, “Particle swarm optimization” in Proc. of the 4th IEEE International Conference on Neural Networks, pp. 1942-1948, 1995.
[22] S. T Hsieh, T. Y Sun, C. C Liu, and C. W Lin, “An improved particle swarm optimizer for placement constraints,” Journal of Artificial Evolution and Applications, Volume 2008 (2008), 10 pages, Open Access Journal.
[23] V. G. Gudise, and G. K. Venayagamoorthy, “Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks,” in Proc. of IEEE Swarm Intelligence Symposium, pp. 110-117, 2003.
[24] T. Y. Sun, S. J. Tsai, and V. Chan, “HIS color model based lane-marking detection,” in Proc. IEEE Intelligent Transportation Systems Conference, pp. 1168-1172, Toronto, Canada, 2006.
[25] F. Devernay, and O. Faugeras, “Straight lines have to be straight: automatic calibration and removal of distortion from scenes of structured environments,” Machine Vision and Applications, vol. 13, issue: 1, pp. 14-24, 2001.
[26] 許智誠，結合慣性道路線標記與車輛陰影之前車偵測演算法，國立東華大學碩士論文，2011。
[27] C. Hughes, R. McFeely, P. Denny, M. Glavin, and E. Jones, “Equidistant (fθ) fish-eye perspective with application in distortion centre estimation,” Image and Vision Computing, Vol. 28, issue: 3, pp. 538-551, 2010.
[28] N. Chernov, Circular and Linear Regression: Fitting Circles and Lines by Least Squares, CRC Press, 2010.
[29] http://www.particleswarm.info/Programs.html, 瀏覽日期：2013/7/31。