臺灣博碩士論文加值系統

相機校正在影像處理與電腦視覺領域的相關議題中一直扮演著重要的角色，常見的校正方法分為內部校正以及外部校正，兩種皆是為了取得相機的參數，用在影像變形還原，常應用在機器手臂、測量距離等。藉由相機外部參數轉換將真實3D世界座標上的座標資訊轉換成相機影像座標，接著用內部參數將相機影像座標轉換成影像座標，成為一張2D平面影像，而取得這些相機參數屬於最佳化問題，因此我們希望結合粒子群最佳化演算法，提升校正的效果。
本論文參考Open CV 提供的相機校正演算法，實驗的相機是使用約170˚廣角鏡頭相機SJCAM-SJ4000，我們對棋盤格校正板拍攝實驗所需的測試用圖，再分別找出影像中的棋盤格角點座標即我們所謂影像座標，與我們預設的世界座標下去計算出實驗相機之相機參數，含內部參數 、鏡片扭曲參數 、外部參數 ，我們欲使用粒子群最佳化演算法對於這些參數再進行估算，現階段我們考慮先針對鏡片扭曲參數進行估算，期望可以得到較佳的參數使校正後的結果與原始結果相比會有改善。

Camera calibration has played an important role in the field of image processing and computer vision. The common methods for calibration can be divided into internal calibration and external calibration. Both methods can find the parameters of cameras, which can be applied to the field of robotic arm applications, measuring distance and so on. To get an image, first we need to transform the information of 3D world coordinate into camera coordinate by external parameters. Next, use internal parameters to transform camera coordinate into 2D image coordinate, and finally we can get an image. Getting external and internal parameters is labeled as optimization problem. In order to fine tune the parameters, we introduce Particle Swarm Optimization (PSO) method to improve the image quality.
In this thesis, we take camera calibration method provided by OpenCV as our reference. We use wide-angle lens camera to test our method. We take pictures of chessboard corrector plate as our testing images. Find out all the corner coordinates in chessboards of each images. By using those coordinates we find that we can estimate the parameters of the testing camera. The parameters include internal parameters, external parameters, and distortion parameters. We try to fine tune for new parameters using PSO. Experimental results show that we can indeed improve the visual quality a little, although the quantity index, reprojection error, exhibits very little improvement.

致 謝 I
摘 要 II
Abstract III
目 錄 IV
圖 目 錄 V
表 目 錄 VI
第一章　研究動機與文獻探討 1
1.1相機校正 1
1.2粒子群最佳化演算法 3
第二章　相機校正 5
2.1相機校正 5
2.2 實驗結果 11
第三章　PSO演算法與應用 13
3.1 粒子群最佳化演算法 13
3.2 PSO實驗結果 15
第四章　使用PSO微調校正參數 19
4.1 系統設定 19
4.2 實驗結果 19
4.3 進階實驗與討論 22
第五章　結論與未來展望 30
參考文獻 31
附錄一 33

[1]Y. I. Abdel-Aziz and H. M. Karara, “Direct linear transformation into object space coordinates in close-range photogrammetry,” Photogrammetric Engineering & Remote Sensing, vol. 81, no. 2, pp. 103–107, 2015.
[2]W. Faig, “Calibration of close-range photogrammetric systems: Mathematical formulation,” Photogram. Eng. Remote Sens., vol. 41, no. 12, 1975.
[3]M. A. Penna, “Determining camera parameters from the perspective projection of a quadrilateral,” Pattern Recognit, vol. 24, no. 6, pp. 533–541, 1991.
[4]Z. Zhang, “A flexible new technique for camera calibration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1330–1334, 2000.
[5]Q. Ji and Y. Zhang, “Camera calibration with genetic algorithms,” IEEE Trans. on Systems, Man, and Cybernetics, Part A:Systems and Humans, vol. 31, no. 2, pp. 120–130, 2001.
[6]A. Abellard, M. Bouchouicha, and M. M. B. Khelifa, “A genetic algorithm application to stereo calibration,” In Proceedings of 2005 IEEE international symposium on computational intelligence in robotics and automation, Espoo, Finland, pp. 285–290, 2005.
[7]S. Kumar, M. Thakur, B. Raman, and N. Sukavanam, “Stereo camera calibration using real coded genetic algorithm,” in TENCON 2008-2008 IEEE Region 10 Conference, pp. 1–5, 2008.
[8]W. Xiang, Z. Zhou, D. Ge, Q. Y. Zhang, and Q. H. Yao, “Camera calibration by hybrid Hopfield network and self-adaptive genetic algorithm,” Meas. Sci. Rev., vol. 12, no. 6, pp. 302–308, 2012.
[9]D. Wang, Y. Tu, and T. Zhang, “Research on the application of PSO algorithm in non-linear camera calibration,” In Proceedings of the 7th world congress on intelligent control and automation, Chongqing, China, pp. 4495-4500, 2008.

[10]K. Deep, M. Arya, and J. C. Bansal, “A non-deterministic adaptive inertia weight in PSO,” In Proceedings of the 13th annual conference on Genetic and evolutionary computation, 2011, pp. 1155–1162.
[11]J. Kennedy, R. C. Eberhart, “Particle swarm optimization,” In Proceedings of IEEE Int. Conf. on Neural Networks, Perth, Australia, vol. 4, pp. 1942-1948, 1995.
[12]R. C. Eberhart, J. Kennedy, “A new optimizer using particle swarm theory,” In Proceedings of IEEE Int. Symposium on Micro Machine and Human Science, Nagoya, Japan, pp. 39-43, 1995.
[13]C. W. Reynolds, “Flocks, herds and schools: a distributed behavioral model,” Computer Graphics, 21(4):25-34, 1987.
[14]F. Heppner, and U. Grenander, “A stochastic nonlinear model for coordinated bird flocks,” In S. Krasner, Ed., The Ubiquity of Chaos. AAAS Publications, Washington, DC, 1990.
[15]E. O. Wilson, “Sociobiology: The new synthesis,” Belknap Press, Cambridge, MA, 1975.
[16]A. Khanra, M. K. Maiti, and M. Maiti, “Profit maximization of TSP through a hybrid algorithm,” Comput. Ind. Eng., vol. 88, pp. 229–236, Oct. 2015.
[17]X. Hu, R. C. Eberhart, and Y. Shi, “Swarm intelligence for permutation optimization: a case study of n-queens problem,” In Proceedings of the 2003 on IEEE(SIS''03) Swarm Intelligence Symposim, pp. 243-246, Apr. 2003.
[18]A. Mekhmoukh and K. Mokrani, “Improved Fuzzy C-Means based Particle Swarm Optimization (PSO) initialization and outlier rejection with level set methods for MR brain image segmentation,” Comput. Methods Programs Biomed., vol. 122, no. 2, pp. 266–281, Nov. 2015.
[19]K. Deep, M. Arya, M. Thakur, and B. Raman, “Stereo Camera Calibration Using Particle Swarm Optimization,” In Applied Artificial Intelligence, vol. 27, no. 7, pp. 618–634, Aug. 2013.
[20]K. Zhou and L. Yu, “Parameters Separated Calibration Based on Particle Swarm Optimization for a Camera and a Laser-Rangefinder Information Fusion,” In Mathematical Problems in Engineering., p. 291-461, 2014.