在電腦視覺中，相機位置與姿態（位姿，Pose）的估測一直是很重要的課題，就像人類一樣，藉由眼睛感測周遭環境的變化來辨識自己位姿的改變，許多研究人員也一直致力於讓機器人透過電腦視覺感知自身位姿的研究與應用。即時定位與地圖構建（Simultaneous Localization and Mapping, SLAM）是集「位姿估測」與「地圖建立」於一身的系統架構，在對地圖進行初始化之後，藉由感測器所給予的資訊，反覆地估測自身在地圖的位姿並擴張地圖，達到類似於人類自我感知的能力。通常太空載具若要得知目前的位姿，必須透過追星儀辨識所偵測的星體後，藉由此星體的天球座標系判斷自我位姿，但錯誤的星體判斷會導致演算法失效，因此本論文將基於SLAM的架構，並著重於位姿估測的探討，提供太空載具另一種不偵測特定物體的位姿估測方法，使用五軸模擬姿態平台模擬太空載具的姿態，以Kinect作為視覺感測器，拍攝預先搭建好的月球表面模型提供影像後，首先偵測棋盤格並校正相機取得內部參數，透過尺度不變特徵轉換（Scale Invariant Feature Transform, SIFT）提取影像上的特徵點，使用KD-tree與隨機取樣一致性算法(Random Sample Consensus, RANSAC)去除錯誤的匹配點，憑藉基礎矩陣（Fundamental Matrix）、投影單應性矩陣（Perspective Homography Matrix）與PnP（Perspective-n- Point）求解相機的位姿，搭配三角化（Triangulation）獲得匹配點在三維空間中的位置，最後利用光束法平差（Bundle Adjustment, BA）得到最佳化的相機位姿與特徵點地圖，並以編碼器（Encoder）作為正解檢驗演算法的位姿估測精度，達到太空載具利用影像定位之應用。

In computer vision, the estimation of camera position and attitude has always been a very important issue. It emulates human eye to recognize changes in the surrounding environment to obtain the pose estimation. Simultaneous Localization and Mapping (SLAM) is a well-known methodology in combining pose estimation and map construction. It repeatedly construct a map of an unknown environment while simultaneously keep track of the location within the constructed map. Conventionally, space vehicle had to know the pose by identify the star through star tracker, and estimates the pose by the celestial coordinate system. But the wrong identification will contribute a wrong pose estimation, therefore, in this paper will have a discussions on pose estimation based on SLAM methodology, the proposed methodology can operate without detecting a specific object for space vehicle pose estimation. This paper will using Kinect as a visual sensor which is installed on a five-axis simulation platform, and getting a few images on an artificial lunar surface to simulate a vision of space vehicle. Besides, this paper will introduce some image features points extraction method by using checkerboard detection, Scale Invariant Feature Transform (SIFT), and computing the camera pose through Random Sample Consensus (RANSAC), Fundamental Matrix, Perspective Homography Matrix and Perspective-n-Point. Furthermore, using Triangulation and Bundle Adjustment to obtain feature map and best pose estimation result, and compare with five-axis platform encoder as ground truth. With this framework, it can be the pose estimation methodology which can be applied on space vehicle.

[1] R. Chatila and J. Laumond, "Position Referencing and Consistent World Modeling for Mobile Robots," Proceedings. 1985 IEEE International Conference on Robotics and Automation, 1985, pp. 138-145.
[2] H. Durrant-Whyte and T. Bailey, "Simultaneous Localization and Mapping: Part I," in IEEE Robotics & Automation Magazine, vol. 13, no. 2, pp. 99-110, June 2006.
[3] T. Bailey and H. Durrant-Whyte, "Simultaneous Localization and Mapping (SLAM): Part II," in IEEE Robotics & Automation Magazine, vol. 13, no. 3, pp. 108-117, Sept. 2006.
[4] G. Dissanayake, P. Newman, S. Clark, H. F. Durrant-Whyte and M. Csorba, "A Solution to The Simultaneous Localization and Map Building (SLAM) Problem," in IEEE Transactions on Robotics and Automation, vol. 17, no. 3, pp. 229-241, Jun 2001.
[5] T. Taketomi, H. Uchiyama and S. Ikeda, "Visual SLAM Algorithms: A Survey from 2010 to 2016", IPSJ Transactions on Computer Vision and Applications, vol. 9, no. 1, 2017.
[6] A. J. Davison, I. D. Reid, N. D. Molton and O. Stasse, "MonoSLAM: Real-Time Single Camera SLAM," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1052-1067, June 2007.
[7] G. Klein and D. Murray, "Parallel Tracking and Mapping for Small AR Workspaces," 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, Nara, 2007, pp. 225-234.
[8] R. Mur-Artal, J. M. M. Montiel and J. D. Tardós, "ORB-SLAM: A Versatile and Accurate Monocular SLAM System," in IEEE Transactions on Robotics, vol. 31, no. 5, pp. 1147-1163, Oct. 2015.
[9] J. Engel, T. Schöps, D. Cremers, "LSD-SLAM: Large-scale Direct Monocular SLAM", Proc. Eur. Conf. Comput. Vision, pp. 834-849, Sep. 2014.
[10] Z. Zhang, "A Flexible New Technique for Camera Calibration," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1330-1334, Nov 2000.
[11] G. Bradski and A. Kaehler, Learning OpenCV. Farnham: O'Reilly, 2012
[12] MathWorks, "What Is Camera Calibration?- MATLAB & Simulink", Mathworks.com, 2018. [Online]. Available: https://www.mathworks.com/help/vision/ug/camera-calibration.html. [Accessed: 18- May- 2018].
[13] Z. Zhang, “Flexible Camera Calibration by Viewing A Plane from Unknown Orientations,” in Proc. IEEE Int. Conf. Comput. Vis., Sep. 1999, vol. 1, pp. 666–673.
[14] A. Geiger, F. Moosmann, Ö. Car and B. Schuster, "Automatic Camera and Range Sensor Calibration Using A Single Shot," 2012 IEEE International Conference on Robotics and Automation, Saint Paul, MN, 2012, pp. 3936-3943.
[15] C. Harris, M. Stephens, "A Combined Corner and Edge Detector", Proceedings of the Alvey Vision Conference, pp. 23.1-23, 1988.
[16] J. Shi and C. Tomasi, "Good Features to Track," 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, 1994, pp. 593-600.
[17] I. Sobel, “An Isotropic 3x3 Image Gradient Operator,” Present. Stanf. AI Proj. 1968, 1968.
[18] D. Comaniciu and P. Meer, "Mean Shift: A Robust Approach Toward Feature Space Analysis," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, May 2002.
[19] D. G. Lowe, "Object Recognition from Local Scale-Invariant Features," Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, 1999, pp. 1150-1157 vol.2.
[20] D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[21] J. J. Koenderink, “The Structure of Images,” Biol. Cybern., vol. 50, pp. 363–370, 1984.
[22] T. Lindeberg, Scale-Space Theory in Computer Vision (Kluwer Int. Ser. in Engineering and Computer Science). Boston, MA: Kluwer, 1994.
[23] K. Mikolajczyk, C. Schmid, "An Affine Invariant Interest Point Detector", ECCV., vol. 1, pp. 128-142, 2002.
[24] C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proc. Fourth Alvey Vision Conf., vol. 15, pp. 147-151, 1988..
[25] M. A. Fischler and R. C. Bolles, “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Commun. ACM, vol. 24, pp. 381-396, June 1981.
[26] Q.T. Luong, Matrice fondamentale et autocalibration en vision par ordinateur, Dec. 1992.
[27] H. C. Longuet-Higgins, "A Computer Program for Reconstructing A Scene from Two Projections", Nature, vol. 293, pp. 133-135, 1981.
[28] 楊子頤，"一個利用影像組的共同主平面之強健 Fundamental Matrix 計算法"，清華大學電機工程學系碩士論文，新竹，民國94年10月。
[29] R. Hartley and A. Zisserman, Multiple view geometry in computer vision. Cambridge: Cambridge University Press, 2003.
[30] R. I. Hartley, "An Investigation of The Essential Matrix", GE CRD Schenectady NY Tech. Rep, 1995.
[31] G. Golub and C. Van Loan, Matrix computations. 2013.
[32] O. FAUGERAS and F. LUSTMAN, "Motion and Structure from Motion in A Piecewise Planar Environment ", International Journal of Pattern Recognition and Artificial Intelligence, vol. 02, no. 03, pp. 485-508, 1988.
[33] E. Malis and M. Vargas. Deeper Understanding of The Homography Decomposition for Vision-Based Control. Research Report 6303, INRIA, 2007.
[34] O. Sorkine-Hornung, M. Rabinovich, Least-Squares Rigid Motion Using SVD, 2017, [online] Available: https://igl.ethz.ch/projects/ARAP/svd_rot.pdf.
[35] X. S Gao, X. R Hou, J. Tang and H. F Cheng, "Complete Solution Classification for The Perspective-Three-Point Problem," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 8, pp. 930-943, Aug. 2003.
[36] W.T. Wu, Basic Principles of Mechanical Theorem Proving in Geometries, vol. I: Part of Elementary Geometries, Beijing: Science Press, (in Chinese), 1984, English version, Berlin: Springer, 1995.
[37] B. Triggs, P. F. McLauchlan, R. I. Hartley, A. W. Fitzgibbon, B. Triggs, A. Zisserman, R. Szeliski, "Bundle Adjustment - A Modern Synthesis" in Vision Algorithms: Theory and Practice ser. Lecture Notes in Computer Science, Springer Berlin Heidelberg, vol. 1883, pp. 298-372, 2000.