本研究針對地面目標物精準定位，利用SURF以特徵匹配方式偵測地面目標物，定義目標物座標系將影像的對應點透過內方位參數投影到相機座標系，同時RANSAC以Homography作為模型剔除不可靠的對應點，計算座標系間的Homography轉換矩陣，最後解Homography參數得到在目標物座標系相機對地面目標物六個自由度參數的相對關係(平移與旋轉)，只要影像與目標有足夠的對應點，無論周圍有無雜物，都可以成功辨識目標物與相機與計算目標物的相對方位。以UAV掛載相機及飛時(ToF)測距感測器偵測高度討論成果，飛行高度與相機解析度直接影響匹配成果，在解析度足夠且獲得足夠特徵點的情況降低運算階層可以不影響計算Homography轉換成果增加運算效能。未來可以延伸應用在UAV降落、目標物追蹤、目標定位執行投擲任務，多架無人機停機坪設計等等。

SURF is used to search correspondences between image captured by camera and the ground target. No matter how the environment changes, as long as enough correspondences are matched, the target can be recognized successfully. Project correspondences from image coordinate to camera coordinate by using intrinsic matrix. RANSAC based on Homography transform as model is used to discard outliers. After verifying geometric relationship of projected shape between two coordinates via Homography matrix, external parameters are obtained by decomposing Homography matrix. The relative position between camera and the target would be known. UAV equipped with downward camera and time of flight rangefinder which is used to measure height information flies at the different altitude to verify the algorithm. The number of correspondences is influenced by the camera resolution and flight altitude directly. At appropriate camera resolution and flight altitude, the compute efficiency increases robustly by reducing octave number.
The vision algorithm can be used to guide UAV landing autonomously, target tracking or goods delivery precisely in the future.

[1] https://www.faa.gov/uas/
[2] https://www.nasa.gov/
[3] https://www.dji.com/zh-tw
[4] http://www.goldmansachs.com/our-thinking/technology-driving-innovation/drones/ index.html
[5] Hrabar, S. Sukhatme, G. S. Corke, P. Usher, K. Roberts, J. "Combined Optic-flow and Stereo-based Navigation of Urban Canyons for a UAV," Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (lROS 2005), pp. 3309-3316, 2005.
[6] Wendel, J. Meister, O. Schlaile, C. Trommer, G. F. "An Integrated GPS/MEMS-IMU Navigation System for an Autonomous Helicopter," Aerosp. Sci. Technol., vol. 10, no. 6, pp. 527-533, 2006.
[7] Tomic,T. Schmid,K. Lutz,P. Domel, A. Kassecker, M. Mair, E. Grixa,I. L. Ruess, F. Suppa, M. Burschka,D. "Autonomous UAV: Research Platform for Indoor and Outdoor Urban Search and Rescue," IEEE Robot. Autom. Mag., vol. 19, no. 3, pp. 46-56, 2012.
[8] Lange, S, Sünderhauf, N, Neubert, P, Drews, S, Protzel, P "Autonomous Corridor Flight of a UAV Using a Low-cost and Light-weight RGB-D Camera," In: Advances in Autonomous Mini Robots, Proc. 6th AMiRE Symposium, pp.183–192, 2011.
[9] García, L. R. Carrillo, Dzul, A. Lozano, R. and Pégard, C. "Combining Stereo Vision and Inertial Navigation System for a Quad-Rotor UAV," Journal of Intelligent & Robotic Systems, 2011.
[10] Caballero,F. Merino, L. Ferruz, J. and Ollero, A., "Vision-based Odometry and SLAM for Medium and High Altitude Flying UAVs," Journal of Intelligent Robotic Systems, vol. 54, pp. 137-161, 2009.
[11] Sharp,C. Shakernia, O. Sastry, S. "A Vision System for Landing an Unmanned Aerial Vehicle," Proc. IEEE Int. Conf. Robotics and Automation, pp. 1720-1727, 2001.
[12] Lange, S. N. Sünderhauf, P. Protzel, "Autonomous Landing for a Multirotor UAV using Vision", Workshop Proceedings of SIMPAR Intl. Conf. on SIMULATION MODELING and PROGRAMMING for AUTONOMOUS ROBOTS, pp. 482-491, 2008.
[13] Xu,G. Zhang, Y. Cheng, S. Ji, Y. and Tian, Y. "Research on Computer Vision-based for UAV Autonomous Landing on a Ship," Pattern Recognition Letters, vol. 30, no. 6, pp. 600-605, 2009.
[14] Wenzel, K., Masselli, A., & Zell, A. "Automatic Take Off, Tracking and Landing of a Miniature UAV on a Moving Carrier Vehicle" Journal of Intelligent Robotic Systems, 61, 221–238, 2011.
[15] L. Hanseob, J. Seokwoo, H. S. David, "Vision-based UAV Landing on the Moving Vehicle," International Conference on Unmanned Aircraft Systems, 2016.
[16] Chen, X., Phang, S.K., Shan, M., Chen, B.M. "System Integration of a Vision-guided UAV for Autonomous Landing on Moving Platform." In: IEEE international conference on control and automation (ICCA), pp. 761–766 , 2016.
[17] Falanga,D. A. Zanchettin, A. Simovic, J. Delmerico, D. Scaramuzza, "Vision-based Autonomous Quadrotor Landing on a Moving Platform," Proc. IEEE Int. Symp. Safety Security Rescue Robot, pp.200-207, 2017.
[18] Saripalli, S., Sukhatme, G.S. "Landing on a Mobile Target Using an Autonomous Helicopter," In: Proceedings of the International Conference on Field and Service Robotics, 2003.
[19] Sanchez-Lopez, J. L. Pestana,J. Saripalli, S. Campoy, P. "An Approach Toward Visual Autonomous Ship Board Landing of a VTOL UAV," Journal of Intelligent & Robotic System, vol. 74, no. 1–2, pp. 113-127, 2014.
[20] Lin, S., Garratt, M.A., Lambert, A.J. " Monocular Vision-based Real-time Target Recognition and Tracking for Autonomously Landing an UAV in a Cluttered Shipboard Environment", Autonom Robots, pp. 1–21,2016.
[21] Yuan, H., Xiao, C., Zhang, F., Shi, C., Ye, H., Xiu, S., Zhou, C., Li, Q., "Feature Recognition for Initial Pose Estimation to Enhance Vision-based UAV Relative Navigation," International Ocean and Polar Engineering Conference, 2017.
[22] Zhao, Y., Pei, H., "An Improved Vision-based Algorithm for Unmanned Aerial Vehicles Autonomous Landing," Phys. Proced. 33, pp. 935–941, 2012.
[23] Cesetti, A., Frontoni, E., Mancini, A., Zingaretti, P., Longhi, S, "A Vision-Based Guidance System for UAV Navigation and Safe Landing Using Natural Landmarks," J. Intelligient, Robot. Syst. 57(1–4), 233–257, 2010.
[24] Hhien, Y. C. "Visual Navigation Algorithm Development and Simulation," Mater thesis, Institute of Aeronautics and Astronautics, National Cheng Kung University, 2013.
[25] Bay, H., Tuytelaars, T. and Gool L. Van. "SURF: Speeded Up Robust Features," In European Conference on Computer Vision, 2006.
[26] R.C. Gonzalez, R.E. Woods, DigitalImage Processing, Prentice Hall, pp. 424-428, 2007.
[27] Zhengyou, Z. "A flexible New Technique for Camera Calibration", IEEE Transactions on pattern analysis and machine intelligence,22(11):pp.1330–1334,2000.
[28] Kaehler, A, Bradski, G., Learning OpenCV. O’Reilly Media, Sebastopol, 2008.
[29] Lowe, D. G. Distinctive Image Features from Scale-Invariant Key-points, IJCV, 2004.
[30] R. Szeliski, " Computer Vision: Algorithms and Applications", 2010.
[31] R. Hartley, A. Zisserman, " Multiple View Geometry in Computer Vision", 2000.
[32] E. Malis, V. Manuel, "Deeper Understanding of the Homography Decomposition for Vision-based Control," Technical Report, 2007.