近年來，無人旋翼機已被廣泛的應用於軍事或民間商業任務。因無人旋翼機能夠執行較複雜之任務，如搜救、未知環境之監測與勘查，重點建築與道路之鑑別等。本文之研究目標在於建立一個影像導航系統，使無人旋翼機僅使用攝影機的情況下進行準確導航。由於此系統於開發期間具備大量不確定因素，可能導致系統開發延宕，其中包含無人旋翼機的控制。因此，本文的實驗首先排除無人飛行器，將系統置於實驗之雙軸軸控平台進行測試，模擬無人飛行器於空中定姿態的飛行狀況。本系統經實驗證實，僅需搭配攝影機以導航所需之樣版地圖，毋須搭配常見之感測器諸如：GPS、羅盤，或者慣性導航儀…等，即足以執行導航任務。

Recent years , UAV(unmanned aerial vehicle) has been widely applied in military and civil missions. UAV can enforce complex missions like rescuing , unknown environment surveying , building and road recognition. The goal of this study is to establish a visual navigation system . The system provides UAV the ability navigates accurately only with visual information. But the process of development may postponed by unknown fact during developing. In these facts, the control of UAV is a possible reason . Therefore, the experiments in this study the system primarily and simulates the situation of UAV flying with firm pose in dual-axis-experiment platform. The system developed in this study only need a camera and model map which is necessary for navigation , the result proofed the system is work well, without other common sensors like GPS ,Compass, inertial navigation system (INS).

[1] D. G. Lowe, “Object recognition from local scale-invariant features” Proceedings of the International Conference on Computer Vision 2.pp. 1150–1157,1999.
[2] D. G. Lowe, “ Distinctive Image Features from Scale-Invariant Keypoints” International Journal of Computer Vision 60(2).pp. 91–110, 2004.
[3] B.D. Lucas and T. Kanade, “ An iterative image registration technique with an application to stereo vision” DARPA Image Understanding Workshop.pp.121-130,1981.
[4] B.K.P. Horn and B.G. Schunk, “ Determing optical flow” Artificial Intellignece.Vol 17 .pp. 185-203,1981.
[5] S .Smith and J. Brady , “SUSAN. SUSAN—A New Approach to Low Level Image Processing” International Journal of Computer Vision 23(1).pp.45–78,1997.
[6] E. Rosten and T. Drummond, “ Fusing Points and Lines for High
Performance Tracking” Int l0 IEEE International Conference on Computer Vision. Volume 2.pp. 1508–1515,2005.
[7] E. Rosten, R. Porter, and T. Drummond, “ Faster and better: A machine learning approach to corner detection” IEEE Trans. Pattern Analysis and Machine Intelligence 32.pp.105– 119, 2010.
[8] H. Durrant-Whyte and T. Bailey, “ Simultaneous localisation and mapping (SLAM): Part I” IEEE Robot. Autom Mag. vol. 13. pp. 99–110, 2006.
[9] H.F. Durrant-Whyte, “ Uncertain geometry in robotics” IEEE Trans.Robot Automat., vol. 4. pp. 23–31, 1988.
[10] R. Smith and P. Cheesman , “ On the representation of spatial uncertainty” Int. J. Robot. Res .pp.56–68, 1987.
[11] C. G. Rafael and E. W. Richard, “Digital Image Processing Third Edition” Prentice Hall .pp.69-77. 2010.
[12] P. V. C. Hough, “Methods and means for recogninzing complex pat-terns” U.S. Patent 3-069-654, 1962.
[13] T. Lindeberg, “Scale-space theory: A basic tool for analysing structures at different scales” J.Appl Stat.21(2).pp.225-270 ,1994.
[14] R. Hartley and A. Zisserman, “Multiple View Geometry in computer vision” Cambridge University Press. pp. 32–33.2004.
[15] D. J. Fleet, Y. Weiss, “Optical Flow Estimation” Mathematical Models in Computer Vision:The Handbook.pp.239-258, 2005.
[16] J.Y. Bouguet, “Pyramidal Implementation of the Lucas Kanade Feature Tracker” Cambridge University Press. pp. 32–33.2000.
[17] L. Kitchen and A. Rosenfeld, “Analysis of Gray Level Corner Detection” Description of the algorithm Processing. Int. Journal of Compuer Vision 23(1) .pp.45-78, 1997. 　　
[18] C. Harris and M. Stephens, “A Combined Corner and Edge Detector Manchester” Proceedings of the 4th Alvey Vision Conference.pp. 147-151, 1988.
[19] J. Shi and C. Tomasi, “Good Features to Track” IEEE Conference on Computer Vision and Pattern Recognition. pp. 593-600, 1994.