臺灣博碩士論文加值系統

無人飛行載具的降落階段是整個飛行任務中最為關鍵的。手動降落兼具困難度及風險，自動降落成了重要課題。本文建立一套利用電腦視覺輔助無人機自動降落系統，辨識跑道上所架設的四盞紅色跑道燈，估測無人機相對於跑道的位置資訊，改善跑道辨識的策略，提升跑道辨識的強健性。使用可移式燈具作為辨識目標物在昏暗環境，甚至夜間，能有較好的辨識能力，不僅增加使用的機動性，不必對跑道完整調查。機體位置姿態估算演算法除了橫向偏移量之外，可得縱向高度，與跑道頭的水平距離，以及三個機體姿態角。在距離跑道頭400m處的橫向估測誤差小於2m，影像處理速度高於24fps。同時探討相機裝置角誤差對於姿態估測的效應，以及不同環境照度下的辨識效果及能力。

The most critical phase of a UAV flight mission is landing. It’s not only hard to recognize the runway from camera in dusk or overcast environments, even at night, but also the pilot is difficult to do visual approach and landing manually. This paper present a computer vision-based automatic landing assistant system for fixed-wing UAV. By recognizing four red runway lights on the edges of the runway to estimate the lateral offset, vertical height, horizontal distance relative to runway head, and three attitude angles. The advantages are to gain flexible usage and not to need to survey runway completely. At a distance of 400m from runway head, the estimation error of lateral offset less than 2m with frame rate greater than 24fps. Also discussed the effect between the angle of setting camera error and pose estimation, and the recognition ability in the different luminance of environment.

1.封面
2.書名頁I
3.中文摘要II
4.英文摘要III
5.誌謝IV
6.目錄V
7.表目錄VIII
8.圖目錄IX
9.符號說明XI
10.論文本文1
11.參考文獻42

[1] Visually Guided Landing of an Unmanned Aerial Vehicle, Srikanth Saripalli, James F. Montgomery, Gaurav S. Sukhatme, University of Southern California, Los Angeles, USA, 2003
[2] Vision Aided Automatic Landing System for Fixed Wing UAV,Maximilian Laiacker, Konstantin Kondak, Marc Schwarzbach and Tin Muskardin,German Aerospace Center, Wessling Germany, 2013
[3] Fully Autonomous Vision-Based Net-Recovery Landing System for a Fixed-Wing UAV, H. J. Kim, M. Kim, H. Lim, C. Park, S. Yoon , D. Lee, H. Choi, G. Oh, J. Park, Y. Kim, Seoul National University, Seoul, Korea, 2013
[4] Airborne Vision-Aided Landing Navigation System for Fixed-Wing UAV,Pengyu Guo , Xin Li , Yang Gui , Xiang Zhou , Hongliang Zhang , Xiaohu Zhang, 2014
[5] Mobile Standards-Based Traffic Light Detection in Assistive Devices for Individuals with Color-Vision Deficiency, Akhan Almagambetov, Aeronautical University, USA, 2014
[6] 以影像識別方法進行跑道偵測於固定翼無人飛機之實現，國立成功大學，黃佩瑩，民國98年
[7] 機器視覺於跑道辨識以導引無人機近場與降落，國立成功大學，周威宇，民國104年
[8] 無人飛機自動降落之飛行控制導引技術與策略之研究與實作，元智大學，林能祺，民國98年
[9] 無人飛機影像辨識輔助降落系統，元智大學，張展維，民國101年
[10] 利用影像辨識輔助無人飛機自動降落之策略研究，元智大學，林偉傑，民國102年
[11] OpenCV documentation http://opencv.org/documentation.html
[12] OpenCV 2 computer Vision Application Programming Cookbook, Robert Laganière, 2011
[13] Computer and Robot Vision, Linda G. Shapiro, Robert M. Haralick, 1992
[14] Digital Image Processing 2nd Edition, Rafael C. Gonzalez, Richard E. Woods, 2002