臺灣博碩士論文加值系統

無人機飛行在近年來已經廣泛的被運用在各種領域，利用機械視覺(Machine vision)來實現自動空中攝影也是其中之一，如何正確的自動降落在指定的地點也成為熱門的研究問題。本論文利用影像處理技術從拍攝的影像中正確的找到停機坪的標誌，讓無人機可以降落到指定的位置。利用加速度穩健特徵(SURF)找出停機坪的特徵點，再利用歐式距離量測模板影像跟檢測影像找出來的SURF特徵點之相似度，保留相似度高的特徵點。找到特徵點後，使用RANSAC方法來估計仿射矩陣的轉換模型來找出大略的停機坪位置。為了更進一步鎖定目標，我們利用找尋輪廓的大小關係和細線化去除背景，再利用霍夫變換來做最後的校正。因為有先例用感興趣區域來縮小處理範圍，可以大幅加快處理速度和準確度。實驗結果顯示論文提出的系統有足以用來做即時檢測的高處理速度和高辨識成功率。

Unmanned Aerial Vehicle (UAV) has been widely used in various fields during the past decades. Using machine vision to achieve the automatic photographing and automatic landing becomes an active research area. In this thesis, we use Speeded-Up Robust Features (SURF) to find the feature points of the heliport, and then use Random Sample Consensus (RANSAC) to find the affine transform model between template image and real-time image to find the heliport. In order to locate the heliport more accurately, we use contours finding and image thinning algorithms to reduce noises and use Hough transform to locate the heliport. Our method uses ROI to reduce the processing area, so the processing speed and detection rate can be improved. The results show that the proposed system has high processing speed and detection rate for real-time automatic landing system.

摘要 i
ABSTRACT ii
致謝 iii
CONTENS iv
LIST OF FIGURES vi
CHAPTER 1 INTRODUCTION 1
1.1 Introduction 1
1.2 Research purposes 2
CHAPTER 2 BASIC IMAGE PROCESSING KNOWLEDGE 4
2.1 Introduction 4
2.2 Image thinning and finding skeleton 4
2.3 Contours finding 8
CHAPTER 3 INTEREST AREA DETECTION 12
3.1 Introduction 12
3.2 Speeded-UP Robust Feature (SURF) 12
3.2.1 Detect the feature 12
3.2.2 Interest feature point description and matching 20
3.3 Hough Transform 25
3.3.1 Hough circle transform 25
3.4 Affine transformation and Random Sample Consensus 28
3.4.1 Random Sample Consensus (RANSAC) 29
3.4.2 Affine transformation 29
3.4.3 Using RANSAC to find affine transformation 30
CHAPTER 4 RESULTS AND ANALYSIS 32
4.1 Introduction 32
4.2 Image pre-processing 33
4.3 Finding the feature points and locating the ROI 34
4.4 Detecting the circle 39
4.5 Simulation 45
4.6 Comparing the processing speed 50
CHAPTER 5 CONCLUSION AND FUTURE WORK 52
5.1 Conclusion 52
5.2 Future work 52
REFERENCES 53

REFERENCES
[1] F. Alarcon, D. Santamaria and A. Viguria. “UAV helicopter relative state estimation for autonomous landing on moving platforms in a GPS-denied scenario,” IFAC-PapersOnLine, Vol. 48, Issue 9, pp. 37-42, 2015.
[2] L. Rosa, T. Hamel, R. Mahony and C. Samson. “Optical-Flow Based Strategies
for Landing VTOL UAVs in Cluttered Environments,” IFAC Proceedings Volumes, Vol. 47, Issue 3, pp. 3176-3183, 2014.
[3] Y. Zhu, Z. Cao, H. Lu and Y. Li. “In-field automatic observation of wheat heading stage using computer vision,” Biosystems Engineering, Vol. 143, pp. 28-41, 2016.
[4] X. Cui, Q. Wu, and J. Zhou. “Online fragments-based scale invariant electro-optic tracking with SIFT,” Optik - International Journal for Light and Electron Optics, Vol. 126, Issue 18, pp. 1720-1725, 2015.
[5] 王君如, “ A Geometric Correction Method for Image Stitching in UAV Images,” 逢甲大學電機系碩士論文，台灣碩博士論文，2014.
[6] T. Zhengyuan, Z. Jiajia, Y. Jie, L. Erqi and Z. Yue. “Infrared target tracking algorithm based on sparse representation model,” Infrared and Laser Engineering, 2012.
[7] T. Y. Zhang and C. Y. Suen. “A fast parallel algorithm for thinning digital pattern,” Communications of the ACM, Vol. 27, No. 3, pp. 236-239, 1984.
[8] D. M. K. K. V. Rao and Tiauw Hiong Go. “Automatic landing system design using sliding mode control,” Aerospace Science and Technology, Vol. 32, Issue 1, pp. 180-187, 2014.
[9] Satoshi Suzuki and KeiichiA be. “Topological structural analysis of digitized binary images by border following,” Computer Vision, Graphics, and Image Processing, Vol. 30, Issue 1, pp. 32-46, 1985.
[10] H. Bay, A. Ess, T. Tuytelaars and L. Van Gool. “Speeded-Up Robust Features (SURF),” Computer Vision and Image Understanding, vol. 110, pp. 346-359, 2008.
[11] D. G. Lowe. “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, Vol. 60, Issue 2, pp. 91-110, 2004.
[12] Richard O. Duda and Peter E. Hart. “Use of the Hough Transform to Detect Lines and Curves in Pictures,” Communications of the ACM, Vol. 15, Issue 1, pp. 11-15, 1972.
[13] P.V.C. Hough. “Method and Means for Recognizing Complex Patterns,” US Patent 3,069,654, 1962.
[14] Martin A. Fischler and Robert C. Bolles. “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Communications of the ACM, Vol. 24, Issue 6, pp. 381-395, 1981.
[15] Nobuyuki Otsu. “A Tlreshold Selection Method from Gray-Level Histograms,” Systems, Man and Cybernetics, IEEE Transactions on, vol. 9, no. 1, pp. 62-66, 1979.
[16]“霍夫轉換算法原理，” Available: http://140.115.11.235/~chen/course/vision/ch8/
ch8.htm, 2004.
[16] “Hough Transform,”Available: http://docs.opencv.org/2.4/doc/tutorials/imgpro
c/imgtrans/hough_lines/hough_lines.html, 2016.
[17] “SURF,”Available: http://docs.opencv.org/2.4/modules/nonfree/doc/feature_de
tection.html?highlight=surf#cv2.SURF, 2016.
[18] 劉海波、沈晶，Visual C++ 數字圖像處理技術詳解。
[19] 毛星雲、冷雪飛，OPENCV3編成入門。
[20] 鄭明傑，應用機器視覺於生產線之電阻即時檢測系統，國立高雄應用科技大學電機工程學系碩士論文，台灣碩博士論文，2014。
[21] 曹榮傑，基於 Android 平台的車牌辨識合成系統，國立高雄應用科技大學電機工程學系碩士論文，台灣碩博士論文，2015。
[22] 柯孜澄，影像辨識系統應用於直升機自動降落系統，國立高雄應用科技大學電機工程學系碩士論文，台灣碩博士論文，2013。
[23] J. G. A. Barbedo. “Using digital image processing for counting whiteflies on soybean leaves,”Journal of Asia-Pacific Entomology, 2014.
[24] M. Karaşahin, M. Saltan and S. Çetin. “Determination of seal coat deterioration using image processing methods,” Construction and Building Materials, Vol. 53, pp. 273-283, 2014.