本論文提出應用二階最小平方法所求得的迴歸線估算由無人空拍機所拍攝的區域影像之土地面積，利用空拍機的優勢，可於較不易步行進入之危險區域進行拍攝，獲取其區域及空拍機的狀態資訊，並可根據使用者的操作達到各角度及高度的拍攝，以獲取多樣化的資訊。
本方法首先使用空拍機蒐集各高度區間之操場草地區塊影像，在70至120公尺間進行數組相同面積之操場草地區塊影像之拍攝；影像處理部分首先設置感興趣區域，接著使用邊緣檢測及形態學處理找出部分區域範圍，並計算此範圍內的連通區域像素數目，便可得出此區域在不同高度下，每一像素數代表實際面積之多寡，根據此數據可推導出二階最小平方迴歸線，如此在已知高度下的空拍影像便能根據此法推算出某區域土地之實際面積。其平均誤差率約為5%以下。

This thesis proposes a method to measure region area in the field by using aerial images. The second order least squares regression line is applied in this research. An unmanned aerial vehicle (UAV) and image processing technology is used to capture images of the land and estimate area. The main advantage of using UAV to capture images is the higher degree of freedom; it can accord user's operation to capture from various angles and heights to obtain more diversified information. Even taking pictures of a dangerous area, the user can remotely control UAV in a safer place, and get the information of the area or the UAV in real time.
In the experiment, an UAV is used to get images of the playground grassland which region area has been known, and capture a series of images in this place with different height from 70 to 120 every ten meters. In image processing process, edge detection and morphology are used to find the range of the interest region, and then count the number of pixels of it. We can get the relation between the different height and per pixels of the real area. With the second order least square regression line theorem, we can estimate the unknown region area of field by the horizon height of the aerial images. Experimental results show that the average deviations of estimating unknown area are less than 5%.

摘要　i
ABSTRACT　ii
目錄　iii
圖目錄　vii
表目錄　x
第一章　緒論　1
1.1研究背景與動機　1
1.2研究方法　3
1.3論文架構　5
第二章　影像處理技術　6
2.1影像變形校正　6
2.2色彩空間轉換　7
2.2.1 RGB色彩空間　7
2.2.2 HSV色彩空間　8
2.3影像增強　9
2.3.1直方圖等化　10
2.3.2邊緣銳利化　11
2.4色彩成分轉換 12
2.4.1灰階影像 12
2.4.2影像二值化 13
2.5感興趣區域及邊緣檢測　14
2.5.1感興趣區域　14
2.5.2邊緣檢測 15
2.6形態學處理　16
2.6.1侵蝕處理　17
2.6.2膨脹處理　18
2.6.3斷開處理　19
2.6.4閉合處理　20
2.7連通區域標記法　22
第三章　空拍影像資料彙整　23
3.1空拍影像蒐集　23
3.2區域面積與像素數關係彙整　31
3.2.1像素數計算　31
3.2.2二階最小平方法　32
第四章　實驗結果　34
4.1實驗用空拍機及測距輪介紹　34
4.1.1無人空拍機　34
4.1.2測距輪　36
4.2實驗結果與分析　38
4.2.1實驗結果分析比較　38
4.2.2 Google Earth Pro衛星影像估算面積　40
4.2.3最小平方迴歸線比較　41
4.2.4土地面積估算　44
4.2.5高度45公尺　45
4.2.6高度90公尺 46
4.2.7高度100公尺 47
4.2.8高度110公尺 48
4.2.9高度120公尺 49
4.2.10湖泊面積估算　50
4.2.11高度40公尺　51
4.2.12高度50公尺　52
4.2.13高度60公尺　53
4.2.14高度70公尺　54
4.2.15高度80公尺　55
4.2.16高度120公尺　56
第五章　結論與未來展望　57
5.1結論　57
5.2未來展望　57
參考文獻　58

[1] 林昱宏，遙控載具錄影及遙測影像於紅樹林植群變遷監測之研究，國立中興大學，土木工程學系，碩士論文，2002。
[2] 劉家仁，應用影像處理技術於空拍影像之地表區域面積估算，國立彰化師範大學，電機工程學系，碩士論文，2016。
[3] 劉震昌，數位影像處理，新加坡商聖智學習亞洲私人有限公司，2010。
[4] 葉倍宏，MATLAB 7程式設計─基礎篇，全華圖書股份有限公司，2009。
[5] 蔡福泰，數位影像相關係數法於鏡頭扭曲校正之應用，國立高雄大學，土木與環境工程學系碩士班，碩士論文，2012。
[6] Janne Heikkilä and Olli Silvén, “A Four-step Camera Calibration Procedure with Implicit Image Correction,” Computer Vision and Pattern Recognition, 1997. Proceedings, 1997 IEEE Computer Society Conference on, pp. 1106-1112, 1997.
[7] Xiaochuan Zhao, Qingsheng Luo, Baoling Han and Xiyu Li, “An Image Distortion Correction Algorithm based on Quadrilateral Fractal Approach Controlling Points,” 2009 4th IEEE Conference on Industrial Electronics and Applications, pp. 2676-2681, 2009.
[8] Giovanni Motta, Erik Ordentlich and Ignacio Ramirez, “The iDUDE Framework for Grayscale Image Denoising,” IEEE Transactions on Image Processing, pp.1-21, 2011.
[9] Nobuyuki Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions On Systems, Man, And Cybernetics, vol. Smc-9, no. 1, pp. 62-66, 1979.
[10] M. A. Rahman, I. K. Edy Purnama and M. H. Purnomo, “Simple method of human skin detection using HSV and YCbCr color spaces,” Intelligent Autonomous Agents, Networks and Systems (INAGENTSYS), 2014 IEEE International Conference on, pp. 58-61, 2014.
[11] 陳仕銘，基於色彩空間調變及粒子濾波器實現目標影像追蹤之研究，國立彰化師範大學，電機工程學系，碩士論文，2012。
[12] F. Liu, X. Liu and Y. Chen, “An efficient detection method for rare colored capsule based on RGB and HSV color space,” Granular Computing (GrC), 2014 IEEE International Conference on, pp. 175-178, 2014.
[13] Mariví Tello Alonso, Carlos López-Martínez, Jordi J. Mallorquí and Philippe Salembier, “Edge Enhancement Algorithm Based on the Wavelet Transform for Automatic Edge Detection in SAR Images,” IEEE Transactions on Geoscience and Remote Sensing, vol.49, no.1, pp. 222-235, 2010.
[14] W. Wang, Y. He, Z. Li and Z. Chen, “A real-time target detection algorithm for Infrared Search and track system based on ROI extraction,” in Signal Processing, Communication and Computing (ICSPCC), 2012 IEEE International Conference on, pp. 774-778, 2012.
[15] I. Barbancho, C. Segura, L. J. Tardon and A. M. Barbancho, “Automatic selection of the region of interest in ancient scores,” in MELECON 2010 - 2010 15th IEEE Mediterranean Electrotechnical Conference, pp. 326-331, 2010.
[16] Yitzhak Yitzhaky and Eli Peli, “A Method for Objective Edge Detection Evaluation and Detector Parameter Selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.25, no.8, pp. 1027-1033, 2003.
[17] Tian Qiu, Yong Yan and Gang Lu, “An Autoadaptive Edge-Detection Algorithm for Flame and Fire Image Processing,” IEEE Transactions On Instrumentation And Measurement, vol. 61, no. 5, pp. 1486-1493, 2012.
[18] F.A. Pellegrino, W. Vanzella, V. Torre, “Edge detection revisited,” IEEE Transactions on Systems, Man, and Cybernetics, vol.34, no. 3, pp.1500-1518, 2004
[19] Bo Peng, Lei Zhang, and David Zhang, “Automatic Image Segmentation by Dynamic Region Merging,” IEEE Transactions on Image Processing, vol.20, no.12, pp. 3592-3605, 2011.
[20] Qin Zhang and Roger Skjetne, “Image Processing for Identification of Sea-Ice Floes and the Floe Size Distributions,” IEEE Transactions on Geoscience and Remote Sensing, vol.53, no.5, pp. 2913-2924, 2014.
[21] 莊鈺平，應用FPGA程式設計於色彩特徵值擷取系統，國立彰化師範大學，電機工程學系，碩士論文，2015。
[22] Tyan Vladimir, Dongwoon Jeon, Doo-Hyun Kim, Chun-Hyon Chang and Jungguk Kim, “Experimental Feasibility Analysis of ROI-Based Hough Transform for Real-Time Line Tracking in Auto-Landing of UAV,” Object/Component/Service-Oriented Real-Time Distributed Computing Workshops (ISORCW), 2012 15th IEEE International Symposium on, pp. 130-135, 2012.
[23] Jiantao Bi, Wenbo Mao and Yuejian Gong, “Research on image mosaic method of UAV image of earthquake emergency,” Agro-geoinformatics (Agro-geoinformatics 2014), Third International Conference on, pp. 1-6, 2014.
[24] Shubha Bhat, Vindhya P Malagi, Ramesh Babu D R, Ramakrishna K A and Ravishankar M, “Scale weight selection for feature extraction using complex wavelets: A framework,” Image Information Processing (ICIIP), 2011 International Conference on, pp. 1-5, 2011.
[25] Larson/Falvo, Elementary Linear Algebra Sixth Edition, Brook/Cole Cengage Learning, 2010.