近年來，植保無人機已漸漸商業化並廣泛於各種國家中進行使用，眾多廠商爭相投入研發，如大疆等公司已開發出可用於各種場合的各式無人機。在美國，以飛機搭載農藥並以空中投放農藥的方式進行農藥噴灑的方法已臻成熟，然而此種方法的限制便是噴灑農藥的農地須幅員遼闊才可以達到使用飛機有效率地噴灑農藥，若農地狹小且破碎，此種方法將不再可行，而台灣的梯田或是坡地更是限制了此種方法的實行。相對於條件較為嚴苛的使用飛機噴灑農藥方法，以植保無人機進行農藥噴灑的方式在台灣，因其更具彈性，可以應對台灣的主流農地地形，因此成為農民噴灑農藥時的選擇之一，近年來台灣農業從業人口老化，勞動力不足，且坡地地形需大量勞動力進行農藥噴灑，而傾斜的地勢也容易造成意外事故的發生，若以植保無人機進行，可節省勞動力，同時也保障了農民的安全。
本研究以各種多光譜圖片進行觀測與紀錄，使用最大概似估計法對多光譜的各種圖像進行物件的分類，在圖像的一隅找出特定物件在多光譜圖像中所呈現的特徵，並使用最大概似估計推估出整張多光譜圖像中各個物件的分布區域，並特別凸顯出龍眼樹的分布區域。
根據龍眼樹的分布大小及位置，以市售植保無人機的噴灑範圍為基準，設計出數個能保證植保無人機完整噴灑農藥於果樹的點作為無人機飛行時懸停的區域，並將這些點的座標以蟻群演算法中的蟻群系統進行路徑規劃，根據多次測試，測量出能經過所有懸停區域的最佳路徑。

In recent years, the agricultural population in Taiwan has been aging and the labor force is insufficient. The slope topography requires a large amount of labor to spray pesticides, and the inclined terrain is also likely to cause accidents. If planted with drones, it can save labor and protect farmers. Safety.
In this study, various multi-spectral images are used for observation and recording. The most approximate estimation method is used to classify various images of multi-spectral images, and the features of specific objects in multi-spectral images are found at a glance of the image. And use the most approximate estimation to estimate the distribution of each object in the entire multi-spectral image, and highlight the distribution of the longan tree.
According to the distribution size and location of the longan tree, based on the spray range of the commercially available plant protection drones, several points are designed to ensure that the plant protection drone completely sprays the pesticides on the fruit trees as the hovering area of the drone during flight. The coordinates of the points are routed by the ant colony system in the ant colony algorithm. According to multiple tests, the best path that can pass through all hovering areas is measured.

[1] 公務預算處、基金預算處、綜合規劃處、會計決算處、綜合統計處、國勢普查處、主計資訊處 (2017 , 03)。〈104 年農林漁牧業普查初步統計結果〉。行政院主計總處，17(3)，頁1-4。
[2] 公務預算處、基金預算處、綜合規劃處、會計決算處、綜合統計處、國勢普查處、主計資訊處 (2017 , 03)。〈104 年農林漁牧業普查報告 初步綜合報告摘要〉。行政院主計總處，17(3)，頁2-6。
[3] Kim, Hyeon-Hye, et al. "Green-light supplementation for enhanced lettuce growth under red-and blue-light-emitting diodes." HortScience 39.7 (2004): 1617-1622.
[4] Nilsson, H. "Remote sensing and image analysis in plant pathology." Annual review of phytopathology 33.1 (1995): 489-528.
[5] Horler, D. N. H., Mo DOCKRAY, and J. Barber. "The red edge of plant leaf reflectance." International Journal of Remote Sensing 4.2 (1983): 273-288.
[6] Filella, I., and J1 Penuelas. "The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status." International Journal of Remote Sensing 15.7 (1994): 1459-1470.
[7] Eitel, Jan UH, et al. "Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland." Remote Sensing of Environment 115.12 (2011): 3640-3646.
[8] Micasense (2019, August 17). An overview of the available layers and indices in Atlas Retrieved August 17, 2019, from the World Wide Web: https://support.micasense.com/hc/en-us/articles/227837307#ndre
[9] Hamel, Sandra, et al. "Spring Normalized Difference Vegetation Index (NDVI) predicts annual variation in timing of peak faecal crude protein in mountain ungulates." Journal of Applied Ecology 46.3 (2009): 582-589.
[10] Micasense (2019, August 17). An overview of the available layers and indices in Atlas. Retrieved August 17, 2019, from the World Wide Web: https://support.micasense.com/hc/en-us/articles/227837307#ndvi
[11] Eric Taipale. (2019). NDVI VS. NDRE: WHAT’S THE DIFFERENCE?. Retrieved May 01, 2019, from the World Wide Web: https://sentera.com/ndvi-vs-ndre-whats-difference/
[12] Socolinsky, Diego A., and Lawrence B. Wolff. "Multispectral image visualization through first-order fusion." IEEE transactions on image processing 11.8 (2002): 923-931.
[13] Running, Steven W., et al. "A remote sensing based vegetation classification logic for global land cover analysis." Remote sensing of Environment 51.1 (1995): 39-48.
[14] Gandhi, G. Meera, et al. "NDVI: vegetation change detection using remote sensing and GIS–a case study of Vellore District." Procedia Computer Science 57 (2015): 1199-1210.
[15] Ahmad, Asmala, and Shaun Quegan. "Analysis of maximum likelihood classification on multispectral data." Applied Mathematical Sciences 6.129 (2012): 6425-6436.
[16] T.M. Lillesand, R.W. Kiefer and J.W. Chipman, Remote Sensing and Image Interpretation, John Wiley & Sons, Hoboken, NJ, USA, 2004.
[17] J.A. Richards, Remote sensing digital image analysis: An introduction. Springer-Verlag, Berlin, Germany, 1999.
[18] Themistocleous, Kyriacos, et al. "The methodology of documenting cultural heritage sites using photogrammetry, UAV, and 3D printing techniques: the case study of Asinou Church in Cyprus." Third International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2015). Vol. 9535. International Society for Optics and Photonics, 2015.
[19] McEvoy, John F., Graham P. Hall, and Paul G. McDonald. "Evaluation of unmanned aerial vehicle shape, flight path and camera type for waterfowl surveys: disturbance effects and species recognition." PeerJ 4 (2016): e1831.
[20] Guan, Senlin, et al. "Assessing Correlation of High-Resolution NDVI with Fertilizer Application Level and Yield of Rice and Wheat Crops using Small UAVs." Remote Sensing 11.2 (2019): 112.
[21] Unger, Jakob, Martin Reich, and Christian Heipke. "UAV-based photogrammetry: monitoring of a building zone." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences-ISPRS Archives 40 (2014) 40.5 (2014): 601-606.
[22] Priestnall, G., J. Jaafar, and A. Duncan. "Extracting urban features from LiDAR digital surface models." Computers, Environment and Urban Systems 24.2 (2000): 65-78.
[23] Nex, Francesco, and Fabio Remondino. "UAV for 3D mapping applications: a review." Applied geomatics 6.1 (2014): 1-15.
[24] Aarts, Emile HL, Jan HM Korst, and Peter JM van Laarhoven. "A quantitative analysis of the simulated annealing algorithm: A case study for the traveling salesman problem." Journal of Statistical Physics 50.1-2 (1988): 187-206.
[25] Dorigo Marco, Vittorio Maniezzo, and Alberto Colorni. "Ant system: optimization by a colony of cooperating agents." IEEE Transactions on Systems, man, and cybernetics, Part B: Cybernetics 26.1 (1996): 29-41.
[26] Dorigo, Marco, and Luca Maria Gambardella. "Ant colony system: a cooperative learning approach to the traveling salesman problem." IEEE Transactions on evolutionary computation 1.1 (1997): 53-66.
[27] 邱智遠. 應用混合式分類法融合光達高度資料於都市地物分類之研究. Diss. 撰者, 2008.
[28] Suzuki, Satoshi. "Topological structural analysis of digitized binary images by border following." Computer vision, graphics, and image processing 30.1 (1985): 32-46.
[29] Dorigo, Marco, and Luca Maria Gambardella. "Ant colonies for the travelling salesman problem." biosystems 43.2 (1997): 73-81.
[30] Stützle, Thomas, et al. "Parameter adaptation in ant colony optimization." Autonomous search. Springer, Berlin, Heidelberg, 2011. 191-215.