虛擬實境(Virtual Reality)的沉浸式體驗能讓使用者有身歷其境的感覺，這一點非常適合用於無人機上來模擬第一人稱的體驗，本研究使用Tello無人機當作載具，並藉由兩套不同的手勢來取代平常操控無人機所需要的搖桿，最後將影像傳到頭戴式裝置上來讓使用者能夠有沉浸式的無人機模擬飛行體驗。
本研究將會詳細敘述研究方法、系統架構以及兩種不同的手勢:光流和法向量。最後以速度與精準度兩種實驗再加上使用者易用性量表的結果來比較兩種手勢的優缺點分析，同時評估整體系統的使用狀況。

The immersive experience of Virtual Reality (VR) allows users to feel as if they are actually present in the simulated environment. This feature makes it very suitable for creating first-person experiences for drone control. In this study, we use Tello drones as the carrier and replace the joystick controls with natural hand gestures. The drone-captured video is then transmitted to a Head-Mounted Display (HMD) to provide an immersive drone flying experience. This study provides a detailed description of the research method, system architecture, and the design of two different sets of hand gestures: Optical Flow and Normal Vector. To evaluate the overall performance of the system, the speed, accuracy, and user usability are analyzed to compare the advantages and disadvantages of the two sets of hand gestures.

誌謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 v
表目錄 vi
第一章 序論 1
第一節 研究動機 1
第二節 研究目的 2
第三節 研究貢獻 3
第二章 文獻探討 4
第一節 虛擬實境技術 4
第二節 Mediapipe 技術 5
第三節 光流 7
第四節 無人機 11
第三章 研究方法 13
第一節 系統架構 13
第二節 影像處理 16
第三節 無人機操作 21
第四節 頭戴式顯示器連接操作 22
第四章 實驗方法 24
第一節 實驗環境 24
第二節 實驗方法 26
第三節 無人機選擇 30
第四節 實驗的分析比較 30
第五章 結論與未來展望 33
第一節 可能的研究方向 33
第二節 可能面臨的困難 33
第三節 可能的應用 34
參考文獻 35
附錄 38

[1] R.Varghese,R.Cherian,S.Ninan,N.Arun,V. Anjusree ,”Automatic Voice Synthesis System using Long Short-Term Memory and Google Mediapipe”in 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 6-8 July 2021,pp.1-5
[2] W.Praditasari,R.Aprilliyani,I.Kholis,”Design and Implementation of Interactive Virtual Museum based on Hand Tracking OpenCV in Indonesia”,in 2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 20-21 Oct. 2021,pp.253 - 256
[3] G.Samhitha,D.Rao,Ch.Rupa,Y.Ekshitha,R.Jaswanthi ,”Vyayam: Artificial Intelligence based Bicep Curl Workout Tacking System”,in 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) , 24-25 September 2021, pp.1 – 5
[4] B.Horn ,B.Schunck” Determining optical flow”in Artificial Intelligence , August 1981, Pages 185-203
[5] B.Lucas ,T. Kanade,” An Iterative Image Registration Technique with an Application to Stereo Vision”, in Proceedings of Imaging Understanding Workshop, pages 121--130
[6] U.Soni,A.Trivedi,N.Roberts ,”Real-time hand tracking using integrated optical flow and CAMshift algorithm”in 2016 Second International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) , 23-25 September 2016 ,pp. 135 - 140
[7] P.Crisnapati, M.Setiawan,I.Arsa, P.Novayanti, M.Wibawa, K.Ciptahadi , ”Real-Time Hand Palm Detection and Tracking Augmented Reality Game Using Lucas Kanade Optical Flow Combined with Color Blob Detection”in 2019 1st International Conference on Cybernetics and Intelligent System (ICORIS) , 22-23 August 2019,pp. 263 - 268
[8] Z.Hang ,”An OPS Hand Tracking Algorithm Based on Optical Flow”in 2009 WRI World Congress on Software Engineering, 19-21 May 2009,pp. 190 – 194
[9] N.Dung and J.Rohacs ,”The drone-following models in smart cities”in 2018 IEEE 59th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON), 12-13 November 2018,pp. 1 - 6
[10] Y.Shi,R.Enami,J.Wensowitch,J.Camp ,”Measurement-based characterization of LOS and NLOS drone-to-ground channels”in 2018 IEEE Wireless Communications and Networking Conference (WCNC) , 15-18 April 2018,pp. 1 - 6
[11] R.Tariq,M.Rahim,N.Aslam,N.Bawany,U.Faseeha,”DronAID : A Smart Human Detection Drone for Rescue”in 2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT), 08-10 October 2018,pp. 33 - 37
[12] D.Lee,W.La,H.Kim ,”Drone Detection and Identification System using Artificial Intelligence”in 2018 International Conference on Information and Communication Technology Convergence (ICTC), 17-19 October 2018,pp. 1131 – 1133