簡易檢索 / 詳目顯示

研究生: 黃暐翔
Huang, Wei-Hsiang
論文名稱: 應用手勢辨識系統於四旋翼無人機控制
Application of Hand Gesture Recognition System for Quadcopter Control
指導教授: 賴維祥
Lai, Wei-Hsiang
學位類別: 碩士
Master
系所名稱: 工學院 - 航空太空工程學系
Department of Aeronautics & Astronautics
論文出版年: 2021
畢業學年度: 109
語文別: 中文
論文頁數: 88
中文關鍵詞: 四旋翼無人機電腦視覺手勢辨識手勢控制人機互動
外文關鍵詞: UAS, Quadcopter, Computer Vision, Hand Gesture Recognition, Hand Gesture Control, Human-Computer Interaction
相關次數: 點閱:139下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 隨著科技發展的演進,人類未來生活將充滿許多各種用途的智慧機器,如何能夠更方便的操控或命令機器是一門相當熱門的研究課題,而這個研究課題即是人機互動(Human-Computer Interaction,HCI)。在人機互動這門領域中有許多輸入命令的方式,其中最常見的方式即是使用手勢控制,手勢控制是一種自然且直觀的人機互動手段。

    早期的手勢辨識是透過有線手套,這種方式的優點為高準確性,但缺點是價格昂貴且笨重。然而隨著近年來電腦視覺技術發展,出現了基於視覺的手勢辨識,其成本相對降低許多,且使用者不需要在穿戴任何裝置,使人能夠真正以自然的方式與機器進行互動。

    本研究將基於電腦視覺設計一套手勢控制演算法,而論文中定義了五種不同的靜態手勢,這些靜態手勢各自對應了五種不同的控制指令。在四旋翼機上掛載攝像頭與嵌入式系統,在飛行中透過嵌入式系統Raspberry Pi對使用者手勢進行辨識,辨識結果和控制指令將透過MAVLink傳遞至飛控電腦Pixhawk,最後實現在戶外環境下利用手勢控制四旋翼機的俯仰、滾轉、偏航。

    With the progress of science and technology, there will be full of intelligent machines with multiple purposes in the future. How to control or command machines more conveniently is a very popular research topic which called human-computer interaction (HCI). There are many ways to input commands in the field of HCI. The most common way is to utilize hand gesture control, which is a very nature and intuitive way.

    The early method for hand gesture recognition is achieved through wired gloves. The advantage of this method is high accuracy, but its disadvantage is expensive and clunky. However, vision-based hand gesture recognition has appeared with the development of computer vision technology in recent years. The cost is much lower, and user doesn’t need to wear any device anymore so that user can interact with the machine in a nature way.

    This research will design a hand gesture control algorithm based on computer vision. There are five different static gestures defined in this thesis, and each of these static gestures correspond to five different control commands. Mount the webcam and embedded system on the quadcopter, and use the embedded system Raspberry Pi to recognize user’s gesture during flight. The recognition result and control command will be transmitted to the flight control computer Pixhawk through MAVLink, and finally the pitch, roll and yaw of the quadcopter can be controlled by hand gesture in an outdoor environment.

    中文摘要 I Extended Abstract II 誌謝 V 目錄 VI 表目錄 XII 圖目錄 XIII 符號表 XVII 第一章 緒論 1 1.1 前言 1 1.2 研究動機與目的 2 1.3 文獻回顧 4 1.4 研究方法與流程 7 1.5 論文架構 12 第二章 演算法介紹 14 2.1 色彩模型 14 2.1.1 RGB色彩模型 14 2.1.2 HSV色彩模型 15 2.1.3 YCbCr色彩模型 16 2.2 感興趣區域(ROI) 17 2.3 平滑濾波器 18 2.3.1 均值濾波(Mean Filtering) 18 2.3.2 雙邊濾波(Bilateral Filtering) 19 2.4 影像分割 20 2.4.1 二值化 20 2.4.2 Otsu二值化 22 2.5 形態學處理 24 2.5.1 膨脹 24 2.5.2 侵蝕 26 2.5.3 開運算和閉運算 27 2.6 凸包與凸缺陷 28 2.6.1 凸包 28 2.6.2 凸缺陷 29 第三章 實驗設備介紹 31 3.1 無人機系統 31 3.1.1 四旋翼無人機 31 3.1.2 飛行控制板 32 3.1.3 GPS接收器 34 3.1.4 動力配置 34 3.1.5 數據傳輸模組 36 3.1.6 遙控器與接收器 37 3.1.7 地面控制站 38 3.1.8 MAVLink 39 3.2 手勢辨識系統設備 40 3.2.1 Raspberry Pi 40 3.2.2 網路攝影機 41 3.2.3 4G Dongle 42 3.3 函式庫 43 3.3.1 OpenCV 43 3.3.2 Dronekit 44 第四章 實驗方法與成果分析 45 4.1 HSV與YCbCr膚色分割於不同背景下之比較 45 4.1.1 實驗目的 45 4.1.2 實驗方法 45 4.1.3 實驗流程圖 46 4.1.4 實驗結果 47 4.1.5 實驗結果分析 50 4.2 手勢辨識驗證 51 4.2.1 實驗目的 51 4.2.2 實驗方法 51 4.2.3 實驗流程圖 52 4.2.4 實驗結果 53 4.2.5 實驗結果分析 55 4.3 手勢辨識距離限制 55 4.3.1 實驗目的 55 4.3.2 實驗方法 55 4.3.3 實驗流程圖 56 4.3.4 實驗結果 57 4.3.5 實驗結果分析 57 4.4 演算法運算速度 58 4.4.1 實驗目的 58 4.4.2 實驗方法 58 4.4.3 實驗流程圖 59 4.4.4 實驗結果 60 4.4.5 實驗結果分析 62 4.5 SITL模擬 62 4.5.1 實驗目的 62 4.5.2 實驗方法 62 4.5.3 實驗流程圖 65 4.5.4 實驗結果 66 4.5.5 實驗結果分析 68 4.6 戶外飛行實驗 70 4.6.1 實驗目的 70 4.6.2 實驗方法 70 4.6.3 實驗流程圖 71 4.6.4 實驗結果 72 4.6.5 實驗結果分析 80 第五章 結論與未來工作 83 5.1 結論 83 5.2 未來工作 84 參考文獻 86

    [1] https://en.wikipedia.org/wiki/General_Atomics_MQ9_Reaper
    [2] Amazon Prime Air, https://www.amazon.com/
    [3] Meenakshi Panwar, Pawn Singh Mehra, “Hand Gesture Recognition for Human Computer Interaction,” International Conference On Image Information Processing, Shimla, India, Nov. 2011.
    [4] Mallikarjun Anandhalli, Vishwanath P. Baligar, “A Novel Approach in Real-time Vehicle Detection and Tracking Using Raspberry Pi,” Alexandria Engineering Journal, Vol. 57, Iss. 3, pp.1597-1607, 2018.
    [5] Ahmad ’Athif Mohd Faudzi, Muaammar Hadi Kuzman Ali, M. Asyraf Azman, Zool Hilmi Ismail, “Real-time Hand Gestures System for Mobile Robots Control,” Procedia Engineering, Vol. 41, pp.798-804, Dec. 2012.
    [6] https://en.wikipedia.org/wiki/HSL_and_HSV
    [7] 毛星雲, 冷雪飛, OpenCV程式設計參考手冊, 松崗出版社, 2015
    [8] OpenCV, https://opencv.org/
    [9] Dronekit, https://dronekit.io/
    [10] Ardupilot, https://ardupilot.org/
    [11] Khamar Basha Shaik, Ganesan P, V.Kalist, B.S.Sathish, J.Merlin Mary Jenitha, “Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space,” Procedia Computer Science, Vol.57, pp.41-48, 2015.
    [12] Jeff Deeds, Zach Engstrom, Caleb Gill, and Zack Woods, “Vision Based Autonomous Control of a Quadcopter,” Department of Electrical and Computer Engineering Bradley University, Dec. 2016.
    [13] S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, and J. Jatakia, “Human Skin Detection Using RGB, HSV, and YCbCr Color Models,” Proceedings of the International Conference on Communication and Signal Processing, Dec. 2016.
    [14] J.L. Raheja, Ankit Chaudhary, Shobhit Maheshwari, “Hand Gesture Pointing Location Detection,” Optik – International Journal for Light and Electron Optics, Vol.125, Iss.3, pp.993-996, Feb. 2014.
    [15] Hongli He, Yongping Dan, “The Research and Design of Smart Mobile Robotic Arm Based On Gesture Controlled,” International Conference on Advanced Mechatronic Systems, IEEE, Hanoi, Vietnam, Dec. 2020.
    [16] Yangguang Yu, Xiangke Wang, Zhiwei Zhong, Yongwei Zhang, “ROS-based UAV Control Using Hand Gesture Recognition,” 2017 29th Chinese Control and Decision Conference, IEEE, Chongqing, China, May. 2017.
    [17] Alexandru Pasarica, Casian Miron, Dragos Arotaritei, Gladdiola Andruseac, Hariton Costin, Cristian Rotariu, “Remote Control of a Robotic Platform Based on Hand Gesture Recognition,” The 6th IEEE International Conference on E-Health and Bioengineering, Sinaia, Romania, Jun. 2017.
    [18] Zhou Ren, Junsong Yuan, Jingjing Meng, Zhengyou Zhang, “Robust Part-Based Hand Gesture Recognition Using Kinect Sensor,” IEEE Transactions On Multimedia, Vol.15, Iss.5, Aug. 2013.
    [19] Amit Kumar, Shivani Malhotra, “Real-time Human Skin Color Detection Algorithm using Skin Color Map”, 2015 2nd International Conference on Computing for Sustainable Global Development, IEEE, New Dehli, India, Mar. 2015.
    [20] 謝秉勳, “地面目標物識別及相對定位視覺演算法,” 國立成功大學航空太空工程研究所碩士論文, 2018。
    [21] 陳建綸, “基於視覺導航修正全球定位系統之旋翼機自動定點降落,” 國立成功大學航空太空工程研究所碩士論文, 2019。
    [22] Mission Planner, https://ardupilot.org/planner/
    [23] Federal Aviation Administration, https://www.faa.gov/
    [24] NASA, https://www.nasa.gov/
    [25] https://en.wikipedia.org/wiki/RGB_color_model

    下載圖示
    2026-06-23公開
    QR CODE