簡易檢索 / 詳目顯示

研究生: 柯志函
Chih-han Ko
論文名稱: 無穿戴即時三維指向偵測暨指向手勢辨識系統設計與開發
Design and Development of Hand-free and 3-D Pointing Gesture Recognition System
指導教授: 李永輝
Yung-Hui Lee
口試委員: 王孔政
Kung-Jeng Wang
楊文鐸
Wen-Dwo Yang
學位類別: 碩士
Master
系所名稱: 管理學院 - 工業管理系
Department of Industrial Management
論文出版年: 2009
畢業學年度: 97
語文別: 中文
論文頁數: 98
中文關鍵詞: 無穿戴人機介面即時系統三維相機校正膚色模型物件追蹤軌跡辨識指向手勢辨識
外文關鍵詞: Bare hand HCI, real time system, 3-D camera calibration, skin color model, object tracking, trajectory recognition, pointing orientation, gesture recognition
相關次數: 點閱:384下載:5
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
  • 指向動作是人類的直覺溝通方式。基於指向有完全的空間相容性,同時指向軌跡也有手勢的意義性等優點,本研究建置一套以兩部相機所發展的「三維指向即時偵測與重現系統」。
    指向過程中,眼、手、物體屬三點一線的共線性關係,本研究以機器視覺偵測法,透過三維相機校正、二維頭手區塊偵測、頭手位置追蹤等程序,取得頭手三維的連續移動位置。研究另以大型顯示器重現三維指向軌跡,作為指標之用,系統進而分析軌跡指向的速度與加速度變化,系統的更新速率為20Hz。
    為了驗證無穿戴指向手勢的優勢,本研究設計了一套指向手勢辨識邏輯,並利用Finite State Machine將手勢組合與音樂播放介面的功能(播放、暫停、音量控制、曲目更換)配對。驗證結果顯示,下達各手勢指令的時耗平均在4秒以內,正確率則在90%以上。


    Pointing gesture is a very intuitive human communication. Basically, the pointing orientation has a fully spatial compatibility, and the meaning of gesture is in the pointing trajectory. The objective of this study is to design and development a "free-hand, 3 dimensional, real time, pointing gesture recognition system” using 2 cameras.
    When pointing an object, the eye, the finger, and the object should be collinear. Base upon this principle, sub-system of 3-D camera calibration, hand/head area detection, and/head tracking were developed to continuously tracking the hand/head 3-D positions. The 3-D pointing positions were reconstructed in a large screen with a refresh speed of 20 Hz. It was then the velocity and the accelerations of the pointing trajectories were calculated.
    To verify the advantage of the system, we built a remote controlled music player with free-hand comments of play, pause, volume control, move to a previous, and move to the next control. Experiment result showed that the average time-spending for gesture command is less than 4 seconds, and the recognition rate of all comments is more than 90%.

    摘要 i 英文摘要 ii 誌謝 iii 目錄 iv 表目錄 vi 圖目錄 vii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 4 1.3 研究目的 6 1.4 系統架構概述 7 1.5 研究限制 9 1.6 論文架構 10 第二章 參考文獻 11 2.1 遊戲控制器之發展 12 2.2 手勢辨識之研究 14 2.2.1 以膚色為線索的手形擷取 14 2.2.2 以手形輪廓資訊的手勢辨識 18 2.3 手座標軌跡追蹤與辨識之研究 22 2.4 指向偵測與辨識之研究 25 2.5 小結 28 第三章 系統設計與開發過程 29 3.1 研究採用的指向定義 29 3.2 系統模組運作流程 31 3.3 三維相機校正 33 3.3.1 DLT的各空間關係定義 34 3.3.2 DLT參數求解 39 3.3.3 DLT基礎定義向量重建 40 3.3.4 DLT座標重建 42 3.3.5 DLT實施順序 43 3.4 二維頭手區塊偵測 44 3.4.1 膚色模型設計 44 3.4.2 濾除小型雜訊-侵蝕演算法 52 3.4.3 頭手位置選擇-K-means分群演算法 53 3.5 二維頭手軌跡追蹤 54 3.5.1 以Histogram為基礎的物件模型設計 55 3.5.2 評估候選區與目標模型的相似度 56 3.5.3 利用梯度法修正候選點 57 3.5.4 Kernel Based Object Tracking演算法 59 3.6 三維指向重現 61 3.7 指向軌跡辨識 62 3.7.1 設定手勢需要對應的功能 64 3.7.2 由座標軌跡序列抽取特徵向量 65 3.7.3 手勢辨識邏輯建構 69 第四章 實驗結果與系統驗證 72 4.1 系統各階段產出實驗結果 73 4.1.1 三維相機校正結果 73 4.1.2 二維頭手區塊偵測結果 76 4.1.3 二維頭手追蹤-Kernel Based Object Tracking實作結果 77 4.1.4 三維指向重現實作結果 80 4.2 系統使用者介面呈現 82 4.3 系統特色探討 85 4.4 系統驗證實驗 86 4.5 實驗結果分析 88 4.5.1 即時三維指向偵測及軌跡重現能力分析 88 4.5.2 即時指向手勢辨識應用情境可用性分析 88 第五章 結論與建議 91 5.1系統建置成果 92 5.2 系統及應用介面可用性驗證 93 5.3 結論 93 5.4 建議 94 文獻 95 附件 98

    期刊論文
    [1] Lawrence R. Rabiner, “A tutorial on Hidden Markov models and selected applications in speech recognition,” Proceedings of IEEE, Vol.77 No.2, 1989.

    [2] Michael Isard, Andrew Blake, "CONDENSATION—Conditional Density Propagation for Visual Tracking," International Journal of Computer Vision 29(1), pp: 5-28, 1998.

    研討會論文
    [3] R. Y. Tsai, “A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses,” IEEE J. Robot. Automat., vol. RA-3, pp. 323–344, 1987.

    [4] Byung-Woo Min, Ho-Sub Yoon, Jung Soh, Takeshi Ohashi, Toshiaki Ejima, "Gesture-based editing system for graphic primitives and alphanumeric characters," Engineering Applications of Arti®cial Intelligence 12, pp:429-441, 1999.

    [5] Byung-Woo Min, Ho-Sub Yoon, Jung Soh, Takeshi Ohashi, Toshiaki Ejima, "Visual Recognition of Static/Dynamic Gesture: Gesture-Driven Editing System," Journal of Visual Languages and Computing No.10, pp: 291-309, 1999.

    [6] Yoichi Sato, Yoshinori Kobayashi, Hideki Koike, "Fast Tracking of Hands and Fingertips in Infrared Images for Augmented Desk Interface," IEEE Automatic Face and Gesture Recognition (FG2000), pp.462-467, 2000.

    [7] Ho-Sub Yoon, Jung Soh, Younglae J. Bae, Hyun Seung Yang, "Hand gesture recognition using combined features of location, angle and velocity," Pattern Recognition 34, pp: 1491-1501, 2001.

    [8] M.S. Lee, D. Weinshall, E. Cohen-Solal, A. Colmenarez, D. Lyons, "A Computer Vision System for On-screen Item Selection By Finger Pointing," Computer Vision and Pattern Recognition (CVPR 2001), Proceedings of the 2001 IEEE Volume: 1, pp.I-1026- I-1033, 2001.

    [9] Chan Wah Ng, Surendra Ranganath, “Real-time gesture recognition system and application,” Image and Vision Computing Volume 20, pp: 993–1007, 2002.

    [10] Yoichi Sato, Hideki Koike, "Real-Time Fingertip Tracking and Gesture Recognition," IEEE Computer Graphics and Applications, Volume: 22, Issue. 6, pp: 64-71, 2002.

    [11] Dorin Comaniciu, Visvanathan Ramesh, Peter Meer, “Kernel-Based Object Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence
    Volume 25, pp: 564-575, 2003.

    [12] Feng-Sheng Chen, Chih-Ming Fu, Chung-Lin Huang, “Hand gesture recognition using a real-time tracking method and hidden Markov models,” Image and Vision Computing Volume 21, pp: 745–758, 2003.

    [13] Carlo Tomasi, Slav Petrov, and Arvind Sastry, "3D Tracking = Classification + Interpolation," Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV 2003) 2-Volume Set, 2003.

    [14] Aditya Ramamoorthy, Namrata Vaswani, Santanu Chaudhury, Subhashis Banerjee, "Recognition of dynamic hand gestures," Pattern Recognition, Volume. 36, pp: 2069-2081, 2003.

    [15] C. Keskin, A. Erkan, L. Akarun, "Real Time Hand Tracking and 3D Gesture Recognition for Interactive Interfaces Using HMM" Proceeding of ICANN/ICONIP, pp.567-570, 2003.

    [16] Kai Nickel, Rainer Stiefelhagen, "Pointing Gesture Recognition based on 3D-Tracking of Face, Hands and Head Orientation," ICMI’03, November 5-7, 2003, Vancouver, British Columbia, Canada.

    [17] Akihiro Imai, Nobutaka Shimada, Yoshiaki Shirai, “3-D Hand Posture Recognition by Training Contour Variation,” Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR’04), 2004.

    [18] McKenna S J and Morrison K, "A Comparison of Skin History and Trajectory-based Representation Schemes for the Recognition of User-Specified Gestures", Pattern Recognition 37(5), pp: 999-1009, 2004.

    [19] Yu Yamamoto, Ikushi Yoda, and Katsuhiko Sakaue, "Arm-pointing Gesture Interface Using Surrounded Stereo Cameras System," Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, Volume: 4, pp. 965 - 970, 2004.

    [20] Roland Kehl and Luc Van Gool, "Real-Time Pointing Gesture Recognition for an Immersive Environment," Automatic Face and Gesture Recognition, 2004. Proceedings. Sixth IEEE International Conference on, pp.577-582, 2004.

    [21] Kai Nickel, Edgar Seemann, Rainer Stiefelhagen, "3D-Tracking of Head and Hands for Pointing Gesture Recognition in a Human-Robot Interaction Scenario," Automatic Face and Gesture Recognition, 2004. Proceedings. Sixth IEEE International Conference on, pp.565-570, 2004.

    碩士論文

    [22] 陳永祚,「虛擬環境下即時三維手勢之介面系統」,碩士論文,國立清華大學資訊工程所,新竹,民國93年。

    [23] 張國君,「基於電腦視覺的手勢辨識系統」,碩士論文,國立清華大學電機工程學系,新竹,民國94年。

    [24] 簡敬宇,「以視覺為基礎之使用多重攝影機之即時手臂指向追蹤及辨識系統」,碩士論文,國立清華大學電機工程學系,新竹,民國95年。

    書籍

    [25] 郭正邦,台灣的微電子世界,麥格羅 希爾,台北,1997。

    網路資源
    [26] DLT method: http://kwon3d.com/theory/dlt/dlt.html
    Update by Young-Hoo Kwon (2003/03/03)

    [27] Eye Toy: http://www.eyetoy.com/
    Sony Computer Entertainment Cooperation, Europe. (2003)

    QR CODE