簡易檢索 / 詳目顯示

回結果列表
研究生： 劉明山
Liu, Ming-Shan
論文名稱： 基於視覺之手部追蹤與手勢辨識之研究
A Study on Vision-Based Hand Tracking and Gesture Recognition
指導教授： 鄭銘揚
Chang, Ming-Yang
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年： 2009
畢業學年度： 97
語文別： 中文
論文頁數： 92
中文關鍵詞： 手勢辨識 、隱藏式馬可夫模型 、手部追蹤
外文關鍵詞： Gesture Recognition, Hand Tracking, Hidden Markov Model
相關次數： 點閱：193  下載：9 
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

    • 現今，絕大多數的人機介面都是透過鍵盤或滑鼠等接觸式裝置來進行命令輸入。然而對於人類而言，手勢的使用是最自然的表達方式之一。手勢辨識系統的發展就是希望透過電腦視覺的方法，讓系統能夠自動對攝影機所擷取的影像進行手部之偵測與追蹤，並進一步分析手勢動作所代表的意義。在目標物偵測與追蹤方面，本論文使用一多重相似度比對法對系統之手部進行偵測，並以物件為基礎對手部持續地追蹤。而在手勢辨識方面，因手勢之多變性，故採用Central Moments對手勢之各種物理意義進行描述，再根據事先使用隱藏式馬可夫模型所建立之手勢模型進行比對，給與相對應之動作。實驗結果顯示，在普通家庭沙發距離攝影機大約1.7~2公尺的範圍內，本論文發展之手勢辨識系統確實可成功達成即時性的辨識任務。

    Nowadays, most of human computer interface (HCI) use the keyboard or mouse as the command input device. However, gesture is considered one of the most natural ways for human to communicate with other people or to issue commands. Generally, the gesture recognition system is designed based on computer vision to automatically detect/track human hands and also recognize the gesture. In object detection and tracking, this thesis develops a multi-cue similarity measurement algorithm for hand detection, and use an object based method to continuously track the hand. In gesture recognition, due to the fact that the gesture image is highly complex and non-separable, at first the Central Moments analysis is employed to extract the physical features from gesture. Then the Hidden Markov Model (HMM) is used to compare the feature sequences and give suitable actions when a match is found. Experimental results show that the gesture recognition system developed in the thesis has the capability of detecting hands and recognizing the gestures for the distance around 1.7~2 meters that is from a normal family sofa to the camera.

    中文摘要........................................I 英文摘要.......................................II 誌謝..........................................III 目錄...........................................IV 表目錄........................................VII 圖目錄.........................................IX 第一章 緒論.....................................1 1.1 前言........................................1 1.2 研究動機與目的..............................1 1.3 文獻回顧....................................2 1.4 本文架構....................................4 第二章 手部偵測與追蹤...........................6 2.1 前言........................................6 2.2 手部偵測....................................6 2.2.1 膚色物件偵測..............................6 2.2.2 物件標示.................................10 2.2.3 雜訊消除.................................11 2.2.4 輪廓萃取.................................13 2.2.5 樣板縮放.................................15 2.2.6 移動像素偵測.............................16 2.2.7 物件相似度...............................19 2.2.8 手部偵測系統架構.........................21 2.3 手部追蹤...................................23 2.3.1 追蹤搜尋範圍.............................23 2.3.2 前一刻手部樣板擷取.......................25 2.3.3 手部追蹤系統架構.........................25 第三章 手勢特徵擷取............................27 3.1 前言.......................................27 3.2 特徵向量擷取...............................27 3.2.1 Central Moments.........................27 3.3 向量量化...................................31 3.3.1 K-mean群集演算法........................33 3.3.2 Binary splitting演算法..................33 3.3.3 Binary splitting+相關係數演算法.........34 第四章 手勢訓練與學習..........................36 4.1 前言.......................................36 4.2 隱藏式馬可夫模型介紹.......................36 4.2.1 隱藏式馬可夫模型分類.....................38 4.2.2 隱藏式馬可夫模型參數意義.................40 4.3 隱藏式馬可夫模型辨識.......................42 4.3.1 隱藏式馬可夫模型輸出機率計算.............42 4.3.2 正算程序.................................43 4.3.3 逆算程序.................................44 4.3.4 Viterbi演算法...........................46 4.4 隱藏式馬可夫模型訓練.......................48 4.4.1 Baum-Welch演算法........................48 4.4.2 多觀測序列的模型訓練.....................49 4.5 隱藏式馬可夫模型架構.......................50 4.6 手勢辨識流程架構...........................51 第五章 系統架構與實驗結果分析..................52 5.1 系統架構...................................52 5.2 實驗硬體與實驗資料分析流程.................53 5.2.1 實驗硬體.................................53 5.2.2 實驗資料分析流程.........................54 5.3 實驗結果...................................57 5.3.1 手部偵測追蹤實驗.........................57 5.3.2 靜態手勢辨識實驗.........................64 5.3.3 動態手勢辨識實驗.........................73 5.3.4 輸入手勢為非系統定義手勢之辨識實驗探討..81 5.3.5 手勢辨識實驗結果分析....................83 第六章 結論與建議..............................86 參考文獻.......................................87

    [1]http://www.penpower.net/brand/3_0technology/3_2technology.html
    [2]http://www.penpower.net/brand/3_0technology/3_5technology.html
    [3]http://news.xinhuanet.com/auto/2007-11/19/content_7103830.htm
    [4]M. Yamamoto, T. Watanabe, and K. Osaki, “Development of and embodied interaction system with InterActor by speech and hand motion input,” in proceedings of the IEEE International Workshop on Robot and Human Interactive Communication, October 2005, pp. 323-328.
    [5]N. K. Looi, C. K. Loo, K. N. Pau, “Real time actions and gestures as intuitive user interface for creative 3D modeling,” in proceedings of the IEEE International Conference on Active Media Technology, May 2005, pp. 487-490.
    [6]http://www.est-kl.com/hardware/gloves/5dt/glovewireless.html
    [7]J. Yamato, J. Ohya, and K. Ishii, “Recognizing Human Action in Time-Sequential Images using Hidden Markov Model,” in Proceedings of the IEEE Computer Society Conference on Computer Vision Pattern Recognition, June 1992, pp. 379-385.
    [8]B. W. Min, H. S. Yoon, J. Soh, Y. M. Yang, and T. Ejjima, “Hand Gesture Recognition Using Hidden Markov Models,” in Proceedings of the 1997 IEEE International Conference on Computational Cybernetics and Simulation, pp. 4232-4235.
    [9]T. Starner and A. Pentland, “Real-time American Sign Language recognition from video using hidden Markov models,” in Proceedings of the IEEE International Symposium on Computer Vision, November 1995, pp. 265-270.
    [10]J. Weaver, T. Starner, and A. Pentland, “Real-time American Sign Language recognition using desk and wearable computer based video,” IEEE Transactions on Pattern Analysis Machine Intelligence, vol. 33 , pp. 1371-1378, 1998.
    [11]R. Bowden, D. Windridge, T. Kadir, A. Zisserman, and M. Brady, “A linguistic feature vector for the visual interpretation of sign language,” in Proceedings of the 8th European Conference on Computer Vision, May 2004, pp. 391-401.
    [12]H. S. Yoon, J. Soh, Y. J. Bae, and H. S. Yang, “Hand gesture recognition using combined features of location, angle and velocity,” Pattern Recognition, vol. 34, pp. 1491-1501, 2001.
    [13]A. Ramamoorthy, N. Vaswani, S. Chaudhury, and S. Banerjee, “Recognition of dynamic hand gestures,” Pattern Recognition, vol. 36, pp. 2069-2081, 2003.
    [14]—, “CONDENSATION—Conditional Density Propagation for Visual Tracking,” International Journal Computer Vision, vol. 1, pp. 5-28, 1998.
    [15]M. J. Black and A. D. Jepson, “A probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions,” in Proceedings of the 5th European Conference on Computer Vision, vol. 1, 1998, pp. 909-924.
    [16]J. Davis and M. Shah, “Visual Gesture recognition,” IEE Proceedings, Vision, Image Signal Processing, vol. 141, no. 2, pp. 101-106, 1994.
    [17]M. Yeasin and S. Chaudhuri, “Visual understanding of dynamic hand gestures,” Pattern Recognition, vol. 33, pp. 1805-1817, 2000.
    [18]P. Hong, T. S. Huang, M. Turk, “Constructing Finite State Machines for Fast Gesture Recognition,” in Proceedings of the 15th International Conference on Pattern Recognition, vol. 3, September 2000, pp 3695-3698.
    [19]P. Hong, M. Turk, and T. S. Huang, “Gesture modeling and recognition using finite state machines,” in Proceedings of the 4th IEEE International Conference on Automatic Face Gesture Recognition, Mar. 2000, pp.410-415.
    [20]M. S. Yang and N. Ahuja, “Recognizing hand gesture using motion trajectories,” in Proceedings of IEEE Computer Society Conference Computer Vision and Pattern Recognition, vol. 1, June 1999, pp. 466–472.
    [21]王國榮，基於資料手套的智慧型手勢辨識之廣泛研究，碩士論文，國立台灣科技大學電機工程系，2001。
    [22]陳治宇，虛擬滑鼠：以視覺為基礎之手勢辨識，碩士論文，國立中山大學資訊工程學系，2003。
    [23]洪兆欣，以軌跡辨識為基礎之手勢辨識，碩士論文，國立中央大學資訊工程學系，2006。
    [24]江明晏，耦合隱藏式馬可夫模型於雙手手勢辨識，碩士論文，國立成功大學資訊工程學系，2007。
    [25]黃俊捷，互動雙足式機器人之設計與實現(I)手勢辨識，碩士論文，國立中央大學電機工程學系，2008。
    [26]D. Chai and A. Bouzerdoum, “A Bayesian Approach to Skin Color Classification in YCbCr Color Space,” in Proceedings of the IEEE Region Ten Conference, Vol. 2, pp. 421-424, September 2000.
    [27]V. Vezhnevets, V. Sazonov and A. Andreeva, “A Survey on Pixel -Based Skin Color Detection Techniques,” in Proceedings of the Graphicon -2003, September 2003, pp. 85-92.
    [28]胡冠宇，基於膚色之裸體影像偵測之研究，碩士論文，國立成功大學工程科學系，2004。
    [29]許倫維，即時性連續手勢追蹤與辨識，碩士論文，國立台北科技大學資訊工程系，2006。
    [30]J. Kovac, P. Peer, and F. Solina, “Human Skin Colour Clustering for Face Detection,” in Proceedings of the International Conference on Computer as a Tool, Ljubljana, Slovenia, Sep. 2003, pp. 144-148.
    [31]R. C. Gonzalez and R. E. Woods, Digital Image Processing. New Jersey: Prentice-Hall, 2002.
    [32]W. Brand, “Morphable 3D models form video,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 456-463.
    [33]N. Weng, Y. H. Yang, and R. Pierson, “3D surface reconstruction using optical flow for medical imaging,” in Proceedings of the IEEE Conference on Nuclear Science Symposium, Vol. 3, November. 1996, pp. 1845-1849.
    [34]J. F. Cohn, A. J. Zlochower, J. J. Lien and T. Kanade, “feature- point tracking by optical flow discriminates subtle differences in facial expression,” in Proceedings of the 3th IEEE International Conference on Automatic Face and Gesture Recognition, April 1998, pp. 396-401.
    [35]A. J. Lipton, “Local application of optic flow to analyze rigid versus non-rigid motion,” Technical Report, CMU-RI-TR-99-13, Robotics Institute, Carnegie Mellon University, 1999.
    [36]J. L. Barron, D. J. Fleet, S. S. Beauchemin and T. A. Burkitt, “Performance of Optical Flow Techniques,” in Proceedings of the 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 236-242.
    [37]http://www.kfunigraz.ac.at/imawww/invcon/pictures/flowfield.gif
    [38]K. Dawson-Howe, “Active Surveillance using dynamic background subtraction,” Technical Report, TCD-CS-96-06, Trinity College, 1996.
    [39]N. Ohta, “A statistical approach to background subtraction for surveillance systems,” in Proceedings of the 8th IEEE International Conference on Computer Vision, Vol. 2, July 2001, pp. 481-486.
    [40]D. Guo, Y. C. Hwang, Y. C. L. Adrian and C. Laugier, “Traffic monitoring using short-long term background memory,” in Proceedings of the IEEE 5th International Conference on Intelligent Transportation Systems, 2002, pp. 124-129.
    [41]C. Wren, A. Azarbyayejani, T. Darrell, and A. Pentland, “Pfinder: Real-time tracking of the human body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, pp. 780-785, 1997.
    [42]H. Fujiyoshi and A. J. Lipton, “Real-time human motion analysis by image skeletonization,” in Proceedings of the 4th IEEE Workshop on Applications of Computer Vision, October 1998, pp. 15-21.
    [43]W. Grimson, C. Stauffer, R. Romano, and L. Lee, “Using adaptive tracking to classify and monitor activities in a site,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 1998, pp. 22-29.
    [44]王俊凱，基於改良式適應性背景相減法與多重影像特徵比對法之多功能即時視覺追蹤系統之設計與實現，碩士論文，國立成功大學電機工程學系，2004。
    [45]R. Li, B. Zeng and M. Liou, “A New Three-Step Search Algorithm for Block Motion Estimation,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 4, pp. 438-442, 1994.
    [46]S. Zhu and K. K. Ma, “A new diamond search algorithm for fast block matching motion estimation,” IEEE Transactions on Image Processing, Vol. 9, pp.287-290, 2000.
    [47]M. K. Hu, “Visual pattern recognition by moment invariants,” IRE Transactions on Information Theory, Vol. 8, Issue 2, pp. 179-187, 1962.
    [48]John-Paul Hosom, Hidden Markov Models for Speech Recognition. Oregon Health & Science University, Spring 2006.
    [49]R. M. Gray, “Vector Quantization,” IEEE ASSP Magazine, pp. 4-29, Apr. 1984.
    [50]J. G. Wilpon and L. R. Rabiner, “A Modified K-Means Clustering Algorithm for Use Isolated Word Recognition,” IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 33, No. 3, pp. 587-594, 1985.
    [51]http://www.data-compression.com/vq.html
    [52]Jeff Bilmes, “What HMMs Can Do,” UWEE Technical Report Number UWETR-2002-2003, Department of Electrical Engin- eering University of Washington, January 2002.
    [53]L.R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, 1993

    下載圖示 校內：2014-08-14公開
    校外：2014-08-14公開
    QR CODE