簡易檢索 / 詳目顯示

研究生: 蔡依龍
Tsai, Yi-Lung
論文名稱: EcoTrack: A Gesture Recognition and Motion Tracking System Based on EcoIMU
EcoTrack:基於雙三軸加速規慣性測量儀之動作辨識與軌跡追縱軟體
指導教授: 周百祥
Chou, Pai H.
口試委員:
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 資訊工程學系
Computer Science
論文出版年: 2010
畢業學年度: 98
語文別: 英文
論文頁數: 54
中文關鍵詞: 三軸加速規免陀螺儀慣性測量儀動作辨識軌跡追縱手寫辨識
外文關鍵詞: EcoTrack, EcoIMU, Gesture Recognition, Motion Tracking, Dead Reckoning, Gyro-free, Handwriting, Eco
相關次數: 點閱:1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
  • EcoTrack is a multi-functional system that performs gesture recognition and motion tracking procedures
    based on EcoIMU, which is a brand-new gyro-free inertial measurement unit (IMU) built
    with a pair of triaxial accelerometers that can be spatially separated and wirelessly connected on a
    handheld unit or on the human body. It can output the translation and rotation data of the system
    from time to time for the purpose of motion tracking and dead reckoning applications. It can also
    recognize the gestures made by a user. It reduces error accumulation and drift problems by using tilt
    information, zero velocity compensation, and geometric constraints on the two nodes. We demonstrate
    the usability of this system by a series of applications including handwriting recognition and
    motion tracking on both a handheld unit and the human bodies. The experimental results show Eco-
    Track to have less drift error on tracking and high recognition rate with low latency while consuming
    significantly lower power than traditional IMUs built with gyroscopes and accelerometers.


    EcoTrack 是一基於雙三軸加速規慣性測量儀之動作辨識與軌跡追縱的多功能軟體。除了能夠計算待測物體的運動軌跡,也可快速地辨識出使用者的動作。同時藉由計算傾斜角度與靜止狀態偵測的補償,明顯地降低了誤差累積與偏移的問題。我們透過一連串的應用,包括了手寫辨識與軌跡追縱,並且應用在身體感測網路上,來展示系統的可用性。實驗結果顯示 EcoTrack 具有低偏移誤差以及高辨識度的特性;相較於傳統的慣性測量,也消耗了更低的能量。

    Abstract i Contents i Acknowledgments vi 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2 Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.2.1 Time Synchronization and Collision-Free Transmission Protocol . . . . . . . 4 1.2.2 High Sampling Rate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3 Goals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3.1 Gesture Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3.2 Dead Reckoning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3.3 Human Wearable, Body Sensor Network Applications . . . . . . . . . . . . 5 1.3.4 User Friendly APIs, Parameterized System . . . . . . . . . . . . . . . . . . 6 2 Background and Related Work 7 2.1 Basic Kinematics of Gyro-free IMU . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 A Traditional Cube Model of Gyro-free IMU . . . . . . . . . . . . . . . . . . . . . 9 2.3 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.3.1 Absolute Tracking vs. Non-Reference Tracking . . . . . . . . . . . . . . . . 13 2.3.2 Recognition with 2 Eco nodes vs. 1 Eco node . . . . . . . . . . . . . . . . . 14 2.3.3 Limitation on Handwriting Recognition . . . . . . . . . . . . . . . . . . . . 14 2.4 Survey on Gesture Recognition Projects . . . . . . . . . . . . . . . . . . . . . . . . 15 3 Problem Statement 16 3.1 EcoIMU . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2 EcoTrack . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4 System Implementation 20 4.1 Architecture and Platform . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.1.1 Eco Nodes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 4.1.2 Base Station . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.2 Time Synchronization on the Node . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.3 Host Subsystem . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.3.1 Filtering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.3.2 Tilt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.3 Compensation for Motion Tracking . . . . . . . . . . . . . . . . . . . . . . 27 4.3.4 Gesture Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.3.5 Parameterized System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 5 Evaluation 32 5.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 5.2 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.2.1 Cancellation of Gravity Effect . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.2.2 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.2.3 Sampling Rate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 5.3 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 6 Conclusions and Future Work 51 6.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 6.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52

    [1] BANG, W., CHANG, W., KANG, K., CHOI, E., POTANIN, A., AND KIM, D. Self-contained
    Spatial Input Device for Wearable Computers. In Proceedings of the 7th IEEE International
    Symposium on Wearable Computers (2003), IEEE Computer Society, p. 26.
    [2] CHEN, J., LEE, S., AND DEBRA, D. Gyroscope free strapdown inertial measurement unit by
    six linear accelerometers. Journal of Guidance, Control, and Dynamics 17, 2 (1994), 286–290.
    [3] CHEN, T., AND PARK, S. MEMS SoC: observer-based coplanar gyro-free inertial measurement
    unit. Journal of Micromechanics and Microengineering 15 (2005), 1664.
    [4] CHO, S., OH, J., BANG, W., CHANG, W., CHOI, E., JING, Y., CHO, J., AND KIM, D.
    Magic wand: a hand-drawn gesture input device in 3-D space with inertial sensors. In Frontiers
    in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on (2004),
    pp. 106–111.
    [5] DISSANAYAKE, G., SUKKARIEH, S., NEBOT, E., AND DURRANT-WHYTE, H. The aiding of
    a low-cost strapdown inertial measurement unit using vehicle model constraints for land vehicle
    applications. IEEE Transactions on Robotics and Automation 17, 5 (2001), 731–747.
    [6] GANERIWAL, S., KUMAR, R., AND SRIVASTAVA, M. Timing-sync protocol for sensor networks.
    In Proceedings of the 1st international conference on Embedded networked sensor systems
    (2003), ACM, p. 149.
    [7] KEIR, P., PAYNE, J., ELGOYHEN, J., HORNER, M., NAEF, M., AND ANDERSON, P. Gesturerecognition
    with non-referenced tracking. The Computer Journal (2006).
    [8] PARK, C., AND CHOU, P. H. Eco: Ultra-wearable and expandable wireless sensor platform. In
    Proc. Third International Workshop on Body Sensor Networks (April 2006), pp. 162–165.
    [9] PARK, S., TAN, C., AND PARK, J. A scheme for improving the performance of a gyroscopefree
    inertial measurement unit. Sensors and Actuators A: Physical 121, 2 (2005), 410–420.
    [10] TAN, C., PARK, S., MOSTOV, K., AND VARAIYA, P. Design of gyroscope-free navigation
    systems. 2001 IEEE Intelligent Transportation Systems, 2001. Proceedings (2001), 286–291.
    [11] YANG, J., CHOI, E., CHANG, W., BANG, W., CHO, S., OH, J., CHO, J., AND KIM, D. A
    novel hand gesture input device based on inertial sensing technique. In Industrial Electronics
    Society, 2004. IECON 2004. 30th Annual Conference of IEEE (2004), vol. 3.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)

    QR CODE