使用慣性傳感器構建即時人體骨架動作

Using Multiple Inertial Sensors for the Construction of Real-time Human Skeleton Animation

項成凱(Cheng-kai Xiang)

指導教授 ： 施國琛

國立中央大學/資訊電機學院/資訊工程學系/碩士(2014年)

摘要

自從人類製造使用機器以來，人機互動就是成為十分重要的議題。近年來，隨著電腦產業的不斷更迭，人機互動也進入了新的時代。
以影像處理為核心技術的微軟體感感測器Kinect，雖然有較為成熟的技術和十分方便的使用結果，但是由於影像採集所需要的在視線範圍內的缺憾，使用者必須站在深度相機能照到的範圍內，並且極易受到環境內的物件的干擾。本項目針對佩戴式的體感偵測的方法進行系統、深入地研究，以期通過使用現在發展迅速的感測器技術結合演算法，從而達到有效穩定的即時體感偵測系統。鑒於已經有一部分的佩戴式體感偵測的研究，本專案擬解決一下幾個關鍵技術，並取得相應創新性成果：第一，更高效，精確，小體積的體感偵測系統；第二，更好的移植性，使得系統可以真正的應用到現在生活所需，例如智慧電視等平臺。最後，將預期的系統與微軟體感感測器進行比較，以驗證成果的正確性和可能性。本系統使用多顆傳感器，構成人體感測網路，結果也還可應用於複健領域。

關鍵字

人機互動 ； 體感偵測 ； 虛擬實境 ； 穿戴式 ； 人體感測網路 ； 複健

並列摘要

Research in Human-Computer Interaction (HCI) has gained interest in recent years and has fostered new ideas and expectations.
As the development of computer science, HCI has got into a new era. There are many kinds of human motion capture methods nowadays. Image based motion tracking system like Microsoft Kinect, it's good for use and easy for coding, but it still has disadvantages. This kind of method camera and human have to be line of sight (LOS), and it will be easily disturb by the object in the environment.
In this progress, we have compared 2 kinds of methods which are the most popular methods in HCI – Microsoft Kinect Sensor and Inertial Sensors. This progress presents a wearable real-time human motion capture system using inertial sensors, and result of our method has been compared with Microsoft Kinect Sensor. Some research have been done, in this progress several technology we want to achieve as following:
1. An efficient accurate motion tracking system;
2. We can use this system into daily life, like smart TV etc.
Several experiments have been performed to validate the effectiveness of our method. Our system using multiple sensors build a body sensor network system, and this system can also be used in Rehabilitation domain;

並列關鍵字

HCI ； Motion tracking ； Virtual reality ； Wearable ； Body sensor network ； Rehabilitation

參考文獻

[1] E. Foxlin and M. Harrington, “Weartrack: A self-referenced head and hand tracker for wearable computers and portable VR,” International Symposium on Wearable Computers, Atlanta, GA, USA, 16-17, pp. 155–162, 2000.

[2] J. C. Lementec and P. Bajcsy, “Recognition of arm gestures using multiple orientation sensors: gesture classification,” The 7th International IEEE Conference on Intelligent Transportation Systems, Washington DC, USA, 3-6, pp. 965–970, 2004.

[3] J. Lee and I. Ha, “Sensor fusion and calibration for motion captures using accelerometers,” Proc. IEEE International Conference on Robotics and Automation, pp. 1954-1959, 1999.

[4] R. Zhu and Z. Zhou, “A Real-Time Articulated Human Motion Tracking Using Tri-Axis Inertial/Magnetic Sensors Package,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol.12, no. 2, pp. 295-302, 2004.

[5] X. Yun, C. Aparicio, E. R. Bachmann, and R. B. McGhee, “Implementation and experimental results of a quaternion-based Kalman filter for human body motion tracking,” Proc. IEEE International Conference on Robotics and Automation, pp. 317-322, 2005.