臺灣博碩士論文加值系統

本研究建立一種辨識頭部運動姿態的系統，選用即時且對使用者有效的方式，提出兩種辨識頭部運動姿態的方法，第一種方法為使用三軸感測模組加速度計、陀螺儀和磁力計，安裝在頭部並且分別量測重力加速度、角速度和磁通量，藉推導運動姿態之傾斜角和方位角，最後使用卡爾曼濾波器消除高斯雜訊，以濾波前估算的傾斜角和方位角作參考依據，對角速度積分估算的姿態角作校正，透過該姿態角推導出頭部的運動姿態，其辨識度高達95%。另一方式是以鏡頭捕捉使用者的臉部影像資訊，透過影像處理的方式捕捉臉部膚色、眼睛、嘴唇和下顎作參考點，並根據各參考點的相對關係，辨識使用者基本的頭部運動狀態與角度，將辨識結果顯示在螢幕上，其辨識率達90%。

This study aims to establish a system which can recognize the gestures of the head movement. Two real-time and effective methods are presented herein to identify the gestures of the head movement. The first method is to utilize the 3-axis sensor with an accelerometer, a gyroscope and a magnetometer mounted on user’s head for respectively measuring the gravity acceleration, angular velocity and magnetic flux to estimate the inclination and orientation angles of the head gesture. Finally, Kalman filter is employed to eliminate the Gauss noise. On the basis of inclination and orientation angles prior to filtering, the angle form integration of the angular velocity is calibrated to be the gesture angle as derivation gestures of the head movement that is shown with 95% accuracy in recognition rate. Moreover, the other method is the face detection capturing image information on user’s face via a camera including the relative positions of the face, eyes, lips as well as mandible and then filtering the noise via image processing as the reference points. Hence, the gesture and orientation of user’s head movement can be recognized based on the relationships between these reference points. The recognition result is shown on the screen that it still has 90% accuracy of recognition rate.

目錄

摘要 I
Abstract II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
第一章. 序論 1
第二章. 系統架構與分析 4
2.1 頭部運動分析 4
2.2 系統架構 6
2.2.1 三軸陀螺儀 9
2.2.2 三軸加速度計 10
2.2.3 三軸磁力計 11
2.3 座標系統 12
2.3.1 座標系統 12
2.3.2 座標軸轉換 13
2.3.3 任意軸旋轉 16
第三章. 感測器誤差校正與量測分析 19
3.1 磁力計 19
3.1.1 硬磁干擾校正 20
3.1.2 軟磁干擾校正 22
3.1.3 方位角計算 27
3.2 加速度計 28
3.2.1 偏移量校正 28
3.2.2 解析度校正 30
3.3 陀螺儀 33
3.3.1 偏移量校正 33
3.3.2 比例校正 35
3.4 系統整合 36
3.4.2 卡爾曼濾波器 37
第四章. 影像辨識 47
4.1 色彩空間與形態學 47
4.1.1 色彩空間 47
4.1.2 形態學 48
4.2 膚色分割 50
4.3 唇色區域偵測 56
4.4 眼睛辨識 59
4.5 頭部姿態 61
第五章. 實驗結果與討論 64
5.1 實驗感測器模組辨識頭部姿態 64
5.1.1 靜態實驗 67
5.1.2 動態實驗 72
5.2 實驗影像視覺模組辨識頭部姿態 73
第六章. 結語與未來展望 76
參考文獻 78

參考文獻

[1]M. Duvinage, T. Castermans, T. Dutoit, "Control of a lower limb active prosthesis with eye movement sequences," IEEE Symposium on,Computational Intelligence, Cognitive Algorithms, Mind, and Brain, pp. 1-7, 2011.
[2]A.L. Yuille, D.S. Cohen, P.W. Hallinan, "Feature extraction from faces using deformable templates," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 104-109, 1989.
[3]Q. Chen, H. Wu, T. Fukumoto, M. Yachida, "3D head pose estimation without feature tracking," Third IEEE International Conference on Automatic Face and Gesture Recognition, pp. 88-93, 1998.
[4]袁信，鄭諤，捷聯式慣性導航，航空專業教材編審組，第48-63頁，1985。
[5]黃良吉，GPS與感測器整合於三維地面車輛定位之應用，國立台灣科技大學機械工程系碩士學位論文，2006。
[6]Christopher Konvalin, Compensating for tilt, hard-iron, and soft-iron effects memsense LLC, 2009, http://www.sensorsmag.com/sensors/motion-velocity-displacement/compensating-tilt-hard-iron-and-soft-iron-effects-6475
[7]張靜，金志華和田蔚風，無航向基準時數字式磁羅盤的自差校正，上海交通大學學報，第38卷，第10期，1757-1760頁，2004。
[8]張弘毅，整合GPS與MEMS感測器於自行車導航系統之應用，國立台灣科技大學機械工程系碩士學位論文，2010。
[9]A. Olivares, G. Olivares, J.M. Gorriz and J. Ramirez, "High-efficiency low-cost accelerometer-aided gyroscope calibration," International Conference on Test and Measurement,Vol. 1, pp. 354-360, 2009.
[10]Steven M. Kay, Fundamentals of statistical signal processing: estimation theory, prentice hall, pp. 419-478, 1993.
[11]陳繼棠，結合膚色區域分割與主要成份分析於多人臉部辨識，國立臺灣海洋大學機械與機電工程學系碩士學位論文，2006。
[12]鄭凱方,人臉可辨識度計算用於監控系統中人臉正面最佳影像判定,國立中央大學資訊工程研究所碩士論文，2005。
[13]郭光哲,以模糊邏輯為基礎的智慧型輪椅自動充電與臉部控制法之研究,國立台北科技大學自動化科技研究所碩士學位論文，2012。
[14]C.C. Chiang, W.K. Tai, M.T. Yang, Y.T. Huang and C.J. Huang, "A novel method for detecting lips, eyes and faces in real time," Journal Real-Time Imaging, Vol.9, No. 4, pp. 277-287, 2003
[15]林志明，視覺式嘴唇輪廓偵測與追蹤—應用於產生MPEG-4臉部動畫參數，國立東華大學資訊工程學系碩士論文，2006。
[16]R.L. Hsu, A.M. Mohamed and A.K. Jain, "Face detection in color images," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, pp. 696-706, 2002.
[17]P.R. Tabrizi, R.A. Zoroofi, "Drowsiness detection based on brightness and numeral features of eye image," Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 1310-1313, 2009.
[18]陳哲，全姿態飛機捷聯式系統姿態角的計算，北京航空學院。