簡易檢索 / 詳目顯示

研究生: 林雋益
Lin, Chun-Yi
論文名稱: 具頭動補償之高速可見光眼動儀
High Speed Visible Light Gaze Tracking System with Head Motion Compensation
指導教授: 高文忠
Kao, Wen-Chung
學位類別: 碩士
Master
系所名稱: 電機工程學系
Department of Electrical Engineering
論文出版年: 2016
畢業學年度: 104
語文別: 中文
論文頁數: 97
中文關鍵詞: 可見光眼動儀高速
DOI URL: https://doi.org/10.6345/NTNU202204377
論文種類: 學術論文
相關次數: 點閱:171下載:13
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
  • 隨著科技的進步越來越重視使用者體驗,人們可透過眼動儀觀察眼睛凝視位置,了解整個視覺歷程與行為脈絡,以更貼近使用者真實感受與體驗。眼動儀的應用範圍包括3C產品、數位廣告及醫療生技。目前市面上的眼動儀是以紅外線光源達到眼睛視線的追蹤,然而長時間的紅外線照射會對眼睛帶來相當大的傷害。因此,近來有許多研究開始專研如何利用自然光源以取代紅外線照射對眼球的不良影響。

    本研究目的是強調利用自然光源照射原理達到眼睛視線的追蹤。這款眼動儀系統主要是架構在外觀法的基礎上並強化其模型匹配的精準度,同時也使用形狀法加強模型建立的穩健性。此外,本研究成功導入頭部移動補償,有效彌補外觀法的缺點。在系統速度上,則加入粒子群聚演算法提升系統的運作速度。因此,本研究開發的眼動儀系統精準度高達1.17度,系統的處理速度為每秒250個畫面。

    Due to the advancement of technology, eye trackers are used to help us understand human behavior and improve overall user experience. The gaze tracking systems are used in wide range of applications such as electronic devices, digital advertising, and medical biotechnology. Most gaze tracking systems use an infrared light source to track gaze positions, however, long hours of infrared light exposure may cause eye hurt. As a result, recent researches are focusing on how to replace infrared light source with visible light.

    The aim of this research is to develop gaze tracking systems which use visible light to track user’s gaze positions. This gaze tracking system adopts appearance-based method to improve the accuracy of iris recognition. In addition, we use shape-based method for head movement compensation which not only enhances the robustness but also increases the accuracy of gaze tracking systems. Besides, the particle swarm optimization is applied to gaze tracking systems to reduce the processing time. Therefore, our system can achieve 1.17 high degree of accuracy and quick processing speed of 250 frames per second

    中文摘要 i 英文摘要 ii 誌 謝 iii 目 錄 iv 表 目 錄 vii 圖 目 錄 viii 第一章 緒論 1 1.1 研究背景 1 1.2 研究目的 2 1.3 研究問題 3 1.4 論文架構 4 第二章 眼動儀方法分類和選擇 5 2.1 虹膜中心追蹤方法 5 2.1.1 Shape-Based 6 2.1.2 Appearance-Based 7 2.1.3 Reflected-Based 9 2.2 凝視點映射方法 10 2.2.1 多項式映射 11 2.2.2 計算凝視點空間位置 11 2.3 選擇的方法 12 2.4 改進的方式 14 第三章 系統架構圖 15 3.1 系統架構圖 15 3.2 建立眼球模型 16 3.2.1 圖像去雜訊 17 3.2.2 直方圖等化 19 3.2.3 選擇虹膜ROI 19 3.2.4 虹膜外型提取 21 3.2.5 虹膜輪廓提取 27 3.2.6 類霍夫圓處理 31 3.2.7 眼角位置偵測 38 3.3 建立映射模型 45 3.3.1 計算眼角位移 46 3.3.2 眼球模型的選擇 48 3.3.3 計算映射模型參數 50 3.4 計算眼睛凝視位置 51 3.4.1 映射模型映射 52 3.5 粒子群聚演算法(PSO)加速 52 3.5.1 眼球模型加速 52 3.5.2 眼角位移計算加速 59 3.6 平行化運算 66 第四章 研究成果 67 4.1 測試環境 67 4.2 建立模型的強健性 70 4.3 自適應的匹配角度 72 4.4 頭部補償的比較 75 4.5 頭動補償加自適應匹配角度比較 78 4.6 各種方法精準度比較 81 4.7 系統精準度 82 4.8 系統速度 91 4.9 系統限制 92 第五章 結論及未來展望 93 5.1 結論 93 5.2 未來展望 93 參考文獻 94 自 傳 96 學術成就 97

    [1] K. N. Kim and R. S. Ramakrishna, “Vision-based eye-gaze tracking for human computer interface,” in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, vol. 2, pp. 324–329, Oct. 1999.
    [2] J. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, Nov. 1986.
    [3] J. Zhu and J. Yang, “Subpixel Eye Gaze Tracking,” in Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 131-136, May 2002.
    [4] I. Sobel and G. Feldman, “A 3x3 isotropic gradient operator for image processing,” presented at the Stanford Artificial Project in, 1968.
    [5] R. Keys, “Cubic convolution interpolation for digital image processing,” IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 29, no. 6, pp. 1153-1160, Dec. 1981.
    [6] T. Moriyama, T. Kanade, J. Xiao, and J.F. Cohn, “Meticulously Detailed Eye Region Model and Its Application to Analysis of Facial Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 5, pp. 738-752, May 2006.
    [7] S. J. Baek, K. A. Choi, C. Ma, Y. H. Kim, and S. J. Ko, “Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems,” IEEE Trans. Consumer Electron., vol. 59, no. 2, pp. 415-421, May 2013.
    [8] J. Sigut and S.-A. Sidha, “Iris center corneal reflection method for gaze tracking using visible light,” IEEE Trans. Biomedical Eng., vol. 58, no. 2, pp. 411-419, Feb. 2011.
    [9] H. Lee, N. Iqbal, W. Chang, and S. Y. Lee, “A calibration method for eye-gaze estimation systems based on 3D geometrical optics,” IEEE Sensors J., vol. 13, no. 9, pp. 3219–3225, Jun. 2013.
    [10] C. H. Marimnoto, et. al. ”Keeping an Eye for HCI,” in Proc. IEEE Symp. on Computer Graphics and Image Processing, pp.171-176, Oct. 1999.
    [11] J. G. Wang, E. Sung and R. Venkateswarlu, “Estimating the eye gaze from one eye,” Computer Vision and Image Understanding, vol. 98, no. 1, pp. 83-103, Apr. 2005.
    [12] J. Kennedy, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks, vol. 4, pp. 1942-1948, Dec 1995.
    [13] C. Y. Lee, “Gaze Tracking with Particle Swarm Optimization,” M.S. thesis, Dept. Electron. Eng., Nat. Taiwan Normal Univ., Taipei, Taiwan, 2015.
    [14] W. C. Kao, et al., "Gaze tracking with particle swarm optimization," Int. Symp. on Consumer Electronics, pp. 1-2, Jun. 2015.
    [15] C. W. Chang, “The effects of graphemic and phonetic cues in text reading : Evidence from eye movements”, M.S. thesis, Graduate Institute of Learning and Instruction, Nat. Central Univ., Taoyuan, Taiwan, 2005.
    [16] S. Suzuki, “Topological structural analysis of digitized binary Images by border following,” Computer Vision, Graphics, and Image Processing, vol. 30, no. 1, pp. 32-46, Apr. 1985.
    [17] F. Meyer, “Color image segmentation,” Int. Conf. Image Processing and its Applications, pp. 303-306, 1992.
    [18] P. R. Reddy, V. Amarnadh and M. Bhaskar, “Evaluation of stopping criterion in contour tracing algorithms,” Int. J. of Computer Sci. and Inform. Technologies, vol. 3, no. 3, pp. 3888-3894, 2012.
    [19] D. W. Hansen, Q. Ji, “In the eye of the beholder: a survey of models for eyes and gaze,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 3, pp. 478-500, Feb. 2009.

    下載圖示
    QR CODE