本論文旨於設計與實現一個能夠自動追蹤使用者目光之自動瞄準系統。此自動射擊系統主要由電力控制之遊戲手槍系統和一個穿戴式目光追蹤器所組成，目光追蹤器安裝了一個攝影機和九軸的慣性量測單元在頭盔上，根據所獲取使用者目光方向，讓遊戲手槍能夠自動瞄準使用者所注視之物體。本文首先，介紹所研製自動瞄準系統之系統架構、遊戲手槍系統以及頭盔機構設計，為了實現低成本頭盔，採用了3-D印表機來製作機構零件，此可運用便宜的原料製作出強韌的機構零件，再來實現目光偵測器以及追蹤系統。本文利用深度信賴網路(DBN)建立出使用者眼睛運動和遊戲手槍所需要移動方向之映射關係，這個以DBN為基底之目光追蹤器讓自動瞄準系統能夠準確並及時地瞄準物體。最後實驗結果顯示，在不同的使用者使用下，所提出自動瞄準與射擊系統，平均準確度可高達96%。
關鍵字：遊戲手槍、目光追蹤器、深度信賴網路、自動瞄準系統

This thesis designs and implements an auto-aiming system, where user’s gaze can be tracked automatically. The auto-aiming system is composed of an electrical controlled gun system and a wearable gaze tracker, which contains a camera and a 9-axis IMU mounted on a helmet. According to a user’s gaze direction captured by the helmet camera, the game gun can automatically aim an object that the user is looking at. First, the architecture of the auto-aiming system, the design concept of the gun control system and the helmet are introduced. In order to design the helmet with lower cost, a 3-D printer is adopted. We can use the cheap material to print the tough structures. Next, gaze detection and tracking system are presented. The mapping between user’s eye movements and desired gun directions is established by a Deep Belief Network (DBN). This DBN-based gaze tracker allows the auto-aiming shooting system to aim the target timely and accurately. Finally, the experimental results demonstrate that the proposed auto-aiming system for different users can achieve an average accuracy of 96%.
Keywords: Game gun, Gaze tracker, Deep brief network, Auto-aiming system

Reference
[1] J. Steuer, “Defining virtual reality: dimensions determining telepresence,” Journal of Communication, vol. 42, no. 4, pp. 73–93, 1992.
[2] C. Cruz-Neira, D. Sandin, and T. DeFanti, “Surround-screen projection-based virtual reality,” in Proceedings of the 20th annual conference on Computer graphics and interactive techniques, 1993.
[3] PLA, https://en.wikipedia.org/wiki/Polylactic_acid.
[4] R. Poli, J. Kennedy, and T. Blackwell, “Particle swarm optimization,” Swarm intelligence, vol. 1, no. 1, pp. 33–57, 2007.
[5] J. Kennedy, “Particle swarm optimization,” Encyclopedia of machine learning, pp.760–766, 2011.
[6] D. Karaboga and B. Basturk, “A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm,” Journal of Global Optimization, vol. 39, no. 3, pp. 459–471, 2007.
[7] D. Karaboga and B. Basturk, “On the performance of artificial bee colony (ABC) algorithm,” Applied Soft Computing, vol. 8, no. 1, pp. 687–697, 2008.
[8] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGA-II,” IEEE Trans. Evolutionary Computation, vol. 6, no. 2, pp. 182–197, 2002.
[9] G. Morris, D. Goodsell, R. Halliday, R. Huey, W. Hart, R. Belew, and A. Olson, “Automated docking using a Lamarckian genetic algorithm and an empirical binding free energy function,” Journal of computational chemistry, vol. 19, no. 14, pp. 1639–1662, 1998.
[10] M. Hagan, H. Demuth, and M. Beale, Neural network design, Boston: PWS Pub., 1996.
[11] G. Hinton, S. Osindero, and Y. Teh, “A fast learning algorithm for deep belief nets,” Neural Computation, vol. 18, no. 7, pp. 1527–1554, 2006.
[12] G. Hinton, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504–507, 2006.
[13] L. Deng and D. Yu, “Deep learning: Methods and applications,” FNT in Signal Processing, vol. 7, no. 3-4, pp. 197–387, 2014.
[14] H. Lee, R. Grosse, R. Ranganath, and A. Ng, “Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations,” in Proc. Int'l Conf. Machine Learning, pp. 609-616, 2009.
[15] V. Nair and G. E. Hinton, “Rectified linear units improve restricted Boltzmann machines,” in Proc. Int'l Conf. Machine Learning, pp. 807-814, 2010.
[16] G. Hinton, “A practical guide to training restricted Boltzmann machines,” Neural Networks: Tricks of the Trade, pp. 599–619, 2012.
[17] E. Scheinerman, Mathematics: A Discrete Introduction, Boston, pp. 363, 2012.
[18] G. Hinton, “Training products of experts by minimizing contrastive divergence,” Neural Computation, vol. 14, no. 8, pp. 1771–1800, 2002.
[19] M. A. Carreira-Perpignan and G. E. Hinton, “On contrastive divergence learning,” in Proc. Artif. Intell. Statist., pp. 33–41, 2005.
[20] D. Rumelhart, G. Hinton, and R. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986.
[21] D. MacKay, “A practical Bayesian framework for backpropagation networks,” Neural Computation, vol. 4, no. 3, pp. 448–472, 1992.
[22] R. Hecht-Nielsen, “Theory of the backpropagation neural network,” Neural Networks, vol. 1, pp. 445, 1988.
[23] NERF, http://nerf.hasbro.com/en-us.
[24] Mbot printer, http://www.woi3d.com.tw/ProductContent.aspx?ID=29&CID=32
[25] Solidworks, http://www.solidworks.com/.
[26] Sony tripod, http://store.sony.com.tw/product/VCT-R640.
[27] Beats Solo2, http://www.new-beats.com.tw/17346.html.
[28] Acer Aspire V, http://www.acer.com/ac/zh/TW/content/series/aspirevnitro.
[29] Microsoft visual studio 2010, https://www.visualstudio.com/zh-tw/visual-studio-homepage-vs.aspx.
[30] Logitech Webcam, http://support.logitech.com/en_us/product/webcam-c905.
[31] Asus Xtion PRO, https://www.asus.com/tw/3D-Sensor/Xtion_PRO/.
[32] ABS, https://en.wikipedia.org/wiki/Acrylonitrile_butadiene_styrene.
[33] B. Tymrak, M. Kreiger, and J. Pearce, “Mechanical properties of components fabricated with open-source 3-D printers under realistic environmental conditions,” Materials & Design, vol. 58, pp. 242–246, 2014.
[34] J. Newton, “Lightweight honeycomb panel structure,” The Journal of the Acoustical Society of America, vol. 99, no. 4, pp. 1821, 1996.
[35] ROBOTIS, http://www.robotis.com/index/.
[36] x-IMU, http://www.x-io.co.uk/products/x-imu/.
[37] D. Gebre-Egziabher, R. Hayward, and J. Powell, “A low-cost GPS/inertial attitude heading reference system (AHRS) for general aviation applications,” IEEE Position Location and Navigation Symposium, pp. 518–525, 1998.
[38] N. Khaneja, T. Reiss, C. Kehlet, T. Schulte-Herbrüggen, and S. Glaser, “Optimal control of coupled spin dynamics: design of NMR pulse sequences by gradient ascent algorithms,” Journal of Magnetic Resonance, vol. 172, no. 2, pp. 296–305, 2005.
[39] W. R. Gilks, “Markov chain monte carlo,” John Wiley & Sons, 2005.
[40] C. J. Geyer, “Practical Markov Chain Monte Carlo,” Statistical Science, vol. 7, no. 4, pp. 473–483, 1992.
[41] E. George and R. McCulloch, “Variable selection via Gibbs sampling,” Journal of the American Statistical Association, vol. 88, no. 423, pp. 881–889, 1993.
[42] UCI machine learning repository, http://archive.ics.uci.edu/ml/.
[43] K. Murphy, “The Bayes net toolbox for Matlab,” Computing Science and Statistics, vol. 33, no. 2, pp. 1024–1034, 2001.
[44] Y. X. Zhang, “Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis,” Talanta, vol. 73, no. 1, pp. 68–75, 2007.
[45] L. Xu, A. Krzyzak, and E. Oja, “Rival penalized competitive learning for clustering analysis, RBF net, and curve detection,” IEEE Trans. Neural Networks, vol. 4, no. 4, pp. 636–649, 1993.
[46] A. Bahrololoum, H. Nezamabadi-pour, H. Bahrololoum, and M. Saeed, “A prototype classifier based on gravitational search algorithm,” Applied Soft Computing, vol. 12, pp. 819–825, 2012
[47] P. Viola and M. J. Jones, “Robust real-time object detection,” In IEEE ICCV Workshop on Statistical and Computational Thesis of Vision, 2001.
[48] P. Viola and M. J. Jones, “Robust real-time face detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137–154, 2004.
[49] Y. Freund and R. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, vol. 55, no. 1, pp. 119–139, 1997.
[50] OpenCV, http://opencv.org/.
[51] R. Haralick, S. Sternberg, and X. Zhuang, “Image analysis using mathematical morphology,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 532–550, 1987.
[52] J. N. Kapur, P. K. Sahoo, and A. K. C. Wong, “A new method for gray-level picture thresholding using the entropy of the histogram,” Computer Vision, Graphics and Image Processing, vol. 29, pp. 273–285, 1985.