本篇論文主要提出基於一個自行設計的無線影像擷取硬體以及影像處理演算方法來監控並且追蹤閉眼時的眼球移動狀態。此系統主要有三部分- 120*160像素的CMOS影像感測鏡頭，2.4~2.524GHz無線傳輸模組，以及在電腦端的發展軟體。首先，CMOS影像感測器會連續地將一幅最新偵測到的影像寫入到一個32KByte的外部記憶體中，在傳送端的MCU將儲存在記憶體中的資料透過無線傳輸模組以1Mbps的速度傳送至接收端。由於影像的取樣能力以及一些協定的因素，整體的傳送速度建議不要低於800Kbps。接收端的MCU會將其由傳送端經過空氣送至無線接收模組的封包以SPI的方式clock out至接收端的外部記憶體中，最後透過RS232把此影像送至電腦端的buffer以供電腦上的軟體存取。

在電腦端所發展的影像處理演算法首先將因為無線傳輸過程中產生的雜訊去除，在此使用了空間域的二維高斯低通濾波器，接著做一些前處理來鎖定我們要定義在影像中的Region of Interest (ROI)，從此ROI中抽取一些相關的特徵數值，最後將這些特徵送至Support Vector Machine (SVM)的類神經網路做訓練。我們以所接收到的最新的二十張影像來組成一個AVI File的video，此發展的系統將有能力在每一段時間間隔當中判斷所收到的影片是在動或不動的狀態。最後，使用不同特徵組合訓練的類神經網路之輸出的正確率也在第五章列出來做比較。

In the thesis, a fully automatic computerized system was proposed to monitor and track the close eyeball motion based on the designed image capture module and its peripheral circuits followed by the application of image processing method. The system is composed of three main parts- CMOS image acquisition module, wireless communication module which operates under 2.4~2.524GHz and image processing unit on PC host. The CMOS image sensor with 120*160 pixels square resolution continuously writes an sensed image onto a 32K*8bits SRAM. A MCU in the transmitting end acts as an intermediate between the SRAM and the wireless transmitting module with the data rate up to 1Mbps. Due to the capacity of sampled image and protocol, the baud rate of transmission module is suggested to be higher than 800 kbps. The MCU in the receiving end clocks out the incoming packages from the wireless receiving module and sends these data to the host PC terminal by means of the RS232 channel. Finally, the developed algorithm on PC end is accomplished to judge close eyeball motion. In the PC terminal, the noise reduction method is first applied to an incoming image, the two dimensional Gaussian low pass filter is adopted herein, then, extracting some types of features from the defined Region of Interest (ROI) which is located after some preprocessing procedures. Finally, the optical flux analysis with support vector machine neural network training is performed. The system has the ability to judge whether a captured video is in a moving or in a freezing status within a time interval. A video is composed of twenty frames. The correct rates of the outputs of neural network which was trained by the various combinations of the features are compared as well.

Reference

[1]N. R. Carlson, Physiology of Behavior 8th Edition, Allyn and Bacon, 2003

[2] H. Berger, “Ueber das Elektroenzephalogramm des Menschen,” Arch. Psychiatr. Nervenkr, 1929

[3] 鄭智銘 “睡眠監測相關研究簡介” Jul., 2002.

[4]Chiwen Hsieh, Chiwen Kan, Tailang Jong, Tailee Chen, and Shenhorng Wang, “EYE-MASK OF CLOSED EYES MONITORING BY IMAGE SENSING WITH WIRELESS TECHNIQUES” Dep. of Electrical Engineering, National Tsing-Hwa University, Taiwan, ROC. Dep. of Physics, National Central University, Taiwan, ROC, 2004.

[5] U. Anliker, J. A. Ward, P. Lukowicz, G. Troester, F. Dolveck, M. Baer, F. Keita, E. B. Schenker, F. Catarsi, L. Coluccini, A. Belardinelli, D. Shklarski, M. Alon, E. Hirt, R. Schmid, and M. Vuskovic, “AMON: A Wearable Multiparameter Medical Monitoring and Alert System” IEEE Trans. on Info. Tech. in Biomedicine, Vol. 8, No.4, Dec. 2004

[6] K.P. White, T.E. Hutchinson, and J.M. Carley, “Spatially Dynamic Calibration of an Eye-Tracking System,” IEEE Trans. on Systems, Man, and Cybernetics, Vol. 23, No. 4, pp. 1162-1168, 1993.

[7] M. Eriksson, N. P. Papanikolopoulos, “Eye-tracking for Detection of Driver Fatigue,” IEEE Conference on Intelligent Transportation System, 1997, ITSC 97.

[8] Bin.Chen, Zhi-Qiang Liu, Xiang Hua Zhu, “Eye Location in Human Face Location Using Fuzzy Integral,” IEEE Conf, Volume 4, 2-5 Page(s):2500 - 2502, Nov. 2003

[9] Fang-Chung Yang, Chung-Hsien Kuo, Ming-Yuan Tsia, Shiao-Chun Huang, “Image-Based Sleep Motion Recognition Using Artificial Neural Network,” IEEE Conf Volume 5, 2-5 Page(s):2775 – 2780, Nov. 2003

[10] K. Sung, M.F. Reschke, “A Model-Based Approach for the Measurement of Eye Movements Using Image Processing,” Technical Paper 3680, NASA, Apr. 1997

[11] T. Ashit, M. John_Michael, M. Steve, L. Raymond, L. Clayton, and L.L. James, “Eye–tracking architecture for biometrics and remote monitoring,” Applied Optics, Vol.44, No.5, pp 693-700, Feb., 2005.

[12] G. M. Hatzilabron, N. Greenberg, R. J. Sclabassi, T. Carroll, R. D. Guthrie, and Mark S. Scher,”A Comparison of Conventional and Matched Filtering Techniques for Rapid Eye Movement Detection of the Newborn,” IEEE transaction on biomedical engineering, Vol. 41, NO. 10, pp 990-995, Oct., 1994.

[13] Q. R. Chen, W. K. Cham and H. T. Tsui, “A Method for Estimation and Accurately Extracting the Eyebrow in Human Face Image,” Proceedings. IEEE 2002 International Conference on Volume 3, Page(s):793 – 796 vol.3, June 2002

[14] K. Sung, and M. F. Reschke, “A Model-Based Approach for the Measurement of Eye Movements Using Image Processing,” nasa, Technical Paper 3680, April 1997.

[15] Tse-Yu Yang, “The Design and Implementation of an SD I/O Imaging card”, July, 2002.

[16] 林金寶 “影像處理及辨識理論與實務─8051 單晶片 C 語言程式設計實例”, Apr, 2003.

[17] Product Specification of “Single Chip 2.4G Transceiver nRF2401” NORDIC Semiconductor

[18] http://en.wikipedia.org/wiki/Cyclic_redundancy_check

[19http://www.ensc.sfu.ca/people/grad/brassard/personal/THESIS/node186.html

[20]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd edition,Prentice Hall, 2002.

[21]S. Haykin, Neural Networks, 2nd edition, Prentice Hall, 1999.

[22]Chih-Wen Kan, “An Image-Based Closed-Eye Motion Detection System Applicable to a Monitoring Eyemask,”, July, 2005.

[23]D. Vignon, B.C. Lovell, and R.J. Andrews, “General Purpose Real-Time Object Tracking Using Hausdorff Transforms,” IPMU2002: Special Session on Intelligent Systems for Video Processing, 2002.

[24] I. Ravyse, H. Sahli, M.J.T. Reinders, J. Cornelis, “Eye Activity Detection and Recognition using Morphological Scale-space Decomposition,” ICPR Proceedings of the International Conference on Pattern Recognition (ICPR'00)-Volume 1 - Volume 1, 2000

[25] R. Brunelli and T. Poggio, “Face Recognition: Features versus Templates,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 15, No. 10, Oct. 1993.

[26] Y. L. Tian, T. Kanade, and J. F. Cohn, “Dual-state Parametric Eye Tracking,” Proceedings of the Fourth IEEE International Conference on, 2000

[27] T. Ohnishi, W. Chen, T. Kobayashi, Y. Honda, T. Saito, T. Nemoto, R. Kusunose, “Continuous Measurments of Eyeball Area and Spectrum Analysis Toward The Quntification of Rest Rhythm of Horse By Image Processing ,” IEEE Conf, pp 3363-3366, 2001.

[28]Hong Man, “Motion Track / Object Recognition,” Dec., 2002.

[29]I. Ravyseu, H. Sahliu, M.J.T. Reinderst, J. Cornelisn “Eye Activity Detection and Recognition using Morphological Scale-space Decomposition,” IEEE Conf on Volume 1, Page(s):1080 - 1083, Sept. 2000.

[30] Z. Hammal, A. Caplier, “Eyes and Eyebrow Parametric Models for Automatic Segmentation,” IEEE Conf Page(s):138 – 141, March 2004

[31]Benno L. Petrig, Josef Bigun, and Marc G. Curchod, “Motion Estimation of Ocular Fundus Images,” IEEE Conf, Volume 3, 16-19 Page(s):691 – 694, Sept. 1996

[32]Azzam F G Taktak, Sarah Simpson, Sam Patel and Georg Meyer, “Neural network analysis of oxygenation signals in infants during sleep,” IOP Publishing Ltd, PP N11-N22, 2000.

[33]T. Penzel, K. Kesper, V. Gross, H. F. Becker, C. Vogelmeier, “Problems in Automatic Sleep Scoring Applied to Sleep Apnea,” IEEE Conf, Volume 1, 17-21 Page(s):358 – 361, Sept. 2003

[34]D. Barschdorff, D. Gerherdt, “Rapid Eye Movement Detection in Infants Using A Neural Network,” IEEE Conf, Volume 3, 31 Page(s):935 – 936, Nov. 1996

[35]Theodore A. Camus, Richard Wildes, “Reliable and Fast Eye Finding in Close-up Images,” IEEE Conf, Volume 1, 11-15 Page(s):389 – 394, Aug. 2002

[36]Fernando De La Torre, Carlos Javier Garcia Rubio, Elisa Martinez, “Subspace Eyetracking for Driver Warning,” IEEE Conf, Volume 3, 14-17 Page(s):III - 329-32, Sept. 2003

[37]Samuel A. Mickelson, “The use of sleep tests for suspected sleep disordered,” Ear, Nose & Throat Journal, Sept, 1999

[38]T.A. Camus, R. Wildes, O. Toronto, “Reliable and Fast Eye Finding in Close-up Images,” 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1, p. 10389, 2002.