臺灣博碩士論文加值系統

因為疲勞駕駛所造成的意外事故屢見不鮮，怎麼降低因為駕駛精神不濟導致的事故發生，在國內外已經有很多學者研究，駕駛人的精神狀態可以透過眼睛的眨眼頻率以及透過量測生理信號的方式來評估。

本論文提出了一套結合生理信號與人臉特徵的瞌睡偵測系統，結合兩種方法的優點，提升瞌睡偵測準確度。演算法主要分為三個部分、包括生理信號偵測、人眼狀態偵測以及瞌睡條件判斷。利用有近紅外線功能的Webcam，照射臉部影像來達到非接觸式的測量，改善了使用接觸式穿戴式裝置的不便，以及在較暗的環境下也可以使用。且能在不同光源下選擇適合的RGB通道取得較好的生理信號。

我們提出的瞌睡偵測系統，主要是利用經由我們演算法得到的交感/副交感神經平衡指標(LF/HF)以及PERCLOS作為瞌睡判斷依據，且使用EEG信號做對比驗證我們的可靠度。

Accidents caused by fatigue driving have frequently occurred. Many scholars have been studying how to reduce the cause by fatigue driving. The driver's spirit status can be assessed through the blinking frequency of eyes and by measuring the physiological signal.

In this thesis, a drowsiness detection system is proposed to combine physiological signals and facial features to improve the drowsy detection accuracy. The proposed algorithm includes three functions, which are physiological detection, eye state detection, and drowsiness judgement. Facial Image captured by NIR webcam can achieve non-contact measurement, which improves the inconvenience of using a contact wearable device, and can still work in the dark environment. The appropriate RGB channel under different light sources can be chosen to obtain better physiological signals.

The drowsiness detection system uses the proposed algorithm to get sympathetic / parasympathetic nervous balance index (LF/HF) and PERCLOS as the drowsiness judgment basis. The EEG (electroencephalography) signal is used as a contrast to validate the reliability of the proposed method.

誌謝 i
中文摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 viii
第1章 緒論 1
1.1研究背景與動機 1
1.2論文架構 2
第2章 文獻探討 3
2.1生理信號相關介紹 3
2.1.1 光體積變化描記圖(Photoplethysmography, PPG) 3
2.1.2 光體積變化描記圖影像 5
2.1.3 心率變異度分析 7
2.1.4 脈搏變異度分析 9
2.1.5 自律神經系統 10
2.1.6 LF/HF比值分析介紹 11
2.2 張閉眼偵測相關介紹 12
2.2.1 臉部、眼部偵測相關介紹 12
2.2.2 張閉眼偵測 13
2.2.3 PERCLOS (Percentage of eyelid closure) 14
2.3 腦波分析 15
第3章 瞌睡偵測系統架構與理論 17
3.1 系統架構與流程 17
3.2 R/G Channel 19
3.3 ROI設定 22
3.4 PRV分析 25
3.4.1 PPI偵測法 (PPI detection) 25
3.4.2功率密度頻譜 27
3.5 張閉眼偵測 28
3.6 瞌睡判斷(Drowsiness Judge) 30
3.6.1 進入睡眠狀態 30
3.6.2 判斷條件 31
3.6.3 瞌睡判斷分析 33
第4章 嵌入式系統與實驗結果 35
4.1 開發環境介紹 35
4.2 Qt介紹 37
4.3 環境架設流程 38
4.3.1 Ubuntu Install 39
4.3.2 OpenCV Install 39
4.3.3 Qt Install 40
4.3.4 Webcam介紹及控制 41
4.3.5 Zedboard Linaro 建置 43
4.4 GUI介面 44
4.5 實驗流程 45
4.6 實驗模擬與結果 47
第5章 結論與未來展望 52
文獻參考 53

[1]The National Highway Traffic Safety Administration (NHTSA)
http://www.nhtsa.gov/
[2]T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, “Wearable photoplethysmographic sensors—past and present,” Electronics, vol. 3, pp. 282-302, 2014.
[3]郭柏妮, 林志陽,“使用視訊元件量測生命徵象的研究,” Journal of Information Technology and Applications, vol. 6, pp. 112-118, 2012.
[4]張建煒,“基於霍夫轉換之駕駛疲勞偵測系統與嵌入式系統實現,”國立中興大學電機工程學系碩士論文, 2014
[5]陳敬修, “利用非侵入式Plethysmography信號評估手術病患舒張壓變化趨勢之研究”,中山大學機械與機電工程研究所碩士論文, 2004
[6]PixArt Healthcare , http://healthcare.pixart.com
[7]Medis , https://medis.company/cms/index.php
[8]D. Cho and B. Lee, “Non-contact robust heart rate estimation using HSV color model and matrix-based IIR filter in the face video imaging,” in Engineering in Medicine and Biology Society (EMBC), 2016 IEEE 38th Annual International Conference, 2016, pp. 3847-3850.
[9]林勤恆, “Contact-Free Measurement of Cardiac Pulse using IR Video Imaging,” 國立中興大學電機工程學系碩士學位論文, 2015
[10]L. Tarassenko, M. Villarroel, A. Guazzi, J. Jorge, D. Clifton, and C. Pugh, “Non-contact video-based vital sign monitoring using ambient light and auto-regressive models,” Physiological Measurement, vol. 35, p. 807, 2014.
[11]WP ’s HP http://www.fen-net.de/walter.preiss/e/wp_frame.html
[12]M.-Z. Poh, D. J. McDuff, and R. W. Picard, “Non-contact, automated cardiac pulse measurements using video imaging and blind source separation,” Optics Express, vol. 18, pp. 10762-10774, 2010.
[13]M. J. Reed, C. Robertson, and P. Addison, “Heart rate variability measurements and the prediction of ventricular arrhythmias,” Qjm, vol. 98, pp. 87-95, 2005.
[14]翁根本,何慈育,歐善福,林竹川,謝凱生,“心率變動性分析,”台灣醫界, vol. 52, no. 6, 2009
[15]S. Akselrod, D. Gordon, F. A. Ubel, D. C. Shannon, A. C. Barger, and R. J. Cohen, “Power spectrum analysis of heart rate fluctuation: a quantitative probe of beat-to-beat cardiovascular control,” Science, pp. 220-222, 1981.
[16]J. T. Bigger, J. L. Fleiss, R. C. Steinman, L. M. Rolnitzky, R. E. Kleiger, and J. N. Rottman, “Correlations among time and frequency domain measures of heart period variability two weeks after acute myocardial infarction,” The American Journal of Cardiology, vol. 69, pp. 891-898, 1992.
[17]Task Force of the European Society of Cardiology the North American Society of Pacing Electrophysiology - Heart Rate Variability, http://circ.ahajournals.org/content/93/5/1043
[18]N. Pinheiro, R. Couceiro, J. Henriques, J. Muehlsteff, I. Quintal, L. Gonçalves, et al., “Can PPG be used for HRV analysis?, ” in Proc. of 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 2016, pp. 2945-2949.
[19]T. Sengthipphany, S. Tretriluxana, and K. Chitsakul, “Comparison of heart rate statistical parameters from Photoplethysmographic signal in resting and exercise conditions,” in Proc. of 2015 12th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2015, pp. 1-5.
[20]KingNet國家網路醫院 「交感神經」與「副交感神經」
http://hospital.kingnet.com.tw/essay/essay.html?pid=18479
[21]中華自律神經醫學會自律神經失調HRV檢測及治療衛教手冊
http://hrvtw.blogspot.tw/2010/09/hrvq.html
[22]T. Heseltine, N. Pears, and J. Austin, “Evaluation of image pre-processing techniques for eigenface based face recognition,” in Proc. of the Second International Conference on Image and Graphics, SPIE, 2002, pp. 677-685.
[23]S. K. Sivanath, S. A. Muralikrishnan, P. Thothadri, and V. Raja, “Eyeball and blink controlled firing system for military tank using LabVIEW,” in Proc. of 2012 4th International Conference on Intelligent Human Computer Interaction (IHCI), 2012, pp. 1-4.
[24]I. Park, J.-H. Ahn, and H. Byun, “Efficient measurement of eye blinking under various illumination conditions for drowsiness detection systems,” in Proc. of 2006. 18th International Conference on Pattern Recognition,2006, pp. 383-386.
[25]D. Dimage and R. Perclos, “A valid psychophysiological measure of a lertness as assessed by psychomotor vigilance,” Report No. FH-WA2MCRT2982006, Federal Highway Administration, Office of Motor Carriers1998.
[26]國際腦波學會, http://www.oset.org/Guidelines.html
[27]NeuroSky, Inc., “Brain Wave Singnal (EEG) ,” Dec 2009.
[28]H. V. Huikuri, S. M. Pikkuja, K. J. Airaksinen, M. J. Ika, A. O. Rantala, H. Kauma, et al., “Sex-related differences in autonomic modulation of heart rate in middle-aged subjects,” Circulation, vol. 94, pp. 122-125, 1996.
[29]施明和,“基於人臉特徵之駕駛人眼經偵測演算法設計與嵌入式系統實現,”國立中興大學電機工程學系碩士論文,2014
[30]M. S. Islam, “Local gradient pattern-A novel feature representation for facial expression recognition, ” Journal of AI and Data Mining, vol. 2, pp. 33-38, 2014.
[31]陳悅,“正常台灣族群心律變異性之性別與姿勢差異,”國立交通大學生物科技學系碩士論文, 2010
[32]M. Szypulska and Z. Piotrowski, “Prediction of fatigue and sleep onset using HRV analysis,” in Proc. of the 19th International Conference Mixed Design of Integrated Circuits and Systems (MIXDES), 2012, pp. 543-546.
[33]http://www.xilinx.com/products/silicon-devices/soc/zynq-7000/smarter-system.html
[34]http://www.cnblogs.com/surpassal/archive/2013/01/12/zed_webcam_lab3.html