Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/9324
標題: 應用於駕駛疲勞警示系統之臉部與頭部狀態偵測技術
Facial and Head Status Detection for Driver Fatigue Alert Systems
作者: 余學翰
Yu, Xue Han
關鍵字: 疲勞警示系統
Driver Fatigue Alert Systems
臉部偵測
頭部偵測
Facial Detection
Head Detection
出版社: 電機工程學系所
引用: 參考文獻 [1] 1994年Nissan 車輛研究實驗室. [2] 尚立股份有限公司,監視攝影機之紅外線照明. [3] 曾定章,曹力仁,”不同照度環境的駕駛昏睡偵測與警示”, 國立中央大學資訊工程學系碩士論文, 2009年. [4] 范志鵬,呂冠賢,” 應用於嬰幼兒監護系統之臉部追蹤與異物偵測演算法設計與實作”, 國立中興大學電機工程學系碩士論文, 2009年 [5] 范志鵬,胡正宏,”應用於嬰幼兒監護系統之臉部特徵點偵測與臉部表情識別演算法設計與實作”, 國立中興大學電機工程學系碩士論文, 2009年 [6] 范志鵬,游聖民,”應用於嬰幼兒監護系統之臉部表情辨識與異物偵測演算法設計與實作”, 國立中興大學電機工程學系碩士論文, 2010年. Reference [7] Soriano, M. Martinkauppi, B. Huovinen, and S. Laaksonen, ”Skin detection in video under changing illumination conditions”, 15th International Conference on Pattern Recognition, vol. 1, pp. 839 – 842 ,2000. [8] P. Viola and M. J. Jones, ”Robust Real-Time Face Detection”, International Journal of Computer Vision, vol. 57(2), pp.137–154, 2004. [9] J. Zhong, S. Yao, and J. Xu, ” Development and Implementation of Automatic White Balance Based on Luminance Compensation”, Second International Symposium on Intelligent Information Technology Application, pp.206-210, 20-22 Dec., 2008. [10] Funt B, F. Ciurea, and J. McCann, “Retinex in Matlab ”, Proceedings of IS&T/SID Eighth Color Imaging Conference Scottsdale, Arizona (USA), pp.112 - 121, November 7-10, 2000. [11] R. C. Gonzalez and R. Ewoods, Digital Image Processing, 3nd Edition, Prentice hall, 2008. [12] Y. Guan, “Robust Eye Detection from Facial Image based on Multi-cue Facial Information”, IEEE International Conference on Control and Automation, pp. 1775 – 1778, 2007. [13] S. Birchfield, "Elliptical Head Tracking Using Intensity Gradients and Color Histograms", IEEE Conf. on computer Vision and Pattern Recognitions, June pp.232 - 237,1998. [14] S. Birchfield, "An elliptical head tracker", 31st Asilomar Conf. On Signal, Systems and Computers, pp. 1710 - 1714,1997 [15] X. He, Z-M. Lin and J-L. Zhou, “Real-time Human Face Detection in Color Image”, Int. Conf. Machine Learning and Cybernetics, vol. 5, pp.2915 - 2920, 2003 [16] D.Huang, Y. H. Wang,Y. D. Wanga, ”Robust Infraed Face Recognition Method Based on Adaboost Gabor Features,” International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China,pp 2 - 4 Nov, 2007. [17] I. Park, J. Ho. Ahn, and H. Byun, “Efficient Measurement of Eye Blinking under Various Illumination Conditions for Drowsiness Detection Systems”, 18th International Conference on Pattern Recognition, pp383 - 386,2006 [18] H. Wang, Li, S.Z., Y Wang , "Face recognition under varying lighting conditions using self quotient image," Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 819 - 824, May 2004 [19] T F. Chan, and L.A. Vese ,“Active Contours Without Edges” IEEE Transactions on Image Processing, vol. 10, no. 2, pp. 266 - 277,February 2001. [20] R. Khudeev, ”A New Flood-Fill Algorithm for Closed Contour” IEEE Conference on Control and Communications pp. 172 - 176,2005. [21] S. Lankton and A. Tannenbaum,” Localizing Region-Based Active Contours” IEEE Transactions on Image Processing, vol. 17, no. 11, pp. 2029 - 2039, November 2008 [22] T. S. Chiou,”Automatic White Balance for Digital Still Camera”, MS thesis, National Taiwan University, Department of Computer Science and Information Engineering, 2006. [23] Dinges, D. and R. Grace,” PERCLOS: A Valid Psychophysiological Measure of Alertness As Assessed by Psychomotor Vigilance”, US Department of Transportation,Federal Highway Administration, TechBrief, FHWA-MCRT-98-006, 1998. [24] ADVANTECH “DVP-7010BE_Manual”,DVP-7010BE SDK Suit [25] Socle Technology Corporation"MDK-3D Hardware Introduction"
摘要: 本論文主要是要提出一個「不受光影」所影響,且可在「夜間使用」的「全天候駕駛人疲勞昏睡偵測」系統技術。當駕駛人因長期駕駛導致疲勞時,會出現眨眼頻率提高或瞌睡點頭等行為,系統便透過攝影機擷取駕駛人影像進行判斷,並發出警告提醒駕駛人做適度的休息,以避免駕駛人因疲勞而導致注意力不集中,無法處理緊急狀況,進而發生事故。為完成全天候與夜間使用,本系統在夜間使用近紅外線(NIR)作為主動式光源。為降低色彩受光線的影響,及配合近紅外線影像類灰階之特性,演算法則以灰階影像為基礎,無需使用色彩資訊。 本系統可分成兩個子系統,頭部動態偵測與臉、眼部偵測。此兩個子系統,可分別獨立運作,不受對方影響。但為了將兩個子系統做結合,本文提出一瞌睡計量方法,將兩者之結果量化,且可將兩者結合,進行綜合計量。不同於一般臉部偵測系統,車用系統沒有人臉存在與否之問題,故本系統先依據臉部特徵,將臉部之大範圍找出,再將範圍限縮以降低運算量,並偵測出眼部位置。頭部動態偵測則是利用前後畫面間的差值與我們提出的行列差值法,同時進行適度運算,並綜合判斷,可以達到識別駕駛人點頭動作之功能。 為將演算法是執行速度提升,我們採用積分影像之技巧,可使相同之單張影像臉部擷取之運算,從3~4秒一張,提升到0.001~0.007秒1張,以階段性系統驗證時,可提高每秒畫格數2倍,約每秒2.8張。為再提升執行速度,將除光影像之程式碼最佳化,提高每秒畫格數約2~3倍。最後執行降取樣,與未程式碼最佳化之除光影像相比,提高每秒畫格數約9~11倍。 實驗結果顯示,使用4核心的個人電腦(3.4GHz,4GB記憶體容量)進行專案運算,處理速度可達每秒22張畫面以上。由於視訊擷取卡驅動程式之限制,即時模擬系統之速度將降低至每秒18張畫面以上。以8部模擬影片,內含4部配戴眼鏡與4部未配戴眼鏡之影片進行模擬測試,計算臉、眼部偵測率,而臉部擷取偵測率最高可達95%,但是由於模擬影像之動作比例偏高,與單調行車動作較少之情形不同,所以眼部擷取偵測率最高約為 65%。頭部動態偵測率以即時模擬系統進行實測,結果最高可達94%。
URI: http://hdl.handle.net/11455/9324
其他識別: U0005-1508201312105400
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1508201312105400
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.