進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-2701201315443200
論文名稱(中文) 基於灰階影像處理與PERCLOS之即時疲勞駕駛監測系統
論文名稱(英文) Real-time Driver Drowsiness Detection System Based on PERCLOS and Grayscale Image Processing
校院名稱 成功大學
系所名稱(中) 工程科學系碩博士班
系所名稱(英) Department of Engineering Science
學年度 101
學期 1
出版年 102
研究生(中文) 林映帆
研究生(英文) Ying-Fan Lin
學號 N96004060
學位類別 碩士
語文別 英文
論文頁數 54頁
口試委員 指導教授-廖德祿
口試委員-顏錦柱
口試委員-林瑞昇
中文關鍵字 人眼定位  灰階影像處理  PERCLOS 
英文關鍵字 eye-tracking  grayscale image processing  PERCLOS 
學科別分類
中文摘要 疲勞會影響汽車駕駛人之專注力,稍不注意就會造成莫大遺憾。尤其是長途開車及夜間駕駛,駕駛者的注意力及反應能力皆會持續下降,容易產生疲勞效應,甚至出現微型睡眠,即數秒鐘的淺眠。為因應此問題,目前市面上已有許多汽車廠開始試行於高階車款安裝車載電腦,並配置疲勞駕駛辨識系統;但其產品多需駕駛另外進行配戴動作,使用上較不方便,且容易被駕駛者忽略;又或者有部分產品需額外對駕駛臉部大量打光,以取得駕駛臉部表情的彩色圖像,增加駕駛眼部負擔。
因此,本論文提出一套根據灰階影像進行駕駛疲勞辨識之方法,該方法分為三大步驟:先自灰階影像中蒐集駕駛臉部資料,計算其臉部的大略位置,再針對所得資料與相對位置,配合小型模板進行臉部位置分析;藉由以上的資料,以及由美國國家公路交通安全管理局所認證,度量疲勞的標準PERCLOS,建立出駕駛者個人的疲勞模型。最後,依據駕駛個人的疲勞模型,持續偵測及判定駕駛的精神狀態。一旦駕駛的精神狀態不佳,則系統會發出警示,提醒駕駛者應停止駕駛並進行休憩。
本論文所提出之偵測方式,不會對駕駛產生負面影響,並且使用灰階影像進行判定,相較於使用彩色圖片之系統,只需三分之一的記憶體,可大幅降低系統所需的記憶體空間。
英文摘要 Fatigue reduces a driver’s attention, especially when driving long distances or at night, when reaction ability declines. The fatigue effect is a common, yet dangerous, driving experience that may even include a few seconds of shallow sleep. In response to this problem, several automobile plants have begun installing onboard computers in their cars featuring a driver drowsiness detection system. However, many of these products require physical contact, which is inconvenient for drivers and easily forgotten. Further some products currently on the market actually increase the burden on driver’s eyes since they need to project extra light on the driver’s face in order to properly obtain color images.
Therefore, this thesis develops a drowsiness detection system based on grayscale image processing to determine whether the driver is fatigued or not. The proposed system comprises three parts: first, it calculates the approximate position of the driver’s face in grayscale images, and then uses a small template to analyze the eye positions; second, it uses the data from the previous step and PERCLOS to establish a fatigue model; and finally, based on the driver’s personal fatigue model, the system continuously monitors the driver’s state. Once the driver exhibits fatigue, the system alerts the driver to stop driving and take a rest.
What differentiates the proposed detection method from others is that it has no negative impact on the driver and is contactless. Further, it uses grayscale images, which can significantly reduce the required memory space compared to a color image based system.
論文目次 摘要 I
Abstract III
誌謝 V
Contents VI
List of Tables VIII
List of Figures IX
Chapter 1 Introduction 1
1.1 Motivation 2
1.2 Objective 2
1.3 Thesis Organization 3
Chapter 2 Fundamental Knowledge 4
2.1 Driver Drowsiness Detection System 4
2.1.1 Contact Types of Driver Drowsiness Detection Systems 4
2.1.2 Contactless Type of Driver Drowsiness Detection System 5
2.2 Face Tracking Methods 6
2.2.1 Eigenfaces 8
2.2.2 Artificial Neural Network 9
2.2.3 Hidden Markov Models (HMMs) 10
2.2.4 Template-based Method 10
2.2.5 Gabor Filters and Wavelets 11
2.2.6 Scale Invariant Feature Transform (SIFT) 12
2.3 Night Vision Device 13
2.4 PERCLOS 14
Chapter 3 Architecture and Design 15
3.1 System Architecture 15
3.2 Data Collection and Eye Location 17
3.2.1 Edge Detection 18
3.2.2 Histogram 22
3.2.3 Template Matching 24
3.2.4 Quick Sort 27
3.2.5 Median Filter 29
3.2.6 Calculated Region 30
3.3 Data Collection and Fatigue Model 31
3.3.1 Binarization 32
3.3.2 Quick Sort 34
3.3.3 Threshold – PERCLOS: P80 35
3.3.4 Time Proportion 36
3.4 Drowsiness Detection 37
Chapter 4 Implementation Result 40
4.1 Introduction of Experiment Instrument 40
4.2 Introduction of Graphic User Interface 41
4.3 Applied Result 42
4.4 Analysis of Performance 48
Chapter 5 Conclusions 49
References 51
參考文獻 [1] R. Knipling, and P. Rau (1998), “PERCLOS: A Valid Psychophysiological Measure of Alertness as Assessed by Psychomotor Vigilance,” U.S. Department of Transportation, Federal Highway Administration.
[2] M. S. Devi, and B. R. Bajaj (2008), “Driver Fatigue Detection Based on Eye Tracking,” Proceedings of the Emerging Trends in Engineering and Technology Conference, pp. 649~ 652.
[3] S. K. L. La, and A. Craig (2001), “A Critical Review of the Psychophysiology of Driver Fatigue,” Biological Psychology, 55(3), pp.173~194.
[4] A. K. Jain, and B. Klare (2011), “Matching Forensic Sketches and Mug Shots to Apprehend Criminals,” IEEE Computer Society, 11, pp.84~86.
[5] A. F. Abate, M. Nappi, D. Riccio, and G. Sabatino (2007), “2D and 3D Face Recognition: A Survey,” Pattern Recognition Letters, 28, pp.1885~1906.
[6] M. Agarwal, H. Agrawal, N. Jain, and M. Kumat (2010), “Face Recognition Using Principle Component Analysis Eigenface and Neural Network,” International Conference on Signal Acquisition and Processing, pp. 310~314.
[7] J. Yang, D. Zhang, Y. Xu, and J. Yang (2005), “Recognize Color Face Images Using Complex Eigenfaces,” Lecture Notes in Computer Science, 3832, pp. 64~68.
[8] R. Gottumukkal, and V. K. Asari (2004), “An Improved Face Recognition Technique Based on Modular PCA Approach,” Pattern Recognition Letters, 25(4), pp.429~436.
[9] A. S. Tolba, A. H. El-Baz, and A. A. El-Harby (2006), “Face Recognition: A Literature Review,” International Journal of Signal Processing, 2(2), pp.88~103.
[10] M. J. Er, S. Wu, J. Lu, and H. L. Toh (2002), “Face Recognition With Radial Basis Function (RBF) Neural Networks,” IEEE Transactions on Neural Networks, 13(3), pp.697~710.
[11] P. Nicholl, A. Amira, D. Bouchaffra, and R. H. Perrott (2008), “A Statistical Multiresolution Approach for Face Recognition Using Structural Hidden Markov Models,” EURASIP Journal on Advances in Signal Processing, 22, pp.1~13.
[12] F. Cardinaux, C. Sanderson, and S. Bengio (2004), “Face Verification Using Adapted Generative Models,” Proceedings of the Automatic Face and Gesture Recognition, IEEE International Conference, pp.825~830.
[13] Z. Jin, Z. Lou, J. Yang, and Q. Sun (2007), “Face Detection Using Template Matching and Skin-color Information,” Neurocomputing, 70(4-6), pp.794~800.
[14] S. Parua, A. Das, D. Mazumdar, and S. Mitra (2011), “Determination of Feature Hierarchy from Gabor and SIFT Features for Face Recognition,” Proceedings of the second International Conference on Emerging Applications of Information Technology, 19-20, pp. 257~260.
[15] L. Shen, and L. Bai (2006), “Information Theory for Gabor Feature Selection for Face Recognition,” EURASIP Journal on Applied Signal Processing, 2006, pp.1~11.
[16] C. Liu, and H. Wechsler (2001), “A Gabor Feature Classifier for Face Recognition,” Proceedings of the eighth IEEE Computer Vision International Conference, 2, pp.270~275.
[17] J. Luo, Y. Ma, E. Takikawa, S. Lao, M. Kawade, and B. Lu (2007), “Person-Specific SIFT Features for Face Recognition,” Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing, 2, pp.593~596.
[18] M. Bicego, A. Lagorio, E. Grosso, and M. Tistarelli (2006), “On the Use of SIFT Features for Face Authentication,” Proceedings of the Computer Vision and Pattern Recognition Workshop Conference.
[19] S. G. Kong, J. Heo, B. R. Abidi, J. Paik, and M. A. Abidi (2005), “Recent Advances in Visual and Infrared Face Recognition—A Review,” Computer Vision and Image Understanding, 97(1), pp.103-135.
[20] B. Zhang, L. Zhang, D. Zhang, and L. Shen (2010), “Directional Binary Code with Application to PolyU Near-Infrared Face Database,” Pattern Recognition Letters, 31(14), pp.2337~2344.
[21] W. Wierwille, L. Ellsworth, S. Wreggit, R. Fairbanks, and C. Kirn (1995), “Research on Vehicle-Based Driver Status/Performance Monitoring: Development, Validation, and Refinement of Algorithms for Detection of Driver Drowsiness,” National Highway Traffic Safety Administration Final Report.
[22] U. Trutschel, B. Sirois, D. Sommer, M. Golz, and D. Edwards (2011), “PERCLOS: An Alertness Measure of the Past,” Proceedings of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design, pp.172~179.
[23] J. Canny (1986), “A Computational Approach to Edge Detection”, Pattern Analysis and Machine Intelligence, PAMI-8(6), pp.679~698.
[24] R. Maini, and J. S. Sohal (2006), “Performance Evaluation of Prewitt Edge Detector for Noisy Images,” Vision and Image Processing, 6(3), pp.39~46.
[25] O. R. Vincent, and O. Folorunso (2009), “A Descriptive Algorithm for Sobel Image Edge Detection,” Proceedings of Informing Science and IT Education Conference, pp.97~107.
[26] C. A. R. Hoare (1962), “Quicksort,” The Computer Journal, 5(1), pp.10~16.
[27] D. R. K. Brownrigg (1984), “The Weighted Median Filter,” Communications of the ACM, 27(8), pp.807~818.
[28] W. Chen, T. Sun, X. Yang, and L. Wang (2009), “Face Detection Based on Half Face-Template,” Proceedings of Electronic Measurement and Instruments Conference, pp.4-54~4-58.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-01-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw