透過智慧型手機影像之基於眼睛狀態的駕駛疲勞監測

簡易檢索 / 詳目顯示

回結果列表

研究生：	彭長生 Chang-Sheng Peng
論文名稱：	透過智慧型手機影像之基於眼睛狀態的駕駛疲勞監測 Eyes Status Based Driving Fatigue Supervision through Smartphone Camera Monitoring
指導教授：	潘敏俊 Min-Chun Pan
口試委員:
學位類別：	碩士 Master
系所名稱：	工學院 - 機械工程學系在職專班 Executive Master of Mechanical Engineering
論文出版年：	2016
畢業學年度：	104
語文別：	英文
論文頁數：	75
中文關鍵詞：	疲勞駕駛、尼布雷克法、凸包法、海伍德圓度法、眼睛粒子數量、布林累積器
外文關鍵詞：	Driving fatigue, NiBlack threshold, Convex Hull, Heywood Circularity, Number of particles, Boolean Accumulator
相關次數：	點閱：19 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本研究以手機鏡頭取代額外的攝影機，在擷取影像後以美國國家儀器公司LabVIEW®之開發環境下實現以眼睛閉合時間為理論基礎之疲勞駕駛辨識系統。此系統在獲得影像後從三原色(RGB)影像中萃取飽和度(Saturation)與色調(Hue)影像，以可降低光線影響之自動二值化之尼布雷克法(NiBlack Threshold)做為基礎，將影像經過多重演算法並堆疊，最後再以凸包法(Convex Hull)萃取完整臉部面積，此時系統亦從RGB影像中萃取亮度(Luminance)影像，以相同二值化方法，將影像經過多重演算，最後再以海伍德圓度法(Heywood Circularity)過濾出眼睛部分並判別眼睛粒子數量(NoP)。隨後將萃取後的完整人臉的上半部面積做為眼睛萃取的區域，進一步降低雜訊的出現。最後以ㄧ組布林累積器(Boolean Accumulator)做為疲勞駕駛判斷的依據，並降低系統因高速擷取布林訊號而導致誤判的機率。系統在NoP小於2時，以電腦同時釋放視覺與聽覺的警告訊息，提醒駕駛人避免疲勞駕駛事件的發生。

In this study, a smartphone lens substituted additional camera in capturing images under National Instrument LabVIEW® development environment to achieve a driving fatigue supervision system based on eye blink analysis. First, the system extracts Saturation and Hue plane from RGB image. In order to reduce the light impact, an automatic binarization with NiBlack threshold was introduced to stack images through multiple algorithms before extract complete face area with Convex Hull. The system also extracted Luminance plane afterward from RGB image with the same binarization through multiple algorithms to filter eye part out and discriminate number of particles (NoP) with Heywood Circularity. Then the system extracted eyes region further on upper half of face for reducing possible noises after a complete face extraction. Subsequently, a set of Boolean Accumulator was developed for judging fatigue driving, and reduce possible failures due to high-speed Boolean signal capturing. At last, the system released both visual and auditory warnings simultaneously by a computer to alert drivers of avoiding fatigue driving when NoP is less than 2.

摘要………………………………………………………………………………….…………I
Abstract……………………………………………………………………………………… II
Acknowledgement…………………………………………………………………………...III
Contents…………………………………………………………………………...................IV
Figures Index…………………………………………………………………………..........VII
Tables Index…………………………………………………………………………..............X
Chapter 1 Introduction…………………………………………………………………...1
1-1 background……………………………………………………………………..1
1-2 Literature Review………………………………………………………………3
1-3 Research Scope………………………………………………………………...7
1-4 System Structure……………………………………………………………….7
Chapter 2 Fundamental Basis…………………………………………………………..10
2-1 Color Spaces………………………………………………...………………..10
2-1-1 The RGB Color Space………………………………………………...……....11
2-1-2 The HSL Color Space………………………………………………………...13
2-2 Binary Image………………………………………………………………….14
2-2-1 Structuring Elements………………………………………………………….15
2-2-2 Connectivity…………………………………………………………………..17
Chapter 3 Closed Eyes in Fatigue Detection System………………………………….19
3-1 Image Acquisition with Smartphone Camera………………………………...19
3-1-1 Android Debug Bridge (ADB)……………………………………………….20
3-1-2 USB Connection……………………………………………………………...21
3-2 Face Extraction…………………………………………………………….....23
IV
3-2-1 Automatic Threshold with Niblack…………………………….….………….24
3-2-2 AND Operator………………………………………………….……………..25
3-2-3 Convex Hull Morphology……………………………….……………………27
3-2-4 Particle Filters on Max Area………………………………….………………30
3-3 Eyes Status Algorithm………………………………………..……….………30
3-3-1 Automatic Threshold with Niblack…………………………….….………….31
3-3-2 Borders Removal…………………………….….…………………………….32
3-3-3 Erosion………………………………………………………………………..32
3-3-4 Holes Filling…………………………………………………………………..34
3-3-5 Heywood Circularity………………………………………………………….36
3-3-6 Dilation………………………………………………………………………..37
3-4 Eyes Extraction……………………………………………………………….39
3-4-1 ROI Selection…………………………………………………………...…….39
3-4-2 Rectangle to ROI Conversion…………………………………………...……40
3-4-3 ROI to Mask…………………………………………………………………..43
3-4-4 Morphology Reconstruction………………………………………………….44
3-4-5 Subtract Operator……………………………………………………………..45
3-5 Fatigue Definition…………………………………………………………….46
3-5-1 Boolean Accumulator…………………………………………………………47
3-5-2 Show Warnings……………………………………………………………….49
Chapter 4 Results and discussions………………………………………………….…..50
4-1 Effects of Brightness…………………………...……………………………..51
4-2 Effects of Eye Sizes…………………………………………………………..54
4-3 Effects of Glasses Wearing…………………………………………………...55
4-4 Comparison of Experiment Devices………………………………………….56
V
Chapter 5 Conclusions and Future Work……………………………………………...59
5-1 Conclusions……………………………………………...................................59
5-2 Future Work……………………………………………...................................60
                                

[1] NHTSA Drowsy Driving Research and Program Plan, National Highway Traffic Safety Administration (NHTSA), 2016.
[2] Causes of Traffic Accidents1975-2013, Taiwan Area National Freeway Bureau, MOTC R.O.C., 2014.
[3] C. L. Wu, R. X. Liu, Z.Y. You, D.Y. Xu, “Real Evidence Characters of Drowsy Driving for Freeway Traffic Crashes,” Ministry of The Interior Research Project Report, 10-13(2012)
[4] G. Y. Zhang, “Hours of Serves Rules for The Long-Distance Bus Drivers in The Other Countries,” Institute of Labor, Occupational Safety and Health, Ministry of Labor, 1-2(2005)
[5] Road Traffic Management and Penalty Act, Laws and Regulations Database of the Republic of China.
[6] C. R. Weng, “A Fast Algorithm of Eye Blink Detection,” Master Thesis, National Chiao Tung University (2005).
[7] C. C. Chang, “A Driver Fatigue Detection System Based on Eye States Tracking,” Master Thesis, National Cheng Kung University (2009).
[8] Z. H. Zhou, X. Geng, “Projection Functions for Eye Detection,” Pattern Recognition, 37(5), 1049-1056 (2004).
[9] S. Kawato, N. Tetsutani, “Detection and Tracking of Eyes for Gaze-camera Control,” Image and Vision Computing. 22(12), 1031–1038 (2004).
[10] T. Ahonen, M. Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12), 2037-2039 (2006).
[11] P. Viola, M. J. Jones,” Robust Real-Time Face Detection,” International Journal of Computer Vision, 57(2), 137–154 (2004).
[12] Z. Zhu, Q. Ji, “Robust real-time eye detection and tracking under variable lighting conditions,” Computer Vision and Image Understanding, 98(1), 124–154 (2005).
[13] C. Garcia, G. Tziritas, “Face detection using quantized skin color regions merging and wavelet packet analysis,” IEEE Transactions on Multimedia, 1(3), 264 – 277 (1999).
[14] J. Xiong, W. Xu, W. Liao, Q. Wang, “Eye Control System Base on Ameliorated Hough Transform Algorithm,” IEEE Sensors Journal, (13)9, 3423-3427 (2013).
[15] Q. Ji, Z. Zhu, “Real-time Nonintrusive Monitoring and Prediction of Driver Fatigue,” IEEE Transactions on Vehicular Technology, (53)4, 1054-1056 (2004).
[16] J. J. Mazzilli, “360.degree automobile video camera system,” United States Patterns, US006795111 (2002).
[17] L. Ariold, Z. Arie, “Method and apparatus for fatigue detection,” United States Patterns, 49867186 (1989).
[18] K. I. Yuan, “Safety apparatus for vehicle,” R.O.C Patterns, I379785 (2012).
[19] K. H. Zheng, “Application of Driving Simulator to the Analysis of Fatigue Characteristic in Drunk
Driving,” Master Thesis, Chung Hua University (2006).
61
[20] Individual Digital Opportunity Survey in Taiwan, National Communications Commission (NCC), 2015.
[21] Y. L. Jian, “Eye Open Detection with Application for In-Class Monitoring,” Master Thesis, National Taiwan Normal University (2012).
[22] H. T. Cheng, “Design of Drowsiness Detection System Base on Image Recognition Method,” Master Thesis, National Taiwan University of Education, (2008).
[23] IMAQ Vision Concepts Manual, National Instruments, 2003.
[24] R. Gonzalez, R.Woods, Digital Image Processing, Prentice Hall (2008).
[25] W. Jackson, Pro Android Wearables: Building Apps for Smartwatches, Apress, 461-463 (2015).
[26] DroidCam User Manual, DEV47APPS, 2010.
[27] F. Shao, W. Shu, T. Tian, Information Technology and Career Education: Proceedings of the 2014 International Conference on Information, CRC Press, 163-165 (2015).
[28] K. S. Kwon, S. Ready, Practical Guide to Machine Vision Software: An Introduction with LabVIEW,
John Wiley & Sons, 43-45, 2014.
[29] D. Agushinta, I. Septadepi, “Face Recognition System Using Eigenface Method based on Facial Component Region,” Gunadarma University, 3-4 (2004)
[30] J. S. Durmer, D. F. Dinges, “Neurocognitive Consequences of Sleep Deprivation,” Seminars in Neurology, 25(1), 7-8 (2005).
[31] S. Chandra, S. Atapathy, P. S. Avadhani, S. K. Udgata, S. Lakshminarayana, ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India, Springer Science & Business Media, 383-384 (2013).
[32] P. Read, M. P. Meyer, Restoration of Motion Picture Film, Butterworth-Heinemann, 23-24 (2000).
[33] Optics and Optical Instruments Master Source Book, Edmund Optics, 2015.
[34] Anatomy of a Video Signal, National Instruments, 2006.
[35] R. Bitter, T. Mohiuddin, M. Nawrocki, LabVIEW: Advanced Programming Techniques, Second Edition, CRC Press, 136-141, 2006.
[36] NI Vision for LabVIEW User Manual, National Instruments, 2005.
[37] J. Webber, “Driver vision field extender,” United States Patterns, US8687288B2 (2004).

簡易檢索 / 詳目顯示

相關論文