臺灣博碩士論文加值系統

本研究提出一套『行車安全監控系統』，此系統包含『駕駛頭部偏移偵測子系統』與『車道偏移偵測子系統』兩大部分，分別監控駕駛頭部與車道線是否處於正常位置，當駕駛頭部或是車道線發生偏移時，則對駕駛發出警告訊號，提醒駕駛注意以達到行車安全的目的。
在駕駛頭部偏移偵測子系統中，我們設計一個LED輔助裝置嵌鑲於駕駛頭枕上，並由駕駛前上方攝影機擷取駕駛頭部周圍區域畫面，透過『駕駛頭部偏移偵測演算法』分析擷取畫面中輔助裝置的變化，來達到監控駕駛頭部偏移的目的。為了展示此子系統的效能，針對所錄製的測試視訊進行軟體模擬，結果顯示此子系統皆能正確監控駕駛者頭部的偏移；此外，硬體驗證結果顯示: 在每秒處理15張以上540960畫面之速度下，硬體成本為569個邏輯單元 (LEs)。此結果顯示此子系統之硬體實現可滿足即時性的需求。
在車道偏移偵測子系統中，由位於擋風玻璃中間上方攝影機擷取車行方向道路畫面，透過『車道偏移偵測演算法』分析兩邊車道線角度的變化，以達到監控車道偏移的目的。為了展示此子系統的效能，針對六段在不同環境下所錄製之測試視訊進行軟體模擬，結果顯示此子系統皆能正確監控車道偏移；此外，硬體驗證結果顯示: 在每秒處理15張170570畫面之速度下，硬體成本為43856個邏輯單元 (LEs)及842496個記憶單元。

The study proposes a new safe driving monitoring system. The system consists of the monitoring subsystem for movement of driver’s head and the monitoring subsystem for lane departure. It monitors whether the driver’s head and traffic lanes are in normal position. If either abnormal movement of driver’s head or departure of traffic lanes are detected, the system issues a warning signal to the driver immedeiately.
In the monitoring subsystem for movement of driver’s head, the LED auxiliary device is adhered to the back cushion behind the driver’s head. The CMOS sensor is used to acquire frames including the region around the driver’s head. The acquired frame is analyzed by the proposed head movement monitoring algorithm. By monitoring the change of the LED region, the algorithm can detect the condition of abnormal head movement. The demonstration of software simulation on the test video indicates the subsystem can detect the abnormal movement of the driver’s head successfully. For hardware verification of the subsystem, the simulation result shows that the throughput can be higher than 15 fps with the hardware cost of 569 logic elements. It reveals that the proposed design achieves the requirement of real time processing.
In the monitoring subsystem for lane departure, the CMOS sensor placed at the middle of upper side of windscreen acquires the frames including the road surface in front of the car. The acquired frames are analysed by the proposed lane departure monitoring algorithm. By monitoring the angles variation of marking lane, the algorithm can detect the condition of lane departure. The demonstrations of software simulation on six test videos from different environments indicate the subsystem can detect lane departure successfully. For hardware verification of the subsystem, the simulation results show that the throughput reaches 15 fps with the hardware cost of 43856 logic elements and memory cost of 842496 bit. It reveals that the proposed design fulfils the requirement of real applications.

致謝........................................... Ⅰ
摘要........................................... Ⅱ
Abstract...................................... Ⅲ
目錄........................................... Ⅳ
圖目錄.......................................... Ⅵ
表目錄.......................................... XIII

第一章　緒論 1
1.1　研究動機....................................1
1.2　文獻回顧....................................2
1.3　研究方法....................................6
1.4　論文架構....................................6

第二章　新的視訊滑鼠系統............................7
2.1　 背景介紹..................................7
2.1.1　色彩空間..................................7
2.1.2　影像分割..................................10
2.1.3　最大熵度準則(MEC)與最大關聯度準則(MCC) ........11
2.1.4　動態臨界值.................................14
2.1.5　霍夫轉換(Hough)............................15
2.2　行車安全監控系統...............................17
2.2.1　系統架構....................................17
2.2.2　駕駛頭部偏移偵測子系統.........................18
2.2.3　車道偏移偵測子系統............................23

第三章　軟體模擬結果................................35
3.1　軟體模擬環境..................................35
3.2　軟體模擬結果..................................35
3.2.1　駕駛頭部偏移偵測子系統結果.....................35
3.2.2　車道偏移偵測子系統模擬結果.....................41

第四章　硬體架構設計與實現............................63
4.1　硬體驗證環境...................................63
4.2　行車安全監控系統之硬體架構設計....................63
4.2.1　駕駛頭部偏移偵測子系統硬體架構設計...............65
4.2.2　車道偏移偵測子系統硬體架構設計...................68
4.3　硬體實現結果....................................83
4.3.1　駕駛頭部偏移偵測子系統硬體實現結果................83
4.3.2　車道偏移偵測子系統硬體實現結果....................91
第五章　結論與未來展望.................................103

5.1　結論...........................................103
5.2　未來展望........................................103

參考文獻.............................................105

[1]Y. Dong, Z. Hu, K. Uchimura, and N. Murayama, “Driver inattention monitoring system for intelligent vehicles: A Review,” IEEE Trans. on Intelligent Transportation Systems, vol. 12, Iss. 2, pp. 596 – 614, June 2011.
[2]J. F. Coughlin, B. Reimer,B. Mehler, “Monitoring, managing, and motivating driver safety and well-being,” IEEE Pervasive Computing, vol. 10, Iss. 3, pp. 14-21, 2011.
[3]R. N. Khushaba, S. Kodagoda, S. Lal, and G. Dissanayake, “Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm,” IEEE Trans. on Biomedical Eng., vol. 58, Iss. 1, pp. 121-131, Jan. 2011.
[4]M. V. Ramesh, A. K. Nair, A. T. Kunnath, “Real-time automated multiplexed sensor system for driver drowsiness detection,” 2011 7th Int. Conf. on Wireless Communi., Networking and Mobile Computing, pp. 1-4, 2011.
[5]A. Kircher, M. Uddman, and J. Sandin, “Vehicle control and drowsiness,” Swedish National Road and Transport Research Institute, 2002.
[6]R. C. Coetzer, and G. P. Hancke, “Eye detection for a real-time vehicle driver fatigue monitoring system,” 2011 IEEE Intelligent Vehicles Symp. (IV), pp. 66 – 71, 5-9 June 2011.
[7]L. Li, Y. Chen and L. Xin, “Driver fatigue detection based on mouth information,” 2010 8th World Congress on Intelligent Control and Auto. (WCICA), pp. 6058– 6062, 7-9 July 2010.
[8]L. M. Bergasa, J. Nuevo, M. A. Sotelo, R. Barea, and M. E. Lopez, “Real-time system for monitoring driver vigilance," IEEE Trans. on Intelligent Transportation Systems, vol. 7, no. 1, March 2006.
[9]D. F. Dinges, and R. Grace, “PERCLOS: A valid psychophysiological measure of alertness as assessed by psychomotor vigilance,” US Department of Transportation, Federal highway Administration. Publication Number FHWA-MCRT-98-006.
[10]H. Singh, J. S. Bhatia, and J. Kaur, “Eye tracking based driver fatigue monitoring and warning system,” 2010 India International Conference on Power Electronics (IICPE), pp. 1-6, 28-30 Jan. 2011.
[11]T. H. Chang, C. S. Hsu, C. Wang, L. K. Yang, “Onboard measurement and warning module for irregular vehicle behavior,” IEEE Trans. on Intelligent Transportation Systems, vol. 9, Iss. 3, pp. 501-513, 2008.
[12]C. F. Wu; C. J. Lin; C. Y. Lee, “Applying a functional neurofuzzy network to real-time lane detection and front-vehicle distance measurement,” IEEE Trans. on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 42, Iss. 4, pp. 577-589, 2012.
[13]W. S. Wijesoma, K. R. S. Kodagoda, and A. P. Balasuriya, “Road boundary detection and tracking using ladar sensing,” IEEE Trans. Robotics and Automation, vol. 20, pp. 456-464, 2004.
[14]T. Wakita, K. Ozawa, C. Miyajima, K. Igarashi, K. Itou, K. Takeda, and F. Itakura, “Driver identification using driving behavior signals,” IEICE Trans. Information System, vol. E89-D, no. 3, pp. 1188–1194, Mar. 2006.
[15]T. Ersal, H. J. A. Fuller, O. Tsimhoni, J. L. Stein, and H. K. Fathy, “Model-based analysis and classification of driver distraction under secondary tasks,” IEEE Trans. Intell. Transp. Syst., vol. 11, no. 3, pp. 692–701, Sep. 2010.
[16]B. G. Lee and W. Y. Chung, “Driver alertness monitoring using fusion of facial features and bio-signals,” IEEE Sensors Journal, vol. 12 , pp. 2416-2422, 2012.
[17]B. G. Lee, S. J. Jung, and W. Y. Chung, “Real-time physiological and vision monitoring of vehicle driver for non-intrusive drowsiness detection,” IET Communications, vol. 5, Iss. 17, pp. 2461-2469, 2011.
[18]Y. Guo, X. Xiao, B. Jian, “Analysis of vehicle surroundings and driver status from video stream based on a single PAL camera,” 2009 9th Int. Conf. on Electronic Measurement & Instruments, pp. 4-363-4-367, 2009.
[19]H. D. Rosario, J. S. Solaz, N. Rodriguez, and L.M. Bergasa, “Controlled inducement and measurement of drowsiness in a driving simulator,” IET Intelligent Transport Systems, vol. 4, pp. 280-288, 2010.
[20]徐祥銘、江政祐、劉寧漢， ”多模式之駕駛瞌睡腦波偵測研究，” 國立屏東科技大學，研討會期刊，民國95年。
[21]曾定章、張光雄， ”主動式紅外線影像的疲勞駕駛偵測系統，” 國立中央大學，碩士論文，民國94年。
[22]曾建誠、吳文揚， ”使用梯度向量流蛇行法偵測車道，” 國立高雄第一科技大學，碩士論文，民國96年。
[23]J. L. Prince and Chenyang. Xu, “Gradient vector flow: a new external force for snakes,” IEEE Computer Society Conf.,” Computer Vision and Pattern Recognition, vol. 17, No.19, pp.66 – 71, June 1997.
[24]J.L Prince and Chenyang Xu, “Snakes, shapes, and gradient vector flow,” IEEE Trans., Image Processing, vol. 7, No.3, pp. 359 – 369, Mar. 1998.
[25]鄭志宏、林義隆、陳韋任， ”使用霍夫神經網路於車道線偵測之研究，”義守大學，民國100年。
[26]D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation,” Parallel Distributed Processing, pp. 318-362, 1986.
[27]O. Richard, E. Duda, and E Peter, “ Use of the Hough Transform to detect lines and curves in pictures,” Grapghucs and Image Processing, vol. 15, No.1, pp. 11 – 15, Mar. 1972.
[28]維基百科(民國103年3月5日)。維基媒體基金會 色彩空間。民國103年6月9日，取自http://en.wikipedia.org/wiki/Color_space
[29]維基百科(民國102年11月23日)。維基媒體基金會 HSL和HSV色彩空間。民國103年6月9日，取自
https://zh.wikipedia.org/wiki/HSV%E8%89%B2%E5%BD%A9%E5%B1%9E%E6%80%A7%E6%A8%A1%E5%BC%8F
[30]B. Bhanu, “Aytomatic target recongnition:State of the art survey,” IEEE Trans.Aerosp.Electron. Syst.,vol. AES-22, no. 4, pp. 364-379, July 1986.
[31]T. W. Ridler and S. Calvard, ”Picture thresholding using an interative selection method,” IEEE Trans. Syst.Man Cyber.,vol. SMC-8, no. 8, pp. 630-632, Aug. 1978.
[32]J. R.Paker,”Gray-level thresholding in badly illuminated images, ” IEEE Trans. Pattern Anal. Nachine Interll.,vol. 13, no. 8, pp. 813-819, Aug. 1991.
[33]R. C. Gonzalez and R. Safabakhsh, “Computer vision techniques for industrial applications and robot control,” Comput.,vol. 15, pp. 17-32, Aug. 1982.
[34]C. K. Chow and T.Kaneko, “Automatic boundary detection of left ventricle from cineangiograms,” Comput. Biomed. Res., vol. 5, pp. 338-410, 1972.
[35]E. S. Gelsema, H. F. Bao, A. W. M. Smeulders, and H. C. D. Harink, ”Application of the method of multiple thresholding to while blood cell classification,” Comput. Biol. Med., vol. 18, no.2, pp. 65-74, 1988.
[36]J. S. Weszka and A.Rosenfeld, ”Histogram modification for threshold selection,” IEEE Trans.Syst.Man Cyber., vol. SMC-9, no.1, pp. 38-52, Jan. 1979.
[37]A. Rosenfeld and A. C. Kak, ”Digital Picture Processing,” New York Academic., vol. 2, 1982.
[38]J. N. Kapur , P. K.Sahoo, and A. K. C. Wong, “A new method for gray-level picture thresholding using the entropy of the histogram,” Comput.Vision, Graph., Image Processing, vol. 29, no. 3, pp. 273-285, Mar. 1985.
[39]A. S. Abutaleb ,”Automatic thresholding of gray-level picture using two-demensional entropy,” Comput.Vision, Graph., Processing, vol. 47, no. 1, pp. 22-32, July. 1989.
[40]S. S. Reddi, S. F. Rudin and H. R. Keshavan, “An optimal multiple threshold scheme for image segmentation,” IEEE Trans.Syst.Man Cyber., vol. SMC-14, no. 4, pp. 661-665, July. 1984.
[41]N. Otsu, “A threshold selection method from gray-level pictures histograms,” IEEE Trans.Syst.Man Cyber., vol. SMC-9, no. 1, pp. 62-66, July. 1979.
[42]J. C. Yen, F. J. Chang and S. Chang, “A New Criterion for Automatic Multilevel Thresholding,” IEEE Trans. On Image Peocessing., vol. 4, no. 3, pp. 370-378, March. 1995.
[43]井上誠喜，八木伸行，林正樹、中須英輔、三谷公二、奧井誠人，<動態臨界值法>，《C語言數位影像處理》；32-34。
[44]李崇瑋，“行車安全監控系統-駕駛頭部偏移偵測,” GOOGLE YOUTUBE，103年6月，取自https://www.youtube.com/watch?v=imW8DTs_23s
[45]李崇瑋，“行車安全監控系統-車道偏移偵測(早晨時段測試結果),” GOOGLE YOUTUBE，103年6月，取自https://www.youtube.com/watch?v=UTux5uxHSOk
[46]YOUTUBE(民國103年6月9日)。GOOGLE公司 行車安全監控系統-車道偏移偵測(下午時段測試結果)。民國103年6月9日，取自
https://www.youtube.com/edit?o=U&video_id=82CgM3dLT3I
[47]YOUTUBE(民國103年6月9日)。GOOGLE公司 行車安全監控系統-車道偏移偵測(隧道時段測試結果)。民國103年6月9日，取自
https://www.youtube.com/edit?o=U&video_id=mqwySuKPtXY
[48]YOUTUBE(民國103年6月9日)。GOOGLE公司 行車安全監控系統-車道偏移偵測(晚間時段測試結果)。民國103年6月9日，取自
https://www.youtube.com/watch?v=vOW_n26MoLo
[49]YOUTUBE(民國103年6月9日)。GOOGLE公司 行車安全監控系統-車道偏移偵測(小雨時段測試結果)。民國103年6月9日，取自
https://www.youtube.com/watch?v=Mb7SF_5xQSo
[50]YOUTUBE(民國103年6月9日)。GOOGLE公司 行車安全監控系統-車道偏移偵測(大雨時段測試結果)。民國103年6月9日，取自
https://www.youtube.com/watch?v=4jufY1q-psw