(3.238.235.155) 您好!臺灣時間:2021/05/16 15:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:王峻國
研究生(外文):Jyun-Guo Wang
論文名稱:利用模糊方法於全天候車道線偵測及偏離警示系統之研究
論文名稱(外文):Applying Fuzzy Method to Vision-Based Lane Detection and Departure Warning System
指導教授:林正堅林正堅引用關係王徳譽
指導教授(外文):Cheng-Jian LinDe-Yu Wang
學位類別:碩士
校院名稱:朝陽科技大學
系所名稱:資訊工程系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2008
畢業學年度:96
語文別:英文
論文頁數:75
中文關鍵詞:模糊法則車道線偵測車道偏離警示系統模糊C均值自我分群演算法
外文關鍵詞:fuzzy rulefuzzy C-meanlane detectionSelf-clustering algorithmlane departure warning system
相關次數:
  • 被引用被引用:2
  • 點閱點閱:302
  • 評分評分:
  • 下載下載:35
  • 收藏至我的研究室書目清單書目收藏:0
近年來,由於車輛數目的快速成長,造成交通事故問題日益嚴重。在台灣,根據交通部的資料顯示在過去的四年中,每年至少有超過兩千五百人在車禍事故發生中受傷或死亡。而大部分車禍發生的原因主要由於駕駛人本身的分心、不注意車況、疲勞駕駛等不適當駕駛行為所引起。因此,為了能盡量避免駕駛者身處於此危險狀態,我們針對車輛前方影像資訊,開發一套以智慧型視覺技術為基礎的車道偵測及偏移系統,以確保駕駛人行駛的安全性。
在車道線偵測部分,為了提高車道邊緣資訊和適用於全天候的光線變化條件,我們透過自我分群方法、模糊C均值和模糊法則的結合去處理空間上影像資訊並且藉由Canny演算法來得到良好的邊緣偵測,使此系統在白天及夜間人眼可視車道範圍內,都能獲得清晰的車道邊界資訊。在車道偏移判斷的部分,本論文利用先前偵測的車道線去計算兩者之間的角度對稱關係,並且我們根據偏移程度的不同給予駕駛者適當的警告訊號。
本論文發展的車道偵測輔助系統在3.2GHz的PC平台上平均可達超過每秒14張的執行結果。測試影像內容為在高速公路的實際駕駛環境,並在白天及夜間範圍內都維持穩定的偵測結果。
As the high growth of population of vehicles, the traffic accidents are becoming more and more serious in recent years. In Taiwan, according to the statistics from the Ministry of Transportation and Communications (MOTC, R.O.C.), in the past four yours, there were more than two thousand and five hundred people hurt and died in traffic accidents every year. Most occurrences of the car accidents results from the distraction, inattention for the adjacent cars, and driving fatigue of the driver. As a result, to avoid the driver being in danger as much as possible, an intelligent vision-based system focused on image contents of front camera setting under the rear-view mirror on vehicle is developed about lane detection and lane departure warning in this study.
In the thesis of lane detection, in order to enhance lane boundary information and to suitable for various light conditions all day, we combine the self-clustering algorithm (SCA), fuzzy c-mean and fuzzy rule model methods to process the spatial information and Canny algorithms to get good edge detection, so that the lane boundary keeps distinct whether people have seen in the day or night environment. In the thesis of lane departure warning, the system uses instantaneous information from the lane detection to calculate angle relations of the boundaries. The system sends a suitable warning signal to drivers, according to degree different of the departure.
The lane detection and departure warning system proposed in this paper have been successfully evaluated on the PC platform of 3.2-GHz CPU with an average frame-rate is up to 14fps. Moreover, this algorithm can maintain stable results in day or night environment of the realistic driving on highway.
摘 要 I
ABSTRACT III
List of Figures IX
List of Tables XII
Chapter1 1
1.1 Motivation 1
1.2 Literature Review 4
1.3 Objectives 7
1.4 Thesis Organization 8
Chapter2 9
2.1 Introduction 9
2.2 Related Works 10
2.3 Camera Calibration 11
2.4 System Framework 12
Chapter3 14
3.1 Overview 14
3.2 Basic Concepts of Fuzzy Logic 15
3.3 Preprocessing 17
3.3.1 Automatic Brightness Compensation using Fuzzy Rules 19
3.3.2 Canny Edge Detection 41
3.3.3 Fan Scanning Detection 48
Chapter4 54
4.1 Overview 54
4.2 Detection of Lane Departure 56
Chapter5 60
5.1 Experimental Setup 60
5.2 Results of Distinct Environments 62
5.2.1 Explanation of Experimental Conditions 62
5.2.2 Results of Lane Detection 62
5.2.3 Results of Lane Departure Warning 65
Chapter6 69
Bibliography 71
List of Figures
Figure 1.1: Two dangerous situations. 8
Figure 2.1: The flow chart of system operation 13
Figure 3.1: Fuzzy membership functions 16
Figure 3.2: The flow chart of lane detection. 18
Figure 3.3: (a) The original image acquired by camera in front of vehicle. (b) The realistic frame acquired using RGB-to-YIQ. 19
Figure 3.4: (a) Calculate of each pixel of the accumulate value by way of entire image; (b) Calculate of each pixel of the accumulated value by way of intensity profile of roadway part block in the image. 20
Figure 3.5: The center of area in the entire image. 21
Figure 3.6: The transformation in data 22
Figure 3.7: A brief clustering process using SCA with samples in 2-D space. 27
Figure 3.8: A special SCA case. 27
Figure 3.9: (a) The two values that separate out the light component and dark component from entire image; (b) The two values that separate out the light component and dark component from intensity profile of roadway part block. (The horizontal axis is the pixel and longitudinal axis is the accumulation value) 30
Figure 3.10: Fuzzy rule table for brightness compensation control units (d: distance; v: light-dark variation) 37
Figure 3.11: Fuzzy logic membership functions. 38
Figure 3.12: The brightness compensation curve. 38
Figure 3.13: (a) The original gray image; (b) The passed through brightness compensation gray image. 40
Figure 3.14: Discrete approximations to Gaussian function 43
Figure 3.15: The mask type of (a) (b) 44
Figure 3.16: The edge direction description 45
Figure 3.17: The five angle regions distribution 45
Figure 3.18: (a) The edge detection without brightness compensation; (b) The edge detection with brightness compensation 47
Figure 3.19: The result of the reduce data. 48
Figure 3.20: Sketch of the neighbor edge. 49
Figure 3.21: The result of the link neighbor edge point. 50
Figure 3.22: Sketch of the merger line segment 52
Figure 3.23: The result of the link in the same lane line segment. 53
Figure 3.24: The result of the depicted in actual image. 53
Figure 4.1: The flow chart of the lane departure warning system. 56
Figure 4.2: Orientation of lane boundaries 57
Figure 4.3: Results of the various warning signal display 59
Figure 5.1: The experimental architecture. 60
Figure 5.2: The programming interface in the PC platform. 62
Figure 5.3: The results of lane detection. 65
Figure 5.4: The Results of lane departure warning 68
List of Tables
Table 2.1 System devices 10
Table 5.1: The specification of platform information 61
[1] J. Hagen, Road safety crisis, UN Chronicle Online Edition,http://www.un.org/Pubs/chronicle/2004/issuel/0104p78.asp
[2] M. Chen, T. Jochem, D. Pomerleau, “AURORA: A vision-based roadway departure warning system,” Proceedings of the IEEE International Conference on Robotics & Automation, Vol. 1, pp. 243-248, Aug. 1995.
[3] D. J. LeBlanc, G. E. Johnson, P. J. Venhovens, G. Gerber, R. D. Sonia, R. D. Ervin, C. F. Lin, A. G. Ulsoy, T. E. Pilutti, “CAPC: A road departure prevention system,” IEEE Control Systems Magazine 16, 61–71, 1996
[4] W. Kwon, J. W. Lee, D. Shin, K. Roh, D. Y. Kim, and S. Lee, “Experiments on decision making strategies for a lane departure warning system,” Proceedings of the IEEE International Conference on Robotics & Automation, pp. 2596-2601, May, 1999.
[5] R. Risack, N. Mohler, W. Enkelmann, “A video-based lane keeping assistant,” Proceedings of IEEE Intelligent Vehicles Symposium, pp. 356-361, Oct. 2000.
[6] J. W. Lee, “A machine vision system for lane-departure detection,” Computer Vision and Image Understanding, Vol. 86, no. 1, pp. 52–78, 2002.
[7] P. L. Hsu, H. Y. Cheng, B. Y. Tsuei, and W. J. Huang, “The adaptive lane-departure warning system,” Proceedings of the 41st SICE Annual Conference, Vol. 5, pp. 2867-2872, Aug. 2002.
[8] J. W. Lee, C. D. Kee, U. K. Yi, “A new approach for lane departure identification,” in: Proceedings of IEEE Intelligent Vehicles Symposium, pp. 100–105, 2003.
[9] N. Apostoloff, A. Zelinsky, “Robust based lane tracking using multiple cues and particle filtering,” in: Proceedings of IEEE Intelligent Vehicles Symposium, pp. 558–563, 2003.
[10] C. S. Hsu, “The decision strategies of irregular vehicle behavior warning system,” M.S. Thesis, Graduate Institute of Civil Engineering, National Taiwan University, Taipei, Taiwan, June 2003.
[11] J. C. McCall, M. M. Trivedi, “An integrated robust approach to lane marking detection and lane tracking,” in: Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy, pp. 533–537, 2004.
[12] C. R. Jung, C. R. Kelber, “A lane departure warning system based on a linear-parabolic lane model,” IEEE Intelligent Vehicles Symposium, pp. 891-895, 14-17 June, 2004.
[13] C. R. Jung, C. R. Kelber, “A lane departure warning system using lateral offset with uncalibrated camera,” Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, pp. 13-16 Sep. 2005.
[14] Y. I. Abdel-Aziz, and H. M. Karara, “Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry”, Proceedings of the Symposium on Close-Range Photogrametry, pp. 1-18, Falls Church, VA: American Society of Photogrammetry, 1971.
[15] T. Echingo, “A camera calibration technique using three sets of parallel lines,” Machine Vision and Applications, Vol. 3, pp. 159-167, 1990.
[16] L. L. Wang and W. Tsai, “Camera calibration by vanishing lines for 3-D computer vision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vo1. 13, No. 4, pp. 370-376, April, 1991.
[17] E. K. Bas and J. D. Crisman, “An easy to install camera calibration for traffic monitoring,” IEEE Conference on Intelligent Transportation System, Nov. 9-12, 1997.
[18] Bucher, Thomas, “Measurement of distance and height in images based on easy attainable calibration parameters,” Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 314-319, Oct. 2000.
[19] Zadeh, A. Lotfi, “Fuzzy sets,” Information and Control, Vol. 8, pp. 338-353, 1965.
[20] Zadeh, A. Lotfi, “Fuzzy logic and the calculus of fuzzy if-then rules,” 22nd International Symposium on Multiple-Valued Logic, IEEE proceedings, May 1992.
[21] C. J. Lin, Y. J. Xu, “A self-adaptive neural fuzzy network with group-based symbiotic evolution and its prediction applications,” Fuzzy Sets and Systems, Vol. 157, Issue: 8, pp. 1036-1056, April 16, 2006.
[22] Yen John and Reza Langari, “Fuzzy Logic: Intelligence control and information,” Prentice-Hall, Inc., 1998.
[23] Rafael C. Gonzalez, Richard E. Woods, and Steven L. Eddins, “Digital Image Processing,” Prentice-Hall, Inc., 2003.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top