本論文之主要目的在發展道路標線偵測與前車碰撞警告系統。因為駕駛者在駕駛時容易被前方車輛或左右車輛無預警的行為影響，導致應變不及而發生危險，因此各車廠陸續開發出許多駕駛安全輔助系統，以保護駕駛者的安全。高速公路上道路標線偵測與前車碰撞警告系統中在駕駛安全輔助系統中扮演一個非常重要的角色。道路標線偵測可以協助系統判斷本車車輛異常跨車道的行為，並監控車輛前方的安全範圍。前車碰撞警告可以在左右車道車輛突然跨入本車車道或是本車前方車輛離本車太近時進行警告避免車禍發生。
本研究將行車紀錄器裝置在車輛的擋風玻璃上，拍攝前方車輛與標線，再輸入系統進行分析。本系統依功能可分為兩個子系統，道路標線偵測子系統與前方車輛偵測子系統。道路標線偵測子系統利用Sobel邊緣偵測技術及Hough transform線段偵測技術來擷取車道標線。前方車輛偵測子系統，在日間時利用Otsu’s method尋找適合之門檻值擷取出陰影特徵，並利用水平邊緣偵測車輛水平特徵，同時採用此兩項特徵進行影像中車輛定位；另外，在夜間或雨天時則使用YCrCb色彩空間的Cr component及HSI的Hue component擷取煞車燈顏色特徵，並透過煞車燈的對稱性進行車輛定位。
實驗結果顯示，本系統具高度的穩定性及可用性。雖然在隧道中前方車輛偵測的正確率較低，但在下雨天或是夜間視線極度不良時仍能正常運作。未來希望能發展成嵌入式系統裝置在各車輛上實際上路使用。

關鍵字：大津法、車道標線偵測、車輛偵測

The main purpose of this thesis is to develop a front-vehicle collision warning system. Drivers are easy to affect by the unexpected behaviors of neighboring vehicles and sometimes cause traffic accidents. Therefore, many driving assistance systems have been developed by car companies to protect drivers. The lane marking detection and front-vehicle detection system on the highway is one of the driving assistance systems.
The lane marking detection system can detect abnormal lane change behaviors of the host vehicle, and monitor the road region in front of the host vehicle for safety. The front-vehicle collision warning system can warn the drivers when they are in dangerous traffic situations, for example, “the left-side or right-side vehicles suddenly enter to the host lane” or “the front vehicle is too close to the host vehicle.”
In this study a recorder is set on front windshield to obtain the input sequences. The proposed system can be divided into two sub-systems, one is the lane marking detection sub-system and the other is the front-vehicle detection sub-system. The lane marking detection sub-system uses Sobel edge detection and Hough transform technique to extract the lane marking.
The front vehicle detection sub-system can process two different situations, the daytime and the nighttime or raining day. This system uses Otsu’s method to find the suitable threshold to extract the vehicle’s shadow, and uses a horizontal edge detection to detect vehicle’s horizontal features in daytime. Combine these two features, the system can verify the locations of front vehicles. On the other hand, the system uses Cr component of YCrCb color model and Hue component of HSI color model to extract the light features in nighttime or raining. Moreover, the system uses the property of the symmetry of brake lights to verify the location of front vehicles.
The experimental results show that the proposed system has great stability and usability. Although the front-vehicle detection system obtains lower correct rate in the tunnel, it still works when raining or extreme bad sight in nighttime. Finally, we hope the proposed system can be embedded into driving assistance systems installed in every vehicle in the future.

Index terms—Otsu’s method, lane detection, vehicle detection

[Aud 11] Audi官方網站，取自http://www.audi.com.tw/tw/brand/zh.html，2011年。
[Bmw 11] BMW官方網站，取自http://www.bmw.com.tw/home/index.htm，2011年。
[Mer 11] Mercedes-benz官方網站，取自http://www.mercedes-benz.com.tw/conte nt/taiwan/mpc/mpc_taiwan_website/twng/home_mpc/passengercars.html，2011年。
[Toy 11] Toyota官方網站，取自http://www.toyota.com.tw/，2011年。
[Nis 11] Nissan官方網站，取自http://www.nissan.com.tw/，2011年。
[Vol 11] Volve官方網站，取自http://www.volvocars.com/tw/Pages/default.aspx，2011年。
[Lex 11] Lexus官方網站，取自http://www.lexus.com.tw/，2011年。
[Inf 11] Infiniti官方網站，取自http://www.infiniti.com.tw/homepage/index.htm，2011年。
[Lux 11] Luxgen官方網站，取自http://www.luxgen-motor.com.tw/，2011年。
[Hon 11] Honda官方網站，取自http://www.honda-taiwan.com.tw/，2011年。
[Mit 11] Mitsubishi官方網站，取自http://www.mitsubishi-motors.com.tw/，2011年。
[For 11] Ford官方網站，取自http://www.ford.com.tw/servlet/Satellite?pagename=DFY/LH，2011年。
[Por 11] Porshce官方網站，取自http://www.porsche.com.tw，2011年。
[Blo 11] http://blog.xuite.net/gm9013355/blog/51633688
[Uca 11] http://newcar.u-car.com.tw/newcar-home.asp
[You 11] http://www.youtube.com/?gl=TW&hl=zh-TW
[Car 11] http://www.carnews.com/detail/18614
[Uca 11] http://news.u-car.com.tw/news-detail.asp?nid=11150
[Mob 11] http://www.mobile01.com/topicdetail.php?f=449&t=1655936
[Uca 11] http://roadtest.u-car.com.tw/roadtest-detail.asp?rid=672
[Aut 11] http://auto.msn.com.tw/testdrive_content.aspx?sn=1012130002
[Ncc 11] http://nccc.cool3c.com/article/13702
[旅行 12] http://xing.glyx.cn/machine/2304.shtml
[Wik 12] http://zh.wikipedia.org/wiki/%E8%BB%8A%E9%81%93%E5%81%8F
%E9%9B%A2%E8%AD%A6%E7%A4%BA
[Cha 12] http://www.channel-auto.com/cars/ai_46_2665.html
[Gon 07] R. C. Gonzalez and R. E. Woods, Digital Image Processing Third Edition Prentice-Hall, New Jersey, 2007.
[Gon 00] J. P. Gonzalez and U. Ozguner, “Lane Detection using Histogram-Based Segmentation and Decision Trees,” Proceedings of IEEE Intelligent Transportation Systems, Westminster, USA, pp.346-351, Aug. 2000.
[Kha 09] O. O. Khalifa, A. A. M. Assidiq, and A. H. A. Hashim, “Vision-Based Lane Detection for Autonomous Artificial Intelligent Vehicles,” Proceedings of IEEE International Conference on Semantic Computing, (ICSC '09), Gombak, Malaysia, pp.636-641, Oct. 2009.
[Lin 10] Q. Lin, Y. Han, and H. Hahn, “Real-Time Lane Detection Based on Extended Edge-Linking Algorithm,” Proceedings of 2th International Conference on Computer Research and Development, Seoul, South Korea, pp.725-730, Jun. 2010.
[Zho 10] S. Zhou, Y. Jiang, J. Xi, J. Gong, J. Xiong, and H. Chen, “A Novel Lane Detection Based on Geometrical Model and Gabor Filter,” Proceedings of Intelligent Vehicles Symposium (IV '10), Beijing, China, pp.59-64, Aug. 2010.
[Zhe 08] B. Zheng, B. Tian, J. Duan, and D. Gao, “Automatic Detection Technique of Preceding Lane and Vehicle,” Proceedings of IEEE International Conference on Automation and Logistics (ICAL '08), Beijing, pp.1370-1375, Sep. 2008.
[Wan 05] C. C. Wang, S. S. Huang, and L. C. Fu, “Driver Assistance System for Lane Detection and Vehicle Recognition with Night Vision,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '05), Taipei, Taiwan, pp.3530-3535, Dec. 2005.
[Lee 09] J. W. Lee and J. S. Cho, “Effective Lane Detection and Tracking Method using Statistical Modeling of Color and Lane Edge-Orientation,” Proceedings of 4th IEEE International Conference on Computer Sciences and Convergence Information Technology (ICCIT '09), Cheonan, South Korea, pp.1586-1591, Dec. 2009.
[Meu 09] M. Meuter, S. Muller-Schneiders, A. Mika, S. Hold, C. Nunn, and A. Kummert, “A Novel Approach to Lane Detection and Tracking,” Proceedings of 12th IEEE Conference on Intelligent Transportation Systems (ITSC '09), Wuppertal, Germany, pp.1-6, Nov. 2009.
[Bro 10] A. Borkar, M. Hayes, and M. T. Smith, “Robust lane Detection and Tracking with RANSAC and Kalman Filter,” Proceedings of 16th IEEE International Conference on Image Processing (ICIP '09), Atlanta, GA, USA, pp.3261-3264, Feb. 2010.
[Liu 11] X. Liu, B. Dai, J. Song, H. He, and B. Zhang, “Real-Time Long-Range Lane Detection and Tracking for Intelligent Vehicle,” Proceedings of 6th International Conference on Image and Graphics (ICIG '11), Changsha, China, pp.654-659, Aug. 2011.
[Chi 05] K. Y. Chiu and S. F. Lin, “Lane Detection using Color-Based Segmentation,” Proceedings of IEEE Intelligent Vehicles Symposium, Hsinchu, Taiwan, pp.706-711, Sep. 2005.
[Sun 06-1] T. Y. Sun, S. J. Tsai, and V. Chan, “HSI Color Model Based Lane-Marking Detection,” Proceedings of IEEE on Intelligent Transportation Systems Conference (ITSC '06), Hualien, Taiwan, pp.1168-1172, Oct. 2006.
[Kim 05] S. Kim, S. Y. Oh, J. K. Kang, J. W. Ryu, K. S. Kim, S. C. Park, and K. H. Park, “Front and Rear Vehicle Detection and Tracking in the Day and Night Times using Vision and Sonar Sensor Fusion,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '05), South Korea, pp.2173-2178, Dec. 2005.
[Ayt 10] B. Aytekin and E. Altug, “Increasing Driving Safety with a Multiple Vehicle Detection and Tracking System using Ongoing Vehicle Shadow Information,” Proceedings of IEEE International Conference on Systems Man and Cybernetics (SMC '10), Istanbul, Turkey, pp.3650-3656, Nov. 2010.
[Che 07] Y. X. Chen, M. Das, and D. Bajpai, “Vehicle Tracking and Distance Estimation Based on Multiple Image Features,” Proceedings of 4th Canadian Conference on Computer and Robot Vision (CRV '07), Montreal, Canada, pp.371-378, Jun. 2007.
[Hua 10] L. L. Huang, “Real-Time Multi-Vehicle Detection and Sub-Feature Based Tracking for Traffic Surveillance Systems,” Proceedings of 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR '10), USA, pp.324-328, Apr. 2010.
[Che 11] G. T. Cheng and X. Chen, “A Vehicle Detection Approach Based on Multi-Features Fusion in the Fisheye Images,” Proceedings of 3rd International Conference on Computer Research and Development (ICCRD '11), Langfang, China, Vol.4 , pp.1-5, May. 2011.
[Geh 07] S. K. Gehrig and F. J. Stein, “Collision Avoidance for Vehicle-Following Systems,” IEEE Transactions on Intelligent Transportation Systems, Vol. 8, No.2, pp.233-234, Jun. 2007.
[Che 06] H. Y. Cheng, B. S. Jeng, P. T. Tseng, and K. C. Fan, “Lane Detection with Moving Vehicles in the Traffic Scenes,” IEEE Transactions on Intelligent Transportation Systems, Vol.7, No.4, pp.571-582, Dec. 2006.
[Dia 08] J. Diaz Alonso, E. Ros Vidal, A. Rotter, and M. Muhlenberg, “Lane-Change Decision Aid System Based on Motion-Driven Vehicle Tracking,” IEEE Transactions on Vehicular Technology, Vol.57, No.5, pp.2736-2746, Sep. 2008.
[Sun 06-2] H. Sun, G. Bebis, and R. Miller, “Monocular Precrash Vehicle Detection: Features and Classifiers,” IEEE Transactions on Image Processing, Vol.15, No.7, pp.2019-2034, Jun. 2006.
[Cha 08] T. H. Chang, C. S. Hsu, C. Wang, and L. K. Yang, “Onboard Measurement and Warning Module for Irregular Vehicle Behavior,” IEEE Transactions on Intelligent Transportation Systems, Vol.9, No.3, pp.501-513, Aug. 2008.
[Zhu 06] Y. Zhu, D. Comaniciu, M. Pellkofer, and T. Koehler, “Reliable Detection of Overtaking Vehicles Using Robust Information Fusion,” IEEE Transactions on Intelligent Transportation Systems, Vol.7, No.4, pp.401-414, Dec. 2006.
[Yim 04] Y. U. Yim and S. Y. Oh, “Three-Feature Based Automatic Lane Detection Algorithm (TFALDA) for Autonomous Driving,” IEEE Transactions on Intelligent Transportation Systems, Vol.4, No.4, pp.219-225, Jan. 2004.
[Tsa 07] L. W. Tsai, J. W. Hsieh, and K. C. Fan, “Vehicle Detection using Normalized Color and Edge Map,” IEEE Transactions on Image Processing, Vol.16, No.3, pp.850-864, Feb. 2007.
[Jaz 11] A. Jazayeri, H. Y. Cai, J. Y. Zheng, and M. Tuceryan, “Vehicle Detection and Tracking in Car Video Based on Motion Model,” IEEE Transactions on Intelligent Transportation Systems, Vol.12, No.2, pp.583-595, May. 2011.