保持安全距離在道路駕駛上是十分重要的，保持和前車的安全距離可以有效降低事故發生的機率，這篇論文中提出了一個有效率的距離量測方法，並且只使用了單一攝影機，有別於一般雙眼立體視覺的架構。
本篇論文共分成四個模組，分別為車燈偵測模組、距離量測模組、車牌偵測模組以及決策模組，透過四個模組的分工，我們便可以知道前車的距離，進一步可以對駕駛人做出警告，避免對前車的碰撞。
在車燈偵測模組中，文中以車燈的亮度及顏色特徵作為車燈偵測的基礎，可以在很短的時間內找到車子的兩個車尾燈，利用車尾燈的寬度帶入距離量測模組中，便可以得到與前車的距離，在距離沒有碰撞的危險時我們使用攝影機變焦的功能，取得車牌的影像，利用車牌偵測模組找到車牌的切確位置，並透過車牌與車燈的比例關係對於距離量測所使用的參數做出校正，已達到更精確的防碰撞效果，在決策模組中，以簡單的物理公式給予使用者適當的輔助，以達成安全駕駛的目標。

Keeping a safe distance away from the frontal car is an important issue for car accident prevention. This thesis presents a practical distance measuring method in nighttime using a single CCD camera. The proposed system consists of three modules including taillight detection, license-plate detection, and distance measurement of which estimating the distance from the frontal car during driving. Firstly, the two taillights of a car are detected and extracted to be the salient features. Based on the proportionality of similar triangles, the distance between the CCD camera and the frontal car can be estimated. In addition, the license plate is detected and the measuring parameters are refined for accuracy enhancement. As a result, less processing time and high accuracy rate can be achieved by using the proposed method.
In taillight detection module, the color and intensity are used to serve as the features. In a special color space, the taillight can be found easily. The second part in the system is the distance measuring module. In this module, we propose a special measuring system in which the real distance can be calculated by just using a single image. In the third module, an Adaboost license plate detector is employed. The license plate can be successfully detected by using Haar function and the system parameter can be automatically improved to uplift the accuracy.
Experimental results demonstrate that our proposed system can indeed achieve the goal of car collision prevention during nighttime.

[1]
K. T. Song, C. H. Chen and C. H. Chiu-Huang, “Design and experimental study of on ultrasonic sensor system for lateral collision avoidance at low speed”, Proc. of 2004 IEEE int. Symposium on Intelligent Vehicles, pp.647-652, 2004.
[2]
Z. Yi, H. Y Khing, C. C. Seng, Z. X. Wei, “Multi-ultrasonic sensor fusion for mobile robots,” Proc. of 2000 IEEE Int. Symposium on Intelligent Vehicles, pp.387-391, 2000.
[3]
N. Tamiya, H. Mandai, T. Fukae, “Optical spread spectrum radar for lateral detection in vehicles,” Proc. of 1996 IEEE Int. Symposium on Spread Spectrum Techniques and Applications, pp.195-198, 1996.
[4]
S. Tanaka, T. Nakagawa, M. Akasu, Y. Fukushima, and W. J. Bracken, “Development of a compact scan laser radar,” in Proc. SAE World Congr., 1999, pp. 101-106.
[5]
K. Hanawa and Y. Sogawa, “Development of stereo image recognition system for active driving assist,” in Proc. IEEE Intelligent vehicles Symposium, 2001. pp. 177-182.
[6]
C. Knoppel, A. Schanz, and B. Michaelis, “Robust vehicle detection at large distance using low resolution cameras,” Proceedings of IEEE Intelligent Vehicles Symposium, pp.267-272, Oct. 2000.
[7]
H.Y. Cheng, B. S. Jeng, P. T. Tseng, and K. C Fan, “Lane Detection With Moving Vehicles in the Traffic Scenes,” IEEE Transaction on Intelligent Transportation System, Vol. 7, NO. 4, Dec. 2006
[8]
Y. U. Yim and S. Y. Oh, “Three-feature based automatic lane detection algorithm (TFALDA) for autonomous driving,” IEEE Transaction on Intelligent Transportation System, Vol. 4, Issue 4, Dec. 2003
[9]
P. Jeong and S. Nedevschi, “Efficient and Robust Classification Method Using Combined Feature Vector for Lane Detection, ” IEEE Transaction on Intelligent Transportation System,” Vol. 15 No. 4, APRIL 200
[10]
E. Dagan, O. Mano, G. P. Stein and A. Shashua, ” 2004 IEEE Intelligent Vehicles Symposium,” University of Parma, Italy June 1447,2004
[11]
G. P. Stein, O. Mano, and A. Shashua, ” 2003 IEEE Intelligent Vehicles Symposium,” Page(s):120 – 125, 9-11 June 2003
[12]
M. C. Lu, W. Y. Wang, and H. H. Lian, “Image-based height measuring system for liquid or particles in tanks,” IEEE International Conference on Networking, Sensing and Control, Vol.1, pp.24-29, 2004.
[13]
M. C. Lu, W. Y. Wang, and C. Y. Chu, “Optical-based distance measuring system (ODMS),” The Eighth International Conference on Automation Technology, pp.282-285, 2005.
[14]
W. Y. Wang, M. C. Lu, T. H. Wang, C. P. Tsai, and Y. Y. Lu, “Image-and robot-based distance and area measuring”,” Proceedings of the 2007 WSEAS Int. Conference on Circuits, Systems, Signal and Telecommunications (CISST’07), Gold Coast, Queensland, Australia, January 17-19, 2007.2007 WSEAS international Conference on (CISST), Gold-Coast, Australia, January 17-19, 2007.
[15]
W. Y. Wang, M. C. Lu, and C. Y. Chu, “Nighttime vehicle distance measuring system(NVDMS),” IEEE Transactions on Circuits and System-II, Volume 54, Jan. 2007.
[16]
T. H. Wang, M. C. Lu, C. C. Hsu, and W. Y. Wang, “A method of distance measurement by digital camera,” Proceedings of 2006 ACAS Automatic Control Conference , St. John’s University, Tamsui, Taiwan, Nov. 10-11, 20032006.
[17]
M. C. Lu, W. Y. Wang, and H. H. Lian, “Image-based distance and area measuring systems,” IEEE Sensors Jornal, vol. 6. no. 2, pp. 495-503, apr.
[18]
H. Zhang, W. Jia, X. He, and Q. Wu, “A fast algorithm for license plate detection in various conditions,” IEEE International conference on Systems, Man, and Cybernetics, Taipei, Taiwan, October 8-11, 2006
[19]
T.-H. Wang, M.-C. Lu, C.-C. Hsu, Y.-Y Lu, and C.-P. Tsai, “Three dimensional distance measurement based on single digital camera,” Proceedings of the 2007 WSEAS Int. Conference on Circuits, Systems, Signal and Telecommunications (CISST’07), Gold Coast, Queensland, Australia, January 17-19, 2007.
[20]
蘇木春, 張孝德, “機器學習：類神經網路、模糊系統以及基因演算法則”, 全華科技圖書股份有限公司, 2003.
[21]
P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," in Proceeding of the IEEE International Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 1-511 – 1-518, 2001.