本文旨在架設一webcam網路攝影機在一台自走車上，利用即時影像處理之技術，辨識十字路口的紅綠燈，使自走車能辨識紅綠燈並自行通過十字路口。
本文著重在紅綠燈號的影像偵測與辨識上，由於戶外環境干擾源眾多，加上紅綠燈顏色易受光源或是拍攝角度影響其顏色，因此如何提高紅綠燈號的辨別率便是本文的主軸，本文利用紅綠燈號在RGB和HSV雙重色彩系統來篩選其候選區，以增加辨別率，再利用一連串的影像處理方法，定義出紅綠燈可能的位置，然後再判斷其燈號顏色。最後將處理完後所得到的紅綠燈顏色訊息傳達至自走車上；自走車的控制晶片為PIC18F4520，用來接收訊號並下達前進或停止的指令，以完成自走車判斷紅綠燈自行過十字路口的任務。
而本文研究的目的便是希望能將辨識紅綠燈的系統用於車輛駕駛輔助系統ADAS(Advanced Driver Assistance Systems)或是導盲輔助系統上，以帶來更便利與安全的生活。

The main purpose of this thesis is to research traffic light detection and recognition. A webcam is set on the AMV(Automatic Mobile Vehicle) to capture the images and the AMV can recognize crossroads traffic light via real-time image processing techniques. The AMV is able to identify traffic light and pass intersection.
Image detection and recognition of traffic light were emphasized in this thesis because of two reasons. First, there are several outdoor environment interferences, such as the weather. Second, traffic light detection is easily affected by light exposure or the shot angles. How to increase traffic light recognition rate is the principle of the article. We utilize the RGB and HSV dual color system to extract candidate regions of traffic light to increase recognition rate. Then making use of a sequence of image processing to define the sites of traffic light, and then determine the color. Finally, sending the color message of traffic light to AMV after image processing. The control chip on the AMV is PIC18F4520 which is used to receive signal of traffic light and then decides to move forward or stop to fulfill task of AMV passing cross-sections by itself.
The goal of this study is apply the traffic light recognition system on ADAS (Advanced Driver Assistance Systems) or blind aid system in order to bring more convenient and security to life.

[1]NASA, Curiosity ,
http://www.nasa.gov/mission_pages/msl/index.html(2015/7/15)
[2]iRobot公司，Roomba ,
http://store.irobot.com/product/index.jsp?productId=28516906&cp=2501652&(2015/7/15)
[3]SONY公司，
http://www.sony-aibo.com/(2015/7/15)
[4]PCM, UPITOR
http://upitor.pmc.org.tw/zh/home.asp(2015/7/15)
[5]Chang, Chin-Kai, Christian Siagian, and Laurent Itti, “Mobile robot monocular vision navigation based on road region and boundary estimation”, Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, 2012. pp. 1043-1050, 7-12 Oct. 2012.
[6]Lin Rui, Du Zhijiang and Sun Lining, “Moving Object Tracking based on Mobile Robot Vision”, Mechatronics and Automation, 2009. ICMA 2009. International Conference on, IEEE. pp. 3625-3630, 9-12 Aug. 2009.
[7]鄭佳其，應用即時影像處理於導盲磚辨識之自走車，國立成功大學工程科學研究所論文，台南，台灣，2009。
[8]Yehu Shen, Umit Ozguner, Keith Redmill, and Jilin Liu, “A robust video based traffic light detection algorithm for intelligent vehicles”, Intelligent Vehicles Symposium, 2009 IEEE.pp.521-526, 3-5 June 2009.
[9]Sorn Sooksatra, Toshiaki Kondo, “Red traffic light detection using fast radial symmetry transform”, Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2014 11th International Conference on, IEEE.pp.1-6, 14-17 May 2014.
[10]Masako Omachi, Shinichiro Omachi, “Traffic light detection with color and edge information” Computer Science and Information Technology, 2009. ICCSIT 2009. 2nd IEEE International Conference on.pp.284-287, 8-11 Aug. 2009.
[11]Raoul de Charette, Fawzi Nashashibi, “Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates”, Intelligent Vehicles Symposium, 2009 IEEE. pp.358-363, 3-5 June 2009.
[12]Microchip Technology Inc., “PIC18F2420/2520/4420/4520 Data Sheet”, http://ww1.microchip.com/downloads/en/devicedoc/39631a.pdf(2015/7)
[13]TOSHIBA 公司，“TA7291P Data Sheet”, http://www.alldatasheet.com/view.jsp?Searchword=Ta7291p&gclid=CKKb_8iQ2sYCFVgmvQodpkoGeA(2015/7)
[14]賴岱佑，劉敏， 數位影像處理技術手冊，文魁資訊股份有限公司，2009.
[15]繆紹綱， 數位影像處理：運用MATLAB，東華書局股份有限公司，2005.
[16]蕭進松， 數位影像處理，全華科技公司，1999
[17]Chang, Fu, Chun-Jen Chen, “A component-labeling algorithm using contour tracing technique”, Proc. Of Seventh International Conference, Document Analysis and Recognition. pp.741-745, 2003.
[18]Chunhe Yu, Chuan Huang, Yao Lang, “Traffic light detection during day and night conditions by a camera”, Signal Processing (ICSP), 2010 IEEE 10th International Conference on. pp. 821-824, 24-28 Oct. 2010.
[19]Ballard, Dana H., “Generalizing the Hough transform to detect arbitrary shapes”, Pattern Recognition. Volume 13, issue 2,pp.111-122,1981.
[20]Gareth Loy, Alexander Zelinsky, “Fast Radial Symmetry for Detecting Points of Interest”, Pattern Analysis and Machine Intelligence, IEEE Transactions on volume 25, issue 8. pp. 959 - 973, Aug. 2003.