本研究目的是要透過電腦視覺技術完成一個完整的交通標誌號與號誌偵測系統，協助駕駛人認知交通號誌與標誌，以減少駕駛人的負擔，並達到降低交通事故。
我們以實際拍攝交通號誌與標誌樣本學習偵測交通號誌與標誌色彩，以凸包演算法填補色彩空間中樣本擷取不足的色彩空缺，並以八分樹資料結構紀錄標誌與號誌的色彩範圍。透過學習到的色彩範圍作為擷取號誌與標誌色彩的依據，並將擷取出的像素連結成一個個區塊。
號誌區塊先根據長寬比、面積大小等幾何條件作初步篩選，並以號誌發光之特性作為判斷的依據。通過篩選的號誌區塊，最後以號誌特有的弧形對稱邊做確認。在偵測到的號誌周邊以邊資訊輔助偵測號誌燈箱，利用燈箱在影像中的寬度及相機內部參數推估號誌距離。
標誌區塊以幾何形狀作初步篩選，其中紅色標誌區塊通過篩選後，將剩餘的區塊正規到固定大小；經過二值化後，與事先定義好的三角形及圓形樣板比對判斷標誌形狀並分類。由於交通標誌的內容皆為白底黑字所構成，對內容物正規到固定的大小，對此區塊作疊代逼近門檻值篩選，自動找出適當的門檻值，再根據此門檻值做二值化。取得這個完整區塊的二值化影像後經由樣板比對辨識限速標誌數值。
我們在不同天候環境下測試我們的系統。交通號誌偵測的準確度為95.62%，交通標誌偵測的準確度為93.08%。限速標誌的數值辨識在772個測試資料中正確辨識755個，正確率有97.80%。

In this thesis, we propose a traffic signal and sign detection system to help drivers noticing the traffic situation on the roads. There are three stages in the proposed system: i. colored signal and sign detection, ii. signal and sign verification, and iii. signal distance estimation and sign recognition. The detection task is the most difficult due to the color is variant in different weather conditions. Here we propose a color learning method to extract the proper pixels to detect traffic signs and signals. The color distributions of traffic signal and sign are analyzed in the IHS color space. The color distribution was built by a convex hull method and described by an Octree data structure. According to the learned color distribution, candidates of signal and sign are extracted from the image. Then regions of candidates of signal and sign are verified by geometric conditions, size, and the rate of width and height. To reduce the rate of wrong detection, two special features are used to verify the detected signals. One is active light emitting, and the other is the symmetrical arc edges of a light. In this study, we only classify the signs into three classes: circle, semicircle, and triangle.
To improve the practical applications, the distance between a signal and the camera is estimated based on the width of the traffic light box which can be detected by edge information around the signal region and the internal parameters of the camera. In the sign recognition, the characters of speed limit are extracted to recognize using template matching. For this purpose, we had to extract the speed limit characters.
The proposed systems were evaluated in variant environments. The accuracy of traffic signal detection is 95.6% and th accuracy of traffic sign detection is 93.1%. The recognition rate of characters in speed limit signs is 97.8% from 772 character samples.

[1] Andrew, A. M., "Another efficient algorithm for convex hulls in two dimensions," Information Processing Letters, vol.9, no.5, pp.216-219, 1979.
[2] Asakura, T., Y. Aoyagi, and K. Hirose, "Real-time recognition of road traffic sign in moving scene image using new image filter," IEEE Trans. Industrial Electronics, vol.3, no.6, pp.2207-2212, 2000.
[3] Broggi, A., P. Cerri, P. Medici, and P. P. Porta, "Real time road signs recognition," in Proc. 2007 IEEE Intelligent Vehicles Symp., Istanbul, Turkey, Jun.13-15, 2007, pp.981-986.
[4] Cheng, S.-C., Detection of Unstructured Road Boundary and Road Sign Recognition, Master Thesis, Department of Electrical Engineering, Univ. of National Chung Cheng, Chiayi, Taiwan, 2003.
[5] Chung, Y. C., J. M. Wang, and S. W. Chen, "A vision-based traffic light detection system at intersections," Journal of National Taiwan Normal University, Mathematics, Science and Technology, vol.47, no.1, pp.67-86, 2002.
[6] De Charette, R. and F. Nashashibi, "Real time visual traffic lights recognition based on Spot Light Detection and adaptive traffic lights templates," in Proc. IEEE Intelligent Vehicles Symp., Xi''an, China, Jun. 3-5, 2009, pp.358-363.
[7] De La Escalera, A., L. E. Moreno, M. A. Salichs, and J. M. Armingol, "Road traffic sign detection and classification," IEEE Trans. Industrial Electronics, vol.44, no.6, pp.848-859, 1997.
[8] De La Escalera, A., J. M. Armingol, J. M. Pastor, and F. J. Rodríguez, "Visual sign information extraction and identification by deformable models for intelligent vehicles," IEEE Trans. Industrial Electronics, vol.5, no.2, pp.57-68, 2004.
[9] Fang, C. Y., S. W. Chen, and C. S. Fuh, "Road-sign detection and tracking," Vehicular Technology, vol.52, no.5, pp.1329-1341, 2003.
[10] Franke, U., D. Gavrila, S. Görzig, F. Lindner, F. Paetzold, and C. Wöhler, "Autonomous driving goes downtown," IEEE Intelligent Systems and Their Applications vol.13, no.6, pp.40-48, 1998.
[11] García, M. Á., M. Á. Sotelo, and E. M. Gorostiza, "Traffic sign detection in static images using matlab," Emerging Technologies and Factory Automation, vol.2, no.5, pp.212-215, 2003.
[12] Hsu, S. H. and C. L. Huang, "Road sign detection and recognition using matching pursuit method," Image and Vision Computing, vol.19, no.3, pp.119-129, 2001.
[13] Hsueh, S. L., Two-step Road Sign Recognition, Master Thesis, Institute of Computer Engineering and Science, Univ. of Yuan-Ze, Chungli, Taiwan, 2002.
[14] Huang, W. C. and C. H. Wu, "Adaptive color image processing and recognition for varying backgrounds and illumination conditions," IEEE Trans. Industrial electronics, vol.45, no.2, pp.351-357, 1998.
[15] Kellmeyer, D. L. and H. T. Zwahlen, "Detection of motorway warning signs in natural video images using color image processing and neural networks," in Proc. IEEE Int. Conf. Neural Networks, Orlando, FL, Jun.14, 1994, pp.4226-4231.
[16] Lee, J. H. and K. H. Jo, "Traffic sign recognition by division of characters and symbols regions," in Proc. the 7th Korea-Russia Int. Symp, Ulsan , Korea, Jun.28-Jul.6, 2003, pp.324-328.
[17] Lindner, F., U. Kressel, and S. Kaelberer, "Robust recognition of traffic signals," in Proc. Intelligent Vehicles Symp., Parma, Italy, Jun.14-17, 2004, pp.49-53.
[18] Maldonado-Bascón, S., S. Lafuente-Arroyo, P. Gil-Jiménez, H. Gómez-Moreno, and F. López-Ferreras, "Road-sign detection and recognition based on support vector machines," Intelligent Transportation Systems, vol.8, no.2, pp.264-278, 2007.
[19] Miura, J., T. Kanda, and Y. Shirai, "An active vision system for real-Time traffic sign recognition," in Proc. IEEE Conf. on Intelligent Transportation Systems, Dearbom, Michigan, Oct.1-3, 2000, pp.52-57.
[20] Nienhuser, D., M. Drescher, and J. M. Zollner, "Visual state estimation of traffic light using hidden markov models," in Proc. 13th Int. Conf. Intelligent Transportation Systems, Madeira Island, Portugal, Sep.19-22, 2010, pp.1705-1710.
[21] Pacheco, L., J. Battle, and X. Cufi, "A new approach to real time traffic sign recognition based on color information," in Proc. IEEE Intelligent Vehicles Symp., Paris, France, Oct. 24-26, 1994, pp.339-344.
[22] Pérez, E. and B. Javidi, "Nonlinear distortion-tolerant filters for detection of road signs in background noise," Vehicular Technology, vol.51, no.3, pp.567-576, 2002.
[23] Priese, L., J. Klieber, R. Lakmann, V. Rehrmann, and R. Schian "New results on traffic sign recognition," in Proc. IEEE Intelligent Vehicles Symp, Paris, France, Oct. 24-26, 1994, pp.249-254.
[24] Priese, L., R. Lakmann, and V. Lakmann "Ideogram identification in a realtime traffic sign recognition system," in Proc. IEEE Intelligent Vehicles Symp., Detroit, MI, Sep. 25-26, 1995, pp.310-314.
[25] Shaposhnikov, D. G., L. N. Podladchikova, A. V. Golovan, and N. A. Shevtsova, "Road sign recognition by single positioning of space-variant sensor window," in Proc. 15th Int. Conf. Vision Interface, Calgary, Canada, May.27-29, 2002, pp.213-217.
[26] Vitabile, S., A. Gentile, and F. Sorbello, "A neural network based automatic road signs recognizer," in Proc. Int. Joint Conf. Neural Networks, Honolulu, Hawaii, May12-17, 2002, pp.2315-2320.
[27] Yung, N. H. C. and A. H. S. Lai, "An effective video analysis method for detecting red light runners," IEEE Trans. Vehicular Technology, vol.50, no.4, pp.1074-1084, 2001.
[28] Zeng, Y. J., W. Ritter, and R. Jamssen, "An adaptive system for traffic sign recognition," in Proc. Intelligent Vehicles ''94 Symp., Paris, France, Oct. 24-26, 1994, pp.165-170.