在不利的環境下做交通標誌的偵測與辨識是一件非常艱困的工作，無論在郊區或市區，複雜的環境、天候、陰影以及任何和光線有關的因素甚至是交通標誌遭到遮蔽都將使得偵測與辨識交通標誌變得相當困難。在本篇論文中，我們定義出較寬鬆的顏色分類(color thresholding)方法，配合一些交通標誌的特徵(如外形)來實作出召回率(Recall)較高的偵測系統，另外在辨識方面，最重要的是找出好的辨識特徵，因此我們利用離散餘弦轉換(discrete cosine transform)和奇異值分解(singular value decomposition)處理待辨識標誌擷取其特徵，並配合一些其他的交通標誌特徵，當作類神經網路(ANN)、naïve Bayes classifier等辨識方法的輸入，來幫助我們完成辨識的工作。目前實作出來的系統在有挑戰性的測試資料下有七成六左右的辨識率。

Robust traffic sign recognition can be a difficult task if we aim at detecting and recognizing traffic signs in images captured under unfavorable environments. Complex background, weather, shadow, and other illumination-related problems may make it difficult to detect and recognize signs in the rural as well as the urban areas. In this thesis, I define a formula for color classification and apply other related features such as the shape of the traffic signs to implement the detection component that offers high recall rate. In traffic sign recognition, the most important thing is to get the effective features. I use discrete cosine transform and singular value decomposition to collect the invariant features of traffic signs that will not be severely interfered by disturbing environments. These invariant features can be used as the input to artificial neural networks or naïve Bayes models to achieve the recognition task. This system yields satisfactory performance about 76% recognition rate when I test them with very challenging data.

第一章 簡介 1
1.1 題目定義 1
1.2 研究動機 2
1.3 系統架構 4
1.4 主要貢獻 5
1.5 本篇論文架構 5
第二章 相關論文 7
2.1 交通標誌偵測相關論文 7
2.2 交通標誌辨識相關論文 10
2.3 文獻方法與實作方法之比較與討論 12
第三章 交通標誌偵測與辨識 13
3.1 Region of Interest的偵測 13
3.1.1 Color 13
3.1.2 Region of interest 22
3.1.3 特徵篩選 24
3.1.4 交通標誌偵測流程 25
3.2 前處理 27
3.3 交通標誌辨識 34
3.3.1 特徵的擷取 34
3.3.2 辨識方法的使用 47
第四章 實驗結果 53
4.1 資料來源 53
4.2 實驗設計 57
4.3 實驗結果 57
4.3.1 交通標誌偵測 58
4.3.2 交通標誌辨識 59
4.4 實驗討論 68
第五章 系統設計的討論 70
5.1 被干擾的標誌 70
5.2 受光程度不同的標誌 71
5.3 相似標誌的問題 72
第六章 結論 75
附錄 77
參考文獻 81

[1] 內政部警政署網站統計資料，臺閩地區道路交通事故(A1類)原因、傷亡及車輛損壞，http://www.npa.gov.tw。
[2] 教育資料館，道路交通標誌標線號誌設置規則，民國八十七年。
[3] 張耀升，戶外交通號誌辨識之研究，國立交通大學電機與控制工程研究所碩士論文，民國八十三年。
[4] 黃上銘，交通標誌辨識研究，國立政治大學資訊科學系大四專題報告，政治大學，台北，台灣，民國九十一年。
[5] 羅華強，類神經網路―MATLAB的應用，民國九十年。
[6] Proceedings of the IEEE 5th International Conference on Intelligent Transportation Systems.
[7] Aoki, M. (1999). Imaging and Analysis of Traffic Scene. Proceedings of the 1999 International Conference on Image Processing, 1-5.
[8] Aoyagi, Y. & Asakura, T. (1996). A study on traffic sign recognition in scene image using genetic algorithms and neural networks. Proceedings of the 1996 IEEE IECON 22nd International Conference on Industrial Electronics, Control, and Instrumentation, 1838-1843.
[9] Bartneck, N. & Ritter, W. (1992). Colour Segmentation with polynomial classification. Proceedings of the 11th The International Association for Pattern Recognition International Conference on Pattern Recognition, 635-638.
[10] Egger, O., Fleury, P., Ebrahimi, T. & Kunt, M. (1999). High-performance compression of visual information: A tutorial review, Part I: still pictures. Proceedings of the IEEE, 87(6), 976-1011.
[11] Escalera, A. D. L., Moreno, L. E., Salichs, M. A. & Armingol, J. M. (1997). Road traffic sign detection and classification. IEEE Transactions on Industrial Electronics, 44(6), 848-859.
[12] Gavrila, D. M. (1999). Traffic sign recognition revisited. Proceedings of the 21st Die Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, 86-93.
[13] Gavrila, D. M., Franke, U., Wöhler, C. & Görzig, S. (2001). Real-time vision for intelligent vehicles. IEEE Instrumentation & Measurement Magazine, 4(2), 22-27.
[14] Gavrila, D. M. & Philomin, V. (1998). Real-time object detection for “smart” vehicles. Proceedings of the IEEE Intelligent Vehicle 1998 Symposium, 274-279.
[15] Ghica, D., Lu, S. W. & Yuan, X. (1995). Recognition of traffic signs by artificial neural network. Proceedings of the IEEE International Conference on Neural Networks, 1444-1449.
[16] Haralick, R. & Shapiro, L. (1992). Computer and Robot Vision, vol. 1, 28—48, Addison-Wesley.
[17] Haralick, R. & Shapiro, L. (1992). Computer and Robot Vision, vol. 1, 346—351, Addison-Wesley.
[18] Hirose, K., Asakura, T. & Aoyagi, Y. (2000). Real-Time Recognition of Road Traffic Sign in Moving Scene Image Using New Image Filter. Proceedings of the 26th Annual Conference of the IEEE Industrial Electronics Society, 3, 2207-2212.
[19] Hsu, S. H. & Huang, C. L. (2001). Road sign detection and recognition using matching pursuit method. Image and Vision Computing, 19(3), 119-129.
[20] Janet, J. A., White, M. W., Chase, T. A., Luo, R. C. & Sutton, III J. C. (1996). Pattern analysis for autonomous vehicles with the region- and feature-based neural network: Global self-localization and traffic sign recognition. Proceedings of the 1996 IEEE International Conference on Robotics and Automation, 3598-3604.
[21] Janssen, R., Ritter, W., Stein, F. & Ott, S. (1993). Hybrid approach for traffic sign recognition. Proceedings of the Intelligent Vehicles 1993 Symposium, 390-395.
[22] Jiang, G. Y., Choi, T. Y. & Zheng, Y. (1996). Morphological traffic sign recognition. Proceedings of the 3rd International Conference on Signal Processing, 531-534.
[23] Kang, D. S., Griswold, N. C. & Kehtarnavaz, N. (1994). An invariant traffic sign recognition system based on sequential color processing and geometrical transformation. Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, 88-93.
[24] Kehtarnavaz, N. & Ahmad, A. (1995). Traffic sign recognition in noisy outdoor scenes. Proceedings of the Intelligent Vehicles 1995 Symposium, 460-465.
[25] Khayam, S. A. (2003). The discrete cosine transform：theory and application. Technical Report ECE 802-602：Information theory and coding, Department of Electrical & Computer Engineering, Michigan State University, Michigan, USA.
[26] Luo, R. C., Potlapalli, H. & Hislop, D. (1993). Traffic sign recognition in outdoor environments using reconfigurable neural networks. Proceedings of 1993 International Conference Joint Conference on Neural Networks. 1306-1309.
[27] Mitchell, T. M. (1997). Artificial neural networks. Machines learning, McGram Hill, 97-98.
[28] Mitchell, T. M. (1997). Instance-based learning. Machines learning, McGram Hill, 230-248.
[29] Miura, J., Kanda, T. & Shirai, Y. (2000). An active vision system for real-time traffic sign recognition. Proceedings of the 3rd IEEE International Conference on Intelligent Transportation Systems, 52-57.
[30] Moran, C. J. (1990). A morphological transformation for sharpening edges of features before segmentation. Computer Vision, Graphics, and Image Processing, 49(1), 85-94.
[31] Piccioli, G., Micheli, E. D., Parodi, P. & Campani, M. (1996). A robust method for road sign detection and recognition. Image and Vision Computing, 14(3), 209-223.
[32] Priese, L., Rehrmann, V., Schian, R. & Lakmann, R. (1993). Traffic Sign Recognition Based On Color Image Evaluationion. Proceedings Intelligent Vehicles 1993 Symposium, 95-100.
[33] Priese, L. & Rehrmann, V. (1993). On hierarchical color segmentation and applications. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 633-634.
[34] Priese, L., Klieber, J., Lakmann, R., Rehrmann, V. & Schian, R. (1994). New Results on Traffic Sign Recognition. Proceedings of the Intelligent Vehicles 1994 Symposium, 249-254.
[35] Priese, L., Lakmann, R. & Rehrmann, V. (1995). Ideograph identification in a realtime traffic sign recognition system. Proceedings of the Intelligent Vehicles 1995 Symposium, 310-314.
[36] Potlapalli, H. & Luo, R.C. (1996). Projection learning for self-organizing neural networks. IEEE Transactions on Industrial Electronics 43(4), 485-491.
[37] Rangarajan, K., Shah, M. & Brackle, D. V. (1989). Optimal Corner Detector. Computer Vision, Graphics, and Image Processing 48, 230-245.
[38] Rijsbergen, C. V. (1979). Information Retrieval. Second Edition Butterworth, London, 174.
[39] Ritter, W. (1992), Traffic sign recognition in color image sequences. Proceedings of the Intelligent Vehicle 1992 Symposium, 12-17.
[40] Sandoval, H., Hattori, T., Kitagawa, S. & Chigusa, Y. (2000). Angle-dependent edge detection for traffic signs recognition. Proceedings of the IEEE Intelligent Vehicles 2000 Symposium, 308-313.
[41] Sonka, M., Hlavac, V. & Boyle, R. (1993). The digitized image and its properties. Image Processing, Analysis, and Machine Vision, 26.
[42] Zadeh, M. M., Kasvand, T. & Suen, C. Y. (1997). Localization and recognition of traffic signs for automated vehicle control systems. Proceedings of SPIE’s Intelligent System & Automated Manufacturing.
[43] Zheng, Y. J., Ritter, W. & Jamssen, R. (1994). An Adaptive System For Traffic Sign Recognition. Proceedings of the Intelligent Vehicles 1994 Symposium, 165-170.