交通路標在日常生活中佔有相當高的重要性，若能收集路標的空間資訊並加以管理，將有助於都市規劃及汽車導航統系統的設計。以往，人們若要收集或更新路標的空間資訊，主要是以外業的方式進行，但交通路標的資料眾多，以外業的方式進行收集，會需要大量的人力資源和時間，其效率並不理想。隨著測量車的發展，其可快速獲取大量具定位資訊的影像序列，若能利用此特性來進行交通路標資訊的收集，將可提高其資料收集的效率。
在測量車進行空間影像序列收集時，常常會受到很多周邊環境因素的影響，例如影像拍攝時，成像光源不足導致影像明亮度過低及對比度不足，還有就是路標周邊的背景的顏色跟路標的顏色相似，讓交通路標被背景所混淆或路標與背景相連，這些原因都會造成路標偵測和路標辨識的困難和失敗。因此，本研究利用調整路標偵測罩窗的方法，改變罩窗的尺寸來偵測被混淆的路標，另外還有利用直方圖等化的方法來降低成像光源不足的問題。
本研究利用兩組品質不同的影像序列進行測試，從實驗成果顯示，對於品質較好的仿測量車影像，本研究所提出的方法，在路標偵測和路標辨識精度上都能達到88%以上，而整體也有84%，效果相當理想。
而另一組影像是本系所研發的測量車所拍的影像序列，偵測和辨識也能有80%以上的精度，而整體精度雖然稍為低一點點，只有73%左右，但在測試影像所拍到的真實世界上的路標中，有將近90%的真實路標有在影像上被偵測出來，並且辦識正確。
從以上實驗顯示，本研究所提出的方法能有效地偵測及辨識出大部份現實空間中的路標。若從辨識到的路標中，找出各對應的共軛路標影像，再導入測量車的定位資訊，就能把交通路標的位置定位出來。

Traffic signs play an important role in our daily life. If the spatial information of traffic signs are collected and managed, it will give a great benefit to the department of urban planning or car navigation system. In the past, the method to collect traffic signs is site investigation. However it is inefficient and labor-intensive because the large number of signs. With the development of Mobile Mapping System(MMS) which can obtain the image sequences with location information, the collection of traffic signs expected to be done more efficiently by using MMS.
The quality of sequence images for sign recognition suffers from many environment factors. For example, the brightness, the contrast, the homogeneity of colors between traffic signs and non-traffic signs. These factors will cause the sign detection and recognition very difficult. For this reason, in this research, we ease the difficulties by adjusting the scale of the constraint windows to detect the signs and, using histogram equalization to improve the brightness and contrast of the image sequences.
Two image sequence data with different quality are used for testing. The first image sequence is captured to simulate the MMS image and the quality is better than the real MMS image sequence. By applying our developed recognition method on the sequence, the accuracy of signs detection and recognition both can be higher than 88%. The overall accuracy is 84%.
The other image sequences are the real MMS images, the accuracy of sign detection and recognition also approaches higher than 80%. The accuracy of the object base can achieve 89%, although the overall accuracy of the image base is just 72%.
From the results, the most traffic signs in the real world can be detected and recognized. Once the location of traffic sign is known, the position of the traffic signs in the real world can be acquired by applying forward intersection on the stereo images.

沈育賢，2007。道路交通標誌之偵測與辨識，碩士論文，國立台灣科技大學，台北

李荏毓，2009。應用移動式圖系統影像序列萃取三維道路邊線及分隔線，碩士論文，國立成功大學，台南

柯奕仲，2008。光學衛星影像於海洋異常物偵測之研究，碩士論文，國立中央大學，中壢

高銘儀，2003。應用3D區域成長法於腦部磁共振影像之分割，碩士論文，國立中央大學，中壢

鄭邦寧，2006。使用空載光達點雲求定數值地表高程模型之小波法，碩士論文，國立成功大學，台南

Coetsee, J., Brown, A. and Bossler, J., 1994. GIS data collection using the GPSVan supported by a GPS/inertial mapping system. Proceedings of IONGPS-94 7th International Technical Meeting of the Satellite Division of the Institute of Navigation, Salt Lake City, Utah. Part 1: 85–93

Douville, P., 2000. Real-Time Classification of Traffic Signs, Real-Time Imaging, 6(3):185-193

De La Escalera, A., Armingol, J.M. and Mata, M., 2003. Traffic sign recognition and analysis for intelligent vehicles, Image and Vision Computing, 21(3): 247–258.
Estable, S., Schick, J., et al., 1994. A real-time traffic sign recognition system, Proceedings of Intelligent Vehicles’94 Symposium

Fang, C.Y., Chen, S.W., and Fuh, C.S., 2003. Road-sign detection and tracking, IEEE Trans Vehicular Technol , 52(5):1329–1341.

Foley, J.D., Dam, A.V., Feiner, S.K. and Hughes, J.F., 1993. Computer Graphics : Principles and Practic. USA.

Gontran, H., Skaloud, J. and Gillieron, P.Y., 2004. Photobus : towards real-time mobile mapping, Proc. XXth Int. Society for Photogrammetry and Remote Sensing (ISPRS) Congress, 7-12.

Gonzalez, R.C. and Woods, R.E., 2001. Digital Image Processing (2nd ed.). New Jersey : Prentice Hall.

Hsu, S.H. and Huang, C.L., 2001. Road sign detection and recognition using matching pursuit method, Image and Vision Computing, 19(3):119-129.

Kehtarnavaz, N., Griswold, N.C. and Kang, D.S., 1993. Stop-sign recognition based on color/shape processing, Machine Vision and Applications, 6(4):206-208.

Kehtarnavaz, N. and Ahmad, A., 1995. Traffic sign recognition in noisy outdoor scenes, Proc. Intelligent Vehicles ’95 Symposium, 460-165.

Kim, E., Haseyama, M., Kitajima, H., 2002. Fast and robust ellipse extraction from complicated images, Proceedings of the IEEE International Conference on Information Technology and Applications

Lapucha, D., 1990. Precise GPS/INS Positioning for Highway Inventory System. M.Sc Thesis, Department of Geomatics Engineering, The University of Calgary, Calgary, Canada

Li, R.Y., 2009. Extraction of 3D Road Boundaries and Dividing Lines Using MMS Image Sequences

Liu, Y.S., Duh, D.J., et al., 2007. Scale and skew-invariant road sign recognition, International Journal of Imaging Systems and Technology, 17(1):28-39.

Miura, J., Kanda, T. and Shirai, Y., 2000. An active vision system for real-time traffic sign recognition, Proc. of IEEE Intelligent Transportation Systems Conference, 52-57.

Muerle, J.L. and Allen, D.C., 1968. Experimental evaluation of techniques for automatic segmentation of objects in a complex scene, In Piclorial Pattern Recognition, 3-13.

Paclik, P., Novovicova, J., Pudil, P. and Somol, P., 2000. Road sign classification using Laplace kernel classifier, Pattern Recognition Letters, 21:1165-1173.

Piccioli, G., De Micheli, E., Parodi, P. and Campani, M., 1996. Roubust method for road sign detection and recognition, Image and Vision Computing, 14(3):209-223.
Prieto. M.S. and Allen. A.R., 2009. Using self-organising maps in the detection and recognition of road signs, Image and Vision Computing, 27(6):673-683.

Ritter, W., Stein, F. and Janssen, R., 1995. Traffic sign recognition using colour information, Mathematical and Computer Modelling, 22(4-7):149-161.

Saturnino, M.B., Sergio, L.A., et al., 2007. Road-sign detection and recognition based on support vector machines, IEEE Transactions on Intelligent Transportation Systems, 8(2):264-278.

Schwarz, K. P., Martell, H. E., El-Sheimy, N., Li, R., Chapman, M.A. and Cosandier, D., 1993. VIASAT - A mobile highway survey system of high accuracy, Proceesing of IEEE Vehicle Navigation and Information System Conference'93, 476-481.

Shadeed, W.G., Abu-Al-Nadi, D.I. and Mismar, M.J., 2003. Road traffic sign detection in color images, Proc. IEEE Electron Circuits System, 890-893.

Tsai, Y.H., Hu, Z.H. and Alberti, C., 2010. Detection of Roadway Sign Condition Changes Using Multi-scale Sign Image Matching (M-SIM), Photogrammetric Engineering and Remote Sensing, 76(4): 391-405.
Vitabile, S., Gentile, A. and Sorbello, F., 2002. A neural network based automatic road signs recognizer, Proc IEEE Neural Networks, 2315-2320.

Zucker, S.W., 1976. Survey Region Growing: Childhood and Adolescence, Computer Graphics and Image Processing, 5:382-399