臺灣博碩士論文加值系統

本論文主要基於視覺與影像，提出一個結合動態車牌辨識之智慧路拱系統設計，並以一個跨領域的系統應用，在交通車輛管理上有進一步的創新應用與研究想法。我們將路拱透過模組化的設計結合至車牌辨識系統，來完成可行性製作。
影像處理方面，包括獲取影像來源、車牌定位、字元切割、字元辨識。在獲取影像來源使用固定式拍攝連續影像；在車牌定位提出一個自適應追蹤車牌的方法，在字元切割提出一個字元修補和自適應字元標記的方法；在字元辨識利用Tesseract-OCR 的軟體工具重新訓練樣本及建立字元模板，依匹配的辨識結果之可信程度，設置一個得分標準，依據得分最高的字元來輸出辨識結果。硬體控制方面，我們影像演算法整合至嵌入式板上，並透過程式撰寫判斷路拱的升降條件，完成整個系統的可行性製作。

This thesis presents an intelligent speed bump system incorporated with the dynamic license plate recognition technique. It is able to decide the enforcement of speed bump based on the vehicle speed and identification. As a part of intelligent transportation systems to provide the traffic flow control, the proposed technique makes the driving safer and more comfortable.
In the dynamic license plate recognition stage, the adaptive tracking is carried out for license plate allocation, followed by character segmentation and identification. ”Tesseract OCR” is then used to construct sample images and perform the recognition task. The experiments are carried out on a prototype system with embedded computation to demonstrate the feasibility of this work.

摘要 i
ABSTRACT ii
誌謝 iii
圖目錄 ix
表目錄 x
中英文字對照 xi

第1章 緒論 1
1.1 前言 1
1.2 研究動機與背景應用 2
1.2.1 減速路拱 3
1.2.2 車牌辨識 4
1.2.3 研究限制 4
1.3 論文架構 6
第2章 智慧系統實施說明與相關研究 7
2.1 影像取得與系統環境設置 7
2.2 系統整合概要 10
2.3 相關研究方法 12
2.3.1 路拱相關文獻 12
2.3.2 影像辨識相關文獻 14
2.3.3 主要貢獻 16
第3章 動態車輛辨識系統 17
3.1 影像辨識方法流程概述 18
3.2 車輛偵測與車牌定位 21
3.2.1 影像序列車輛偵測 21
3.2.2 車牌定位前處理與方法應用 23
3.2.3 自適應車牌定位 29
3.3 字元切割與辨識策略 30
3.3.1 適應性二值化影像 31
3.3.2 字元切割與連通成分 33
3.3.3 修補候選連通區域 34
3.3.4 自適應字元標記 35
3.3.5 字元辨識方法應用 36
3.4 系統維護與處理機制 39
3.4.1 演算法與限制條件 39
3.4.2 先驗知識 41
第4章 實驗結果與分析 42
4.1 實驗設備 42
4.2 影像辨識實驗結果 45
4.2.1 辨識結果與分析 45
4.2.2 車牌辨識系統成功率 50
4.3 智慧型系統實作成果 51
4.3.1 模擬平台環境 51
4.3.2 嵌入式板實作成果 53
5 結論與未來展望 58
參考文獻 60

[1] “智能减速路拱”, Feb. 2 2011, CN Patent App. CN 201,010,261,228.
[2] W.H. Blair, D.R. Blair, and R.E. Steele, “Portable speed bump,” Sept. 23 2003, US Patent 6,623,206.
[3] C.-N. E. Anagnostopoulos, I. E. Anagnostopoulos, I. D. Psoroulas, V. Loumos, and E. Kayafas, “License plate recognition from still images and video sequences: A survey," IEEE Transactions on Intel ligent Transportation Systems, vol. 9, no. 3, pp. 377–391, 2008.
[4] P. Blythe, “Rfid for road tolling, road-use pricing and vehicle access control,” IEE Colloquium on RFID Technology, pp. 8/1–8/16, 1999.
[5] J. Gajda, R. Sroka, M. Stencel, A.Wajda, and T. Zeglen, “A vehicle classification based on inductive loop detectors,” IEEE Conference Instrumentation and Measurement Technology Conference, 2001, vol. 1, pp. 460–464.
[6] Qiu J, Sun B, and You Q, “Study on rfid antenna for railway vehicle identification,” IEEE International Conference on ITS Telecommunications Proceedings, 2006, pp. 237–240.
[7] I.R. Urazghildiiev, R Ragnarsson, K Wallin, A Rydberg, P Ridderström, and E Ojefors, “A vehicle classification system based on microwave radar measurement of height profiles,” Proceedings of the RADAR Conference, 2002, pp.409–413.
[8] “震動柔和的道路减速路拱”, Sept. 22 2010, CN Patent App. CN 201,010,156,705.
[9] “基於激勵與约束機制的交通管理與减速路拱装置”, Mar. 19 2014, CN Patent 102,561,225.
[10] J.L. Welford, “Electronically controlled speed bump device,” Dec. 7 1993, US Patent 5,267,808.
[11] “道路减速路拱液壓缓衝装置”, Sept. 28 2011, CN Patent 201,990,962.
[12] “機械結構的减速路拱”, Oct. 13 2010, CN Patent 101,597,891.
[13] O.A. Breazeale, G.M. Lee, and C.J. Cole, “Retractable speed bump,” Mar. 14 2006, US Patent 7,011,470.
[14] G. Geminiani, “Recessed speed reducing system for street traffic,” Nov. 26 2008, EP Patent App. EP20,080,103,749.
[15] “自動升降式减速路拱”, May 2 2007, CN Patent App. CN 200,510,114,553.
[16] C.N.E. Anagnostopoulos, I.E. Anagnostopoulos, V. Loumos, and E. Kayafas, “A license plate-recognition algorithm for intelligent transportation system applications,” IEEE Transactions on Intel ligent Transportation Systems, vol. 7, no. 3, pp. 377–392, 2006.
[17] Ming G.He, A.L. Harvey, and T. Vinay, “Hough transform in car number plate skew detection,” IEEE International Symposium on Signal Processing and Its Applications, 1996, vol. 2, pp. 593–596.
[18] K. Zheng, Y. Zhao, J. Gu, and Q. Hu, “License plate detection using haar-like features and histogram of oriented gradients,” IEEE International Symposium on Industrial Electronics, 2012, pp. 1502–1505.
[19] R. Zunino and S. Rovetta, “Vector quantization for license-plate location and image coding,” IEEE Transactions on Industrial Electronics, vol. 47, no. 1, pp. 159–167, 2000.
[20] Jiun-Chang Hsu, G and Y.-Z. Chung, “Application-oriented license plate recognition,” IEEE Transactions on Vehicular Technology, vol. 62, no. 2, pp. 552–561, 2013.
[21] D. L. Baggio, Mastering OpenCV with practical computer vision projects, Packt Publishing Ltd, 2012.
[22] Y.-P. Huang, S.-Y. Lai, and W.-P. Chuang, “A template-based model for license plate recognition,” IEEE International Conference on Networking, Sensing and Control, 2004, vol. 2, pp. 737–742.
[23] T. Kohonen, “The self-organizing map,” Proceedings of the IEEE, vol. 21, no. 1, pp. 1–6, 1998.
[24] J.A.G. Nijhuis, M.H. ter Brugge, K.A. Helmholt, J.P.W. Pluim, L. Spaanenburg, R.S. Venema, and M.A. Westenberg, “Car license plate recognition with neural networks and fuzzy logic,” IEEE International Conference on Neural Networks, 1995, vol. 5, pp. 2232–2236.
[25] 張斐章, 張麗秋, 黃浩倫, et al., 類神經網路, 東華書局, 民國九十四年.
[26] L. Wang, W. Fan, Y. He, J. Sun, Y. Katsuyama, and Y. Hotta, “Fast and accurate text detection in natural scene images with user-intention,” IEEE International Conference on Pattern Recognition, 2014, pp. 2920–2925.
[27] L. Sun, Q. Huo, W. Jia, and K. Chen, “Robust text detection in natural scene images by generalized color-enhanced contrasting extremal region and neural networks,” IEEE International Conference on Pattern Recognition, 2014, pp. 2715–2720.
[28] J. Du, Q. Huo, L. Sun, and J. Sun, “Snap and translate using windows phone,” IEEE International Conference on Document Analysis and Recognition, 2011, pp. 809–813.
[29] R. Smith, “An overview of the tesseract ocr engine,” IEEE International Conference on Document Analysis and Recognition, 2007, pp. 629–633.
[30] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time tracking of non-rigid objects using mean shift,” IEEE Conference on Computer Vision and Pattern Recognition, 2000, vol. 2, pp. 142–149.
[31] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[32] J. Sauvola and M. Pietikäinen, “Adaptive document image binarization,” IEEE International Conference on Pattern Recognition, vol. 33, no. 2, pp. 225–236, 2000.
[33] “Tesseract ocr engine”, http://code.google.com/p/tesseract-ocr/.