簡易檢索 / 詳目顯示

回結果列表
研究生： 許溥鑫
論文名稱： 在日夜間環境下的汽機車車牌定位系統
A License Plate Location System for Cars and Motorcycles under Day and Night Condition
指導教授： 葉榮木
Yeh, Zong-Mu
蔡俊明
Tsai, Chun-Ming
學位類別： 碩士
Master
系所名稱： 機電工程學系
Department of Mechatronic Engineering
論文出版年： 2007
畢業學年度： 95
語文別： 中文
論文頁數： 81
中文關鍵詞： 影像增強 、形態梯度 、二值化 、車牌定位
英文關鍵詞： Image Enhancement, Morphology Gradient, Binarization, Location of License Plate
論文種類： 學術論文
相關次數： 點閱：271  下載：15 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 交通工具數量的激增是現代化國家均有的問題之ㄧ，在台灣這地窄人稠的地方，更突顯出此問題的嚴重性。根據國際道路聯盟所做的統計，在台灣平均每戶家庭小客車數有0.77台為亞洲之冠，其中平均每79.81輛車就有1台發生事故，完全反映了交通工具數量增加所造成的交通問題。在警察數量遠不及車輛數目的今日，如何對交通工具做更有效的管理是刻不容緩的問題。
    現今之車牌定位系統，大多以白天且有夠多亮度的影像進行定位，對於亮度不均勻（包含黃昏或夜晚）之影像卻沒有進行車牌定位研究。因此，本文利用自動化影像處理，針對不同亮度下（包含日、夜間）的汽、機車影像，進行車牌定位。本文首先提出利用平均亮度值來區分白天與夜間的車牌偵測之演算法，再利用高增幅濾波器（High Boost Filter）來增強影像對比，接著，利用形態梯度（Morphology Gradient）運算子去偵測車牌區域，接著，利用平均亮度值乘上固定常數作為二值化閥值，進行影像二值化，再利用車牌外觀特性完成車牌初步定位。
    本文主要針對兩車道之影像進行車牌定位，同時考量車牌解析度過低的問題，故使用640×480 pixel之影像。在白天部分，汽車車牌定位成功率為96.2％，機車車牌定位成功率為95.4％，在夜間部份，汽車車牌定位成功率為88.5，機車車牌定位成功率為75.7％。白天車牌定位總成功率為95.9%，速度為0.25sec，夜間車牌定位總成功率為83% ，速度為0.36sec。

    The increasing amount of vehicles is one of the common problems for most developed countries, and it is more critical for Taiwan which the population density is higher than lots of countries. According to the International Road Federation(IRF) census in 2005, in Taiwan, every family has 0.77 car in average, and there is a car got accident in every 79.81 cars. The above data totally reflect the problems made by the increasing numbers of vehicles. For nowadays the number of police far less than the vehicle, how to effectively manage the vehicle is an urgent issue.
    Today, most license plate location systems are applied for daytime image, which has enough brightness. However, they can’t be applied for dark and nighttime images. In this paper, we proposed a algorithm to locate license plate of cars and motorcycles under day and night conditions. At first, we calculated the value of average brightness of picture to distinguish day and night. After intensifying the picture contrast by a high boost filter, we apply the morphology gradient for detecting the plate candidate. Furthermore, we multiplied a constant to the average brightness value of images to be the threshold to image binarization, and checked the characteristic of plate appearance and calculated the three horizontal lines crossings to extract the correct plate position.
    The experiment results show that the average extraction rate and speed are 95.9%, 0.25sec at daytime and 83%, 0.36sec at nighttime. We believe the proposed method would be a robust license plate extraction system utilized in all day.

    摘要.............................................................................................................Ⅰ Abstract.......................................................................................................Ⅱ 目錄.............................................................................................................Ⅲ 圖目錄.........................................................................................................Ⅴ 表目錄.........................................................................................................Ⅷ 第一章 緒論.................................................................................................1 1-1 前言....................................................................................................1 1-2 研究動機............................................................................................2 1-3 研究目的............................................................................................3 1-4 研究目標............................................................................................6 1-5 系統架構............................................................................................7 1-6 研究流程............................................................................................9 1-7 論文大綱..........................................................................................10 第二章 文獻探討.......................................................................................11 2-1 基本影像處理原理..........................................................................11 2-2 車牌定位方法..................................................................................20 2-3 車牌定位方法分析..........................................................................26 第三章 車牌定位......................................................................................37 3-1 車牌影像定位的難題......................................................................37 3-2 車牌定位系統架構..........................................................................38 3-3 前處理..............................................................................................40 3-4 日間車牌偵測演算法......................................................................43 3-5 夜間車牌偵測演算法......................................................................54 3-6 車牌定位..........................................................................................63 第四章 實驗結果與分析...........................................................................69 4-1 實驗環境與設備..............................................................................69 4-2 實驗結果比較與分析......................................................................70 第五章 結論與建議...................................................................................76 5-1 結論..................................................................................................76 5-2 未來目標..........................................................................................77 圖 目 錄 圖1.1 實際查緝畫面[30].............................................................................4 圖1.2 利用基因演算法偵測的連續拍攝圖[22].........................................4 圖1.3 具汽機車車牌之後照式取像...........................................................5 圖1.4 車牌定位流程圖...............................................................................7 圖2.1 摺合演算法示意圖..........................................................................11 圖2.2 High Boost Filter原理示意圖..........................................................12 圖2.3 形態學遮罩示意圖.........................................................................16 圖2.4 形態學膨脹及侵蝕示意圖.............................................................16 圖2.5 形態學運作模擬圖.........................................................................17 圖2.6 利用AIM擷取車牌區域.................................................................27 圖2.7 利用影像差值與基因法則及色彩學擷取車牌區域.....................28 圖2.8 利用字元反差與梯度特性擷取車牌區域.....................................29 圖2.9 利用小波與邊緣特徵擷取車牌區域.............................................30 圖2.10 利用字元與車牌寬高度擷取車牌區域.......................................32 圖2.11 利用梯度與形態學擷取車牌區域................................................33 圖2.12 利用中值濾波器與形態梯度擷取車牌區域...............................34 圖2.13 利用BottomHat與形態梯度擷取車牌區域.................................35 圖3.1 車牌定位系統架構流程圖.............................................................39 圖3.2 白天平均亮度統計圖.....................................................................41 圖3.3 夜間平均亮度統計圖.....................................................................42 圖3.4 日間演算法架構流程圖.................................................................43 圖3.5 原圖灰階影像經High Boost Filter.................................................44 圖3.6 經形態梯度及相減後之影像.........................................................46 圖3.7 經過二值化的影像.........................................................................47 圖3.8 經Otsu與本文的二值化比較圖.....................................................48 圖3.9 車輛標誌與車牌相連的處理.........................................................49 圖3.10 經過開運算後的影像...................................................................50 圖3.11 經過Dilation後的影像..................................................................51 圖3.12 經過Labeling後可框出車牌候選區............................................53 圖3.13 夜間演算法架構流程圖...............................................................54 圖3.14 亮度分佈均勻經HE及BBHE處理的比較圖...........................56 圖3.15 亮度分佈不均勻經HE及BBHE處理的比較圖.......................57 圖3.16 灰階影像與RGB影像經過BBHE之差異圖............................59 圖3.17 夜間影像經日間演算法後的影像...............................................61 圖3.18 綜合日、夜間演算法候選區後的影像.......................................62 圖3.19 前處理架構流程圖.......................................................................63 圖3.20 像素模擬示意圖...........................................................................65 圖3.21 車牌交越量示意圖.....................................................................67 圖4.1 拍攝距離示意圖...........................................................................69 圖4.2 車牌定位成功示意圖...................................................................74 圖4.3 車牌定位失敗示意圖...................................................................75 表 目 錄 表3.1 現行車牌規格.................................................................................52 表3.2 各種二值化後的比較圖.................................................................66 表4.1 在日、夜間對汽車車牌定位比較...................................................70 表4.2 在日、夜間對機車車牌定位比較...................................................71 表4.3 本文與各文獻的比較.....................................................................72

    [1]J. Kong, X. Liu, Y. Lu, and X. Zhou, “A Novel License Plate Localization Method Based On Textural Feature Analysis”, International Symposium on Signal Processing and Information Technology of IEEE, pp. 275-279, 2005.
    [2]H. Zhang, W. Jia, X. He, and Q. Wu. “Learning-Based License Plate Detection Using Global and Local Features”, The 18th International Conference on Pattern Recognition of IEEE, 2006.
    [3]Y. P. Huang, S. Y. Lai, and W. P. Chuang, “A Template-Based Model for License Plate Recognition”, International Conference on Networking, Sensing & Control of IEEE Proceedings, pp. 737-742, 2004.
    [4]H. S. Song and G. Q. Wang, “The High Performance Car License Plate Recognition System and Its Core Techniques”, International Conference on Vehicular Electronics and Safety of IEEE, 2005.
    [5]P. Dubey, “Heuristic Approach for License Plate Detection”, in Proc. Advanced Video and Signal Based Surveillance of IEEE, pp. 366-370, 2005.
    [6]C. Anagnostopoulos, T. Alexandropoulos, S. Boutas, V. Loumos, and E. Kayafas, “A Template-guided Approach to Vehicle Surveillance and Access Control”, in Proc. Advanced Video and Signal Based Surveillance of IEEE, pp.534-539, 2005.
    [7]M. Yu and Y. D. Kim, “An Approach to Korean License Plate Recognition Based on Vertical Edge Matching”, in Proc. International Conference on Systems, Man, and Cybernetics of IEEE, pp.2975-2980, 2000.
    [8]M. Sarfraz, M. J. Ahmed, and S. A. Ghazi, “Saudi Arabian License Plate Recognition System”, in Proc. of the 2003 International Conference on Geometric Modeling and Graphics of IEEE, pp.36-41, 2003.
    [9]V. S. L. Nathan, R. J., and K. P. S., “New Approach for License Plate Recognition System”, Intelligent Sensing and Information Processing of IEEE, pp.149-152, 2004.
    [10]D. Zheng, Y. Zhao, J. Wang, “An Efficient Method of License Plate Location”, Pattern Recognition Letters of IEEE , v26, pp. 2431-2438, 2005.
    [11]Rafacel C. Gonzalez, Richard E. Woods, “Digital Image Processing, 2/E” ,Prentice Hall, 2001.
    [12]Y. Yanamura, M. Goto, D. Nishiyama, M. Soga, H. Nakatani, H. Saji, “Extraction and Tracking of the License Plate Using Hough Transform and Voted Block Matching”, Intelligent Vehicles Symposium of IEEE, pp. 243-246,2003.
    [13]Y. Yohimori, Y. Mitsukura, M. Fukumi, N. Akamatsu, and W. Pedrycz, “License Plate Detection System by Using Threshold Fuction and Improved Template Matching Method”, Fuzzy Information of IEEE, pp. 357-362, 2004.
    [14]S.Y. Chen, H. J. Lee, “Extraction and Recognition of License Plates of Motorcycles on Highways”, Pattern Recognition, ICPR of IEEE, pp.356-359, 2004.
    [15]Feng Yang, Zheng Ma “Vehicle License Plate location Based on Histogramming and Mathematical Morphology”, in Proc. Automatic Identification Advanced Technologies of IEEE, pp.89-94, 2005.
    [16]D.S. Gao, J. Zhou, “Car License Plates Detection from Complex Scene”, in Proc. International Conference on Signal Processing WCCC-ICSP of IEEE, pp. 1409-1414 vol.2, 2000.
    [17]J.W. Hsieh, S. H. Yu, and Y. S. Chen, “Morphology-based License Plate Detection from Complex Scene”, in Proc. International Conference on Pattern Recognition of IEEE, pp. 176-179, 2002.
    [18]H. L. Bai, C. P. Liu, “A Hybrid License Plate Extraction Method Based on Edge Statistics and Morphology”, in Proc. of the 17th International Conference on Pattern Recognition of IEEE, pp. 831-834,2004.
    [19]P. V. Suryanarayana, S. K. Mitra, A. Banerjee, and A. K. Roy, “A Morphology Based Approach for Car License Plate Extraction”, in Proc. INDICON of IEEE, pp.24-27, 2005.
    [20]Hsien-Huang P. Wu,Hung-Hsiang Chen,Ruei-Jan Wu,Day-Fann Shen, “License Plate Extraction in Low Resolution Video”, in Proc. of the 18th International Conference on Pattern Recognition of IEEE , pp.824-827, 2006.
    [21]Cheokman Wu, Lei Chan On, Chan Hon Weng, Tong Sio Kuan, Kengchung Ng, “A Macao License Plate Recognition System”, in Proc. International Conference on Machine Learning and Cybernetics of IEEE, pp.4506-4510, 2005.
    [22]S. Yoshimori, Y. Mitsukura, M. Fukumi, N. Akamatsu, and R. Khosal, “License Plate Detection System in Rainy Day”, in Proc. International Symposium on Computational Intelligence in Robotic and Automation of IEEE, pp.972-976, 2003.
    [23]H. K. Xu, F. H. Yu, J. H. Jiao, and H. S. Song, “A New Approach of The Vehicle License Plate Location”, in Proc. of the 6th International Conference on Parallel and Distributed Computing, Applications and Technologies, IEEE, 2005.
    [24]W. G. Zhu, G. J. Hou, and X. Jia, “A Study of Locating Vehicle License Plate Based on Color Feature and Mathematical Morphology”, in Proc. of the 6th International Conference on Signal Processing , IEEE, pp.748-751, 2002.
    [25]S. Kim, D. Kim, Y. Ryu, and G Kim, “A Robust License-Plate Extraction Method under Complex Image Condition”, in Proc. of the 16th International Conference on Pattern Recognition, IEEE, pp.-216-219, 2002.
    [26]M. I. Chacon M., A. Zimmerman S., “License Plate Location Based on a Dynamic PCNN Scheme”, in Proc. of the International Joint Conference on Neural Networks, IEEE, pp.1195-1200, 2003.
    [27]C. N. E. Anagnostopoulos, V. Loumos, “A License Plate-Recognition Algorithm for Intelligent Transportation System Applications”, Transactions on Intelligent Transportation System of IEEE, Vol. 7, No. 3, pp.377-392, 2006.
    [28]Ching-Tang Hsieh, Yu-Shan Juan , Kuo-Ming Hung, “Multipe License Plate Detection for Complex Background”, in Proc. Advanced information Networking and Applications of IEEE, pp.389-392, 2005.
    [29]交通部運輸研究所，智慧形運輸系統，http://www.iot.gov.tw/its/
    [30]陳志誠、黃景彰、陳英傑、林樹國， ”影像辨識技術應用於警政系統-以台北縣警察局「贓車自動辨識系統」為例”， 2000第四屆資訊管理學術暨警政資訊實務研討會， pp.177-p187，2000/5/12。
    [31]陳英傑、林樹國、陳志誠、黃景彰， ”建構贓車查緝網路以台北縣警察局為例”， 2001年第五屆資訊管理學術暨警政資訊實務研討會， pp.177-186，2001/6/1。
    [32]Yeong-Taeg Kim, “Contrast Enhancement Using Brightness Preserving Bi-Histogram Equalization” , in Proc. Transactions on Consumer Electronics of IEEE, pp.1-8, 1997.
    [33]Yu Wang, Qian Chen, Baomin Zhang, “Image Enhancement Based on Equal Area Dualistic Sub-Image Histogram Equalization Method”, in Proc. Transactions on Consumer Electronics of IEEE, pp.68-75, 1999.
    [34]Otsu N., “A Threshold Selection Method from Gray-Level Histograms”, in Proc. Trans. On System, Man, and Cybernetics of IEEE ,pp. 62-66, 1979.

    QR CODE