臺灣博碩士論文加值系統

台灣汽車數量龐大，伴隨著每年會有數百萬張交通違規的罰單，其中又以『超速』的違規數量最多，如此龐大的數目都是以人工的方式來辨識超速車輛的車牌號碼，需要大量的人力。由於影像辨識的技術不斷在進步，目前有許多利用攝影機與電腦取代人工判讀的應用，其中車牌辨識就是一個積極在發展的項目。本研究的目的是利用影像辨識的技術發展一套車速偵測、車牌定位與字元分割的系統；我們以固定式攝影機的方式拍攝行駛中的車輛，利用串流影像時間的關聯性計算出車速，針對超速的車輛再進行車牌定位與字元分割。經由大量的實驗測試本研究之方法，得知，車速之計算其誤差小於 4km/h，車牌定位之準確度達 95%而字元分割結果之正確率約為 96%。

In Taiwan, there are a large amount of cars in this small island, and also it comes millions of tickets because of exceeding the speed limit. Until now, the license plate is
recognized manually; it costs a lot of time and manpower. License plate recognition is a powerful method that uses optical character recognition to read the characters of the plate on the car. The purpose of our research is to develop a system that can detect the speed of vehicle. If the vehicle speed exceeds the limit, then the license plate of the car will be located and the characters of the plate are also segmented. Lots of images on the streets were used to verify the proposed methods. It was found that the error of the vehicle speed calculation is less than 4km/h. License plates were locates with a correction rate of 95% and the correction rate of character segmentation is about 96%.

口試委員審定書 I
誌謝 II
摘要 III
ABSTRACT IV
論文目錄 V
圖目錄 VII
表目錄 IX
第一章、緒論 1
1.1 研究動機與目的 1
1.2 相關研究 3
1.3 論文架構 6
第二章、系統架構 7
2.1 裝備設置 7
2.2 攝影機規格 8
2.3 攝影機內部參數校正 9
2.4 攝影機外部參數校正 10
2.5 系統流程 12
2.5.1 讀取影像 13
2.5.2 建立背景 14
2.5.3 背景更新 16
2.5.4 車速計算 16
2.5.5 車牌定位及字元分割 17
第三章、背景建立及車速計算 18
3.1 背景建立與更新 18
3.1.1 背景建立 18
3.1.2 背景更新 21
3.2 車輛偵測與車速計算 23
3.2.1 動態閥值 23
3.2.2 車輛偵測 24
3.2.3 車速計算 25

第四章、車牌定位及字元分割 28
4.1 車牌定位 28
4.2 字元分割 32
4.2.1 刪除上下雜訊 32
4.2.2 刪除左右雜訊 34
4.2.3 尋找破折號位置 36
4.2.4 字元切割 39
4.2.5 刪除螺絲孔雜訊 41
第五章、實驗結果與討論 43
5.1 背景更新結果 43
5.2 車速偵測結果 46
5.3 車牌定位結果 52
5.4 字元分割結果 54
5.5 實驗結果 55
第六章、結論與未來方向 56
參考文獻 58

[1]內政部警政署, http://www.npa.gov.tw/ .
[2]Bihai Hong and Chenhui Yang, “An Approach to License Plate Locating in Intelligent Transportation System,” Pervasive Computing and Applications, ICPCA’07, pp.319 - 322, 2007.
[3]Faradji, F., Rezaie, A.H. and Ziaratban, M., “A Morphological-Based License Plate Location,” Image Processing, ICIP’07, vol.1, pp.I-57 - I-60, 2007.
[4]Anagnostopoulos, C.N.E., Anagnostopoulos, I.E., Loumos, V. and Kayafas, E., “A License Plate-Recognition Algorithm forIntelligent Transportation System Applications,” IEEE Transactions on Intelligent Transportation Systems, vol.7, No.3, pp.377 - 392, 2006.
[5]林家緯, ”以統計數據為基礎的車牌影像處理與辨識方法,” 國立中山大學機械與機電工程學系碩士論文, 2006.
[6]Ondrej Martinsky, “Algorithmic and mathematical principles of automatic number plate recognition systems,” Brno University of Technology, B.SC. Thesis, 2007.
[7]Shigueo Nomura, KeijiYamanakab, Osamu Kataia, Hiroshi Kawakamia and Takayuki Shiose, “A novel adaptive morphological approach for degraded character image segmentation,” Pattern Recognition, vol.38, pp.1961 - 1975, 2005.
[8]Huei-Yung Lin, “Vehicle Speed Detection and Identication from a Single Motion Blurred Image,” Application of Computer Vision, vol.1, pp.461 - 467, 2005.
[9]Yucheng Li, Liang Yin, Yan Jia and Mushu Wang, “Vehicle Speed Measurement Based on Video Images,” Innovative Computing Information and Control, ICICIC’08, pp. 439 - 439, 2008.
[10]He Zhiwei, Liu Yuanyuan and Ye Xueyi, “Models of Vehicle Speeds Measurement with a Single Camera,” Computational Intelligence and Security Workshops, CISW’07, pp. 283 - 286, 2007.
[11]Hsi-Jian Lee, Si-Yuan Chen and Shen-Zheng Wang, “Extraction and Recognition of License Plates of Motorcycles and Vehicles on Highways,” Pattern Recognition, ICPR’04, vol.4, pp.356 – 359, 2004.
[12]Feng Yang and Zheng Ma, “Vehicle License Plate location Based on Histogramming and Mathematical Morphology,” Automatic Identification Advanced Technologies, pp. 89 - 94, 2005.
[13]Guangmin Sun, Gang Li, Lei Xu and Jing Wang, “A New Method of Vehicle License Plate Location Based on Mathematical Morphology and Texture Characteristics,” Industrial Electronics and Applications, ICIEA’08, pp.985 - 988, 2008.
[14]Feng Yang, Zheng Ma and Mei Xie, “A Novel Approach for License Plate Character Segmentation,“ Industrial Electronics and Applications, pp.1 - 6, 2006.
[15]Zhang Jian, Fan Xiaoping and Huang Cailun, “Research on Characters Segmentation and Characters Recognition in Intelligent License Plate Recognition System,” Chinese Control Conference, CCC’06, pp.1753 - 1755, 2006.
[16]Feng Yang, Zheng Ma and Mei Xie, “A Robust Character Segmentation Approach for License Plate,” Communications, Circuits and Systems, ICCCAS’07, pp.679 - 683, 2007.
[17]Xianchao Zhang, Xinyue Liu and He Jiang, “A Hybrid Approach to License Plate Segmentation under Complex Conditions,” Natural Computation, ICNC’07, pp.68 - 73, 2007.
[18]Yungang Zhang and Changshui Zhang, “A New Algorithm for Character Segmentation,” Intelligent Vehicles Symposium, pp.106 - 109, 2003.
[19]Byeong Rae Lee, Kyungsoo Park, Hyunchul Kang, Haksoo Kim and Chungkyue Kim, “Adaptive Local Binarization Method for Recognition of Vehicle License Plates,” Combinatorial Image Analysis, pp.646 - 655, 2005.
[20]Anagnostopoulos, C.-N. E., Anagnostopoulos, I. E., Psoroulas, I. D., Loumos, V. and Kayafas, E., “License Plate Recognition From Still Images and Video Sequences: A Survey,” Intelligent Transportation Systems, vol.9, No.3, pp.377 - 391, 2008.
[21]Yilin Yang, Chenhui Yang and Xiaohui Wang, “A Detection and Tracing Algorithm of Moving Vehicles,” Pervasive Computing and Applications, ICPCA’07, pp.447 - 450, 2007.
[22]Iwasaki, Y. and Kurogi, Y., “Real-time robust vehicle detection through the same algorithm both day and night,” Wavelet Analysis and Pattern Recognition, ICWAPR''07, vol.3, pp.1008 - 1014, 2007.
[23]莊佳龍, “車輛偵測與車牌辨識系統,” 國立中正大學機電光整合工程學系碩士論文, 2005.
[24]陳翔傑, “自動化車牌辨識系統設計,” 國立中央大學電機工程研究所碩士論文, 2005.
[25]林泰良, “智慧型車牌定位與字串分割,” 國立台灣大學電機工程學研究所碩士論文, 2000.
[26]黃莫凱, “全方位智慧型車輛-前車追撞及車道偏離警示系統,” 國立台灣大學工程科學及海洋工程學研究所碩士論文, 2006.