不同於汽車的車牌辨識系統，機車的車牌辨識系統相關的研究非常稀少，因此本論文為少數針對機車車牌辨識系統為目標所做的研究。研究初期比較了幾種常見的車牌偵測法包含Adaboost、Histograms of oriented gradients(HOG)、Gaussian mixture model(GMM)與投影法應用於一般場景時的車牌偵測效果，發現由於車牌偏斜、場景複雜、車牌周邊充斥各種檢驗貼紙、車行廣告與裝飾物等原因，直接使用以上車牌偵測法會有很多的錯誤偵測產生，因此我們加入車體偵測來去除複雜背景並縮小車牌偵測的處理範圍，提升系統處理速度，本論文主要探討不同角度的車體偵測、車牌偵測以及車牌字元的角度修正。我們比較了HOG、Adaboost、Deformable Part Model (DPM)等多種不同偵測法應用於複雜場景以及偵測不同角度目標物的效能，並結論出HOG結合Support Vector Machine(SVM)為最適合應用於即時機車車體與車牌偵測的偵測法，其訓練的方式與參數設置也將於實驗章節一併介紹。字元角度修正是利用改良的適應性Maximally stable extremal regions(MSER)針對每一張車牌影像設置其最佳參數，藉此優化車牌字元的大小、角度與位置資訊，計算出字元偏斜與車牌旋轉角度後利用Affine transformation將其轉回正面車牌影像，以提升字元切割與辨識率。字元切割和字元辨識部分非本論文探討重點，方法主要根據前人所做的研究，適用車牌以台灣車牌為主。

Different from most of vehicular license plate recognition that concerns automobiles, this study focuses on motorcycles. Because of the difference on where the license plate is installed, the detection of the license plate on a motorcycle is often more difficult than that on an automobile. To efficiently detect a motorcycle's license plate, it is proposed that the detection of motorcycle must be handled first so that the search area for the plate can be substantially reduced. Several detectors, including AdaBoost, HOG and DPM, are implemented and compared on the performance of motorcycle detection. When the motorcycle is detected, the aforementioned three detectors are implemented again, but modified for the detection of the license plate. In the performance comparison of license plate detectors, one made by GMM is also considered, as it was proven effective for detecting automobile license plates. It is found that DPM can be an excellent detector for both motorcycles and license plates, but it is too slow to be consider a practical solution. Tested on the data collected from various conditions, the best performance is given by an SVM classifier with HOG as the feature

[1] Mukhtar, A.;Likun Xia;Tang Tong Boon;Abu Kassim,K.A.“On-road approaching motorcycle detection and tracking techniques: A survey”, Control System, Computing and Engineering (ICCSCE), 2013 IEEE International Conference
[2] J. Chiverton, "Helmet presence classification with motorcycle detection and tracking," IET Intelligent Transport Systems, vol. 6, pp. 259 – 269, September 2012.
[3] D. Bobo, L. Wei, F. Pengyu, Y. Chunyang, W. Xuezhi, and Y. Huai, "Real-time on-road vehicle and motorcycle detection using a single camera," in Industrial Technology, 2009. ICIT 2009. IEEE International Conference on, 2009, pp. 1-6.
[4] W. Xuezhi, Y. Huai, S. Chunyan, L. Wei, and Z. Hong, "An algorithm based on SVM ensembles for motorcycle recognition," in Vehicular Electronics and Safety, 2007. ICVES. IEEE International Conference on, 2007, pp. 1-5.
[5] N. Kanhere, S. Birchfield, W. Sarasua, and S. Khoeini, "Traffic Monitoring of Motorcycles During Special Events Using Video Detection," Transportation Research Record: Journal of the Transportation Research Board, vol. 2160, pp. 69-76, 12/01/ 2010.
[6] M. Djalalov, H. Nisar, Y. Salih, and A. S. Malik, "An algorithm for vehicle detection and tracking," in Intelligent and Advanced Systems (ICIAS), 2010 International Conference on, 2010, pp. 1- 5.
[7] P. KaewTraKulPong and R. Bowden, "An improved adaptive background mixture model for real-time tracking with shadow detection," in Video-Based Surveillance Systems, ed: Springer US, 2002, pp. 135-144.
[8] C. Zezhi, T. Ellis, and S. A. Velastin, "Vehicle detection, tracking and classification in urban traffic," in Intelligent Transportation Systems (ITSC), 2012 15th International IEEE Conference on, 2012, pp. 951-956.
[9] Nguyen Phi-Vu, Le Hoai-Bac. "Incorporating statistical background model and Joint Probabilistic Data Association filter into motorcycle tracking", In: IEEE International Conference on Research, Innovation and Vision for the Future[C], Ho Chi Minh, Vietnam,2008:284-291.
[10] C. Tzomakas and W. v. Seelen, “Vehicle detection in traffic scenes using shadows ”, Technical Report 98-06, Institut fur Neuroinformatik, Ruht Universitat, Bochum, Germany, 1998.
[11] M. B. Van Leeuwen and F. C. A. Groen, “Vehicle detection with a mobile camera: spotting midrange, distant, and passing cars,” Robotics & Automation Magazine, IEEE, vol. 12, pp. 37-43,2005
[12] M. Betke, E. Haritaoglu, and L. S. Davis, “Real-time multiple vehicle detection and tracking from a moving vehicle,” Machine Vision and Applications, vol. 12, pp. 69-83, 2000/08/01 2000.
[13] M. Bertozzi, A. Broggi, and S. Castelluccio, “A real-time oriented system for vehicle detection,” Journal of Systems Architecture, vol. 43, pp. 317-325, 3// 1997.
[14] A. Bensrhair, M. Bertozzi, A. Broggi, A. Fascioli, S. Mousset, and G. Toulminet, “Stereo vision-based feature extraction for vehicle detection,” in Intelligent Vehicle Symposium, 2002. IEEE, 2002, pp. 465-470 vol.2.
[15] D. Bin, F. Yajun, and W. Tao, “A Vehicle Detection Method via Symmetry in Multi-Scale Windows,” in Industrial Electronics and Applications, 2007. ICIEA 2007. 2nd IEEE Conference on, 2007, pp. 1827-1831.
[16] Y. Du and N. P. Papanikolopoulos, “Real-time vehicle following through a novel symmetry-based approach,” in Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on, 1997, pp. 3160-3165 vol.4.
[17] A. Kuehnle, “Symmetry-based recognition of vehicle rears,” Pattern Recognition Letters, vol. 12, pp. 249-258, 4// 1991.
[18] T. Zielke, M. Brauckmann, and W. Vonseelen, “Intensity and Edge-Based Symmetry Detection with an Application to Car- Following,” CVGIP: Image Understanding, vol. 58, pp. 177-190, 9// 1993.
[19] T. Bucher, C. Curio, J. Edelbrunner, C. Igel, D. Kastrup, I. Leefken, et al., “Image processing and behavior planning for intelligent vehicles,” Industrial Electronics, IEEE Transactions on, vol. 50, pp. 62-75, 2003.
[20] T. Luo-Wei, J. W. Hsieh, and F. Kuo-Chin, "Vehicle Detection Using Normalized Color and Edge Map," Image Processing, IEEE Transactions on, vol. 16, pp. 850-864, 2007.
[21] L. Wei, W. Xuezhi, D. Bobo, Y. Huai, and W. Nan, “Rear Vehicle Detection and Tracking for Lane Change Assist,“ in Intelligent Vehicles Symposium, 2007 IEEE, 2007, pp. 252-257.
[22] Jie Yu; Fengli Zhang; Jian Xiong; Wen Qiang Guo "Distinguishing moving objects from traffic video by the dynamic background skeleton based model", Communications, Circuits and Systems (ICCCAS), 2013 International Conference on, On page(s): 271 - 275 Volume: 1, 15-17 Nov. 2013
[23] Sun Li; Bo Wang; ZhiHui Zheng; HaiLuo Wang "Multi-view vehicle detection in traffic surveillance combining HOG-HCT and deformarle part models", Wavelet Analysis and Pattern Recognition (ICWAPR), 2012 International Conference on, On page(s): 202 – 207
[24] S. Messelodi, C. M. Modena, and G. Cattoni, "Vision-based bicycle/motorcycle classification," Pattern Recognition Letters, vol. 28, pp. 1719-1726, 10/1/ 2007.
[25] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 99, 2010.
[26] 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," Intelligent Transportation Systems, IEEE Transactions on, vol. 9, pp. 377-391, 2008
[27] G.-S. Hsu, J.-C. Chen, and Y.-Z. Chung, "Application-Oriented License Plate Recognition," Vehicular Technology, IEEE Transactions on, vol. 62, pp. 552-561, 2013.
[28] A. Khammari, F. Nashashibi, Y. Abramson and C. Laurgeau, “Vehicle detection combining gradient analysis and AdaBoost classification,” in Proceedings of IEEE Intelligent Transportation Systems, 2005, pp. 66-71.
[29] Xue-Chao Li, Cui-Hua Li, Yi Xie, ”A retrieval system of vehicles based on recognition of license plates”, Published in: Machine Learning and Cybernetics (ICMLC), 2011 International Conference on (Volume:4 )
[30] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 886-893 vol. 1.
[31] 陳明宏, "基於MSER之車牌字元切割和階層式分類器之字元辨識," 台灣科技大學碩士學位論文, 2011.
[32] J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust wide baseline stereo from maximally stable extremal regions," Image and Vision, vol. 22, pp. 761-767, 2004.
[33] 鍾育儒, "含自動學習機制之動態影像車牌辨識," 台灣科技大學碩士學位論文, 2014.
[34] H.-J. Lee , S.-Y. Chen and S.-Z. Wang "Extraction and recognition of license plates of motorcycles and vehicles on highways", Proc. ICPR, pp.356 -359 2004
[35] Y. P. Huang , C. H. Chen , Y. T. Chang and F. E. Sandnes "An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition", Expert Syst. Appl., vol. 36, no. 5, pp.9260 -9267 2009