使用雙攝影機系統於大範圍區域進行車牌辨識

License Plate Recognition in a Large Area with a Dual-Camera System

蔡承志(Cheng-Chih Tsai)

指導教授 ： 洪一平

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2011年)

https://doi.org/10.6342/NTU.2011.01134

摘要

近年來，智慧型監控系統在日常生活中的應用越來越廣泛。在本論文裡，我們提出一套結合主從式智慧型監控與車牌辨識的系統。此系統硬體由兩支攝影機組成，其中一台為固定式場域監控攝影機，一台為高速球型攝影機。此系統可以監控廣泛區域，並同時取得監控場景中車輛的高解析度清晰影像，以進行車牌辨識。為了達成上述功能，我們必須在固定式場域監控攝影機畫面裡取出車輛的影像，預測其可能移動的路徑，並控制高速球型攝影機進行旋轉追蹤。此外，由於我們所監控的場景為一廣泛區域，車輛會由不同角度及路徑經過。可是傳統的車牌辨識方法僅能針對正面車牌影像進行偵測與辨識。因此，我們提出一可於不同的距離與角度進行準確的車牌辨識方法。實驗結果顯示，所提出的方法可自動估測車輛行進軌跡並取得高解析度車牌影像，且能對不同視角之車牌影像進行偵測與辨識。

關鍵字

車牌辨識 ； 影像監控 ； 雙攝影機系統

並列摘要

In the last few years, intelligent visual surveillance system plays an important role in our daily life. In this thesis, we combine a master-slave dual-camera system with a novel license plate recognition technique. Our system is consisted of two cameras, one is a wide-angle, fixed camera, and the other is a speed dome camera. The system is able to monitor a wide area with wide-angle camera and grabs high-resolution images with the speed dome camera to process license plate recognition. In order to achieve the functions mentioned above, we have to detect the vehicle from image sequences of wide angle fixed camera first, predict the position of the vehicle, and then control the speed dome camera to track it. In addition, since the monitored area is large, the view angle to the license plate may be arbitrary. Compare to traditional license plate recognition methods, which can only deal with the almost frontal view cases, here, we propose a novel method, which can recognize license plates even with different distances and arbitrary view-angles. The experimental results show our method can detect and predict the vehicle, and further recognize the inclined license plate well.

並列關鍵字

license plate recognition ； video surveillance ； dual camera system

參考文獻

[1] B. Hongliang and L. Changping, “A hybrid license plate extraction method based on edge statistics and morphology,” in Proc. ICPR, 2004, pp. 831–834.

[2] D. Zheng, Y. Zhao, and J. Wang, “An efficient method of license plate location,” Pattern Recognit. Lett., vol. 26, no. 15, pp. 2431–2438, Nov. 2005.

[4] C. Anagnostopoulos, I. Anagnostopoulos, E. Kayafas, and V. Loumos, “A license plate recognition system for intelligent transportation system applications,” IEEE Trans. Intell. Transp. Syst., vol. 7, no. 3, pp. 377–392, Sep. 2006.

[5] C. Anagnostopoulos, I. Anagnostopoulos, I. Psoroulas, and V. Loumos, “License plate recognition from still images and video sequences: Asurvey,” IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 3, pp. 377–391, 2008.

[6] K. Deb, S. Kang, and K. Jo, “Statistical characteristics in HSI color model and position histogram based vehicle license plate detection,” Intell. Serv. Robotics 2, 173–186, 2009.