動態單攝影機多車道車牌辨識系統

車牌辨識現今已被廣泛應用於高速公路收費系統，停車場管理系統，以及各項交通違規等系統中，可大幅提高效率。然而現行的系統，都為單一系統，即一個攝影機只能辨識一個車道。本論文提出，使用高解析度的攝影機，一個攝影機可同時辨識多個車道的車牌辨識，此方法不但可以大幅降低攝影機的建置成本，也可提高辨識的效率，使之更經濟且效益。因此，本研究包含動態車牌定位演算法與車牌辨識演算法。首先是車牌定位演算法，本論文中使用車道切割的技術，我們可以使用單一攝影機拍攝出來的多車道影像，經過車道切割的方法，即可將影像切割成多個車道，達成使用單一攝影機同時辨識多車道的目的。我們動態多車道車牌定位成功率為94%。車牌辨識的部份，使用Tesseract-OCR當辨識的核心演算法，加上已訓練的車牌字庫，本論文的辨識系統可應用於多車道車牌辨識上。即一次可同時辨識多個車道的車牌，優於傳統的辨識系統只能應用於單一車道和辨識單一個車牌。我們測試本系統在高速公路多車道的環境中，拍攝行駛中的車輛，並得到了車牌辦識成功率為86％。

關鍵字

車牌辨識；車牌定位；多車道；邊緣偵測

並列摘要

License Plate Recognition (LPR) System has now been widely used in highway toll collection, parking management, various traffic regulations enforcement, and other systems. Currently, most of the existing license plate localization systems are with single camera that is limited to recognizing vehicles in one lane. This thesis presents a license plate recognition system that simultaneously recognizes license plates of vehicles on multiple lanes by using single high-resolution camera. Our approach significantly reduces the hardware cost of LPR system without sacrificing the accuracy of recognition. Therefore, the dynamic LPR algorithm and recognition algorithm are included in this study. First, about the dynamic LPR algorithm of this study, we apply lane separation technique on multi-lane image captured by single camera to separate image into individual lanes which makes possible for one camera to recognize vehicles in multiple lanes. Our success rate is about 94%. Furthermore, we employ Tesseract-OCR as the core engine and the well trained database for the license plates to recognize license plates in our system. Hence, our design makes our system superior to traditional LPR, which can only be used in one single lane to recognize one single license plate. We tested our system on highway to capture images of fast moving vehicles in multiple lanes and got a recognition success rate 86%.

並列關鍵字

License plate recogntion ； License plate Localization ； Multi-lane ； Edge Detection

參考文獻

[33] J. L. Wu, “An Automatic Enhancement Method for High Contrast Images via Bilateral Filtering”, Journal of Science and Engineering Technology, Vol. 3, No. 3, 2007, pp. 81-87.

[36] 陳光中，即時車牌辨識系統 - 動態影像中有效辨識多個車牌的方法，碩士論文，國立台北科技大學電資學院電資碩士班，台北，2010。

[3] A. Taleb-Ahmed, D. Hamad, and G. Tilmant, “Vehicle license plate recognition in marketing application,” 2003 Proceedings of Intelligent Vehicles Symposium, IEEE, 2003, pp. 90-94.

[4] S. L. Chang, L. S. Chen, Y. C. Chung, and S. W. Chen, “Automatic license plate recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol. 5, 2004, pp. 42-53.

[5] C. T. Hsieh, Y. S. Juan, and K. M. Hung, “Multiple license plate detection for complex background,” 2005 Proceedings of International Conference on Advanced Information Networking and Applications, Vol. 2, 2005, pp. 389-392.

國際替代計量

動態單攝影機多車道車牌辨識系統

未授權

主題瀏覽