交通自動監控系統之研究

On the Study of Automatic Traffic Surveillance System

游世豪(Shih-Hao Yu)

指導教授 ： 陳永盛

元智大學/工程學院/電機工程學系/碩士(2002年)

摘要

由於各國的社會經濟的快速發展，車輛不斷增加但新闢道路有限，故解決交通擁塞問題刻不容緩，本論文提出一個對於交通影像序列的自動監控系統。此交通監控系統由三部分所組成，首先，我們使用適應性背景更新法和背景差值法來偵測移動物體；然後，卡門濾波器再加以追蹤個別的移動物體；最後，我們利用視覺上的直觀，提出一個新方法將車輛分類。另外，由於車牌辨識在交通監控系統內扮演一個不可或缺的角色，所以本論文也提出以形態學為基礎的方法來定位車牌。車牌辨識系統由三部分構成，首先，利用形態學基礎的方法來抽取具高對比特徵的車牌；接著，如果車牌被切割幾個部分，再利用車牌校正演算法予以校正；最後以車牌中所出現的字元數做車牌確認的工作。實驗結果證明我們所發展的系統具有不錯的穩定性與實用性。

關鍵字

交通監控 ； 車輛分類 ； 車牌定位

並列摘要

This thesis develops an automatic traffic surveillance system for tracking and classification vehicles in traffic video sequences. First, we utilize an adaptive background update method and background difference to detect moving objects. Then, a Kalman filter was used to stabilize tracking and track individual objects. Finally, we propose a novel method to classify vehicles by means of direct percept on visual data. On the other hand, license plate recognition (LPR) is a very important task in the traffic surveillance system. This thesis also presents a morphology-based method for extracting license plates from cluttered images. The LPR system consists of three major components. At the first, a morphology-based method is proposed to extract important contrast features as guides to search the desired license plates. A recovery algorithm is then applied for reconstructing a license plate if the plate is fragmented into several parts. The last step of the proposed method performs license plate verification based on the number of characters appearing in the plate. Experimental results show that the developed system improves the sate-of-the-art work in terms of effectiveness and robustness for classification of vehicles and license plate detection.

並列關鍵字

traffic surveillance ； vehicle classification ； license plates localiztion

參考文獻

[1] O. Masoud, N. P. Papanikolopoulos, and E. Kwon, “Vision-based monitoring of weaving sections,” Proc. of IEEE Conference on Intelligent Transportation Systems, pp. 770-775, October 1999.

[4] C. Li, K. Ikeuchi, and M. Sakauchi, “Acquisition of traffic information using a video camera with 2D spatio-temporal image transformation technique,” Proc. of IEEE Conference on Intelligent Transportation Systems, pp. 634-637, October 1999.

[5] R, Defauw, S. Lakshmanan, and K. V. Prasas, “Asystem for small target detection, tracking, and classification,” Proc. of IEEE Conference on Intelligent Transportation Systems, pp. 639-648, October 1999.

[7] M. Fathy and M. Y. Siyal, “A window-based image processing technique for quantitative and qualitative analysis of road traffic parameters,” IEEE Transactions on Vehicular Technology, vol. 47, no. 4, pp. 1342-1349, November 1998.

[10] R. Cucchiara, M. Piccardi, and P. Mello, “Image analysis and rule-based reasoning for a traffic monitoring system,” IEEE Transactions on Intelligent Transportation Systems, vol. 1, no. 2, pp. 119-130, 2002.