›› 2016, Vol. 29 ›› Issue (6): 150-.

• 论文 • 上一篇    下一篇

基于OpenCV的行驶车辆车牌定位实现

程挥竣,应捷   

  1. (上海理工大学 光电信息与计算机工程学院,上海 200093)
  • 出版日期:2016-06-15 发布日期:2016-06-22
  • 作者简介:程挥竣(1992-),男,硕士研究生。研究方向:图像处理与模式识别。

Vehicle License Plate Location Based on the Travel OpenCV Implementation

CHENG Huijun,YING Jie   

  1. (School of OpticalElectrical and Computer Engineering, University of Shanghai for Science and Technology,Shanghai 200093, China)
  • Online:2016-06-15 Published:2016-06-22

摘要:

车牌定位是车牌自动识别系统中的一个关键问题。系统从两方面进行了设计。一是视频中移动车辆的定位,采用高斯背景建立模模块。二是静态图像中车牌提取系统,采用顶帽变换、能量滤波、寻找联通区域等多模块结合精确定位出车牌区域。该移动车牌定位算法在QT平台上采用OpenCV和C++编程,实现了综合利用车牌结构特征和纹理特征,提高了车牌定位可靠性。实验结果表明,该方法速度快、准确度高,可满足实时监控的需求。

关键词: 车牌识别, 混合高斯建模, 顶帽变换, 能量滤波

Abstract:

The license plate location is a key problem in the automatic recognition system of the license plate. More in-depth design did in two areas. Firstly, the video of the mobile vehicle positioning that mainly involved in the Gauss background modeling. Secondly, the static image of the license plate extraction system included the top hat transform, energy filtering, to find the area of the Unicom area and other modules to accurately locate the license plate region. The mobile license plate location algorithm using OpenCV and C++ programming is based on the QT platform to achieve a comprehensive use of the structure and texture features of the license plate, improving the reliability of the license plate location. Experimental results show that the method is faster and more accurate. The system can meet the needs of real-time monitoring.

Key words: license plate recognition;hybrid gauss modeling;top hat transformation;energy filtering

中图分类号: 

  • TP751.1