计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于车牌字符边界定位的视频测速

陈 群,杨东勇,卢 瑾   

  1. (浙江工业大学信息工程学院,杭州 310023)
  • 收稿日期:2013-02-27 出版日期:2014-05-15 发布日期:2014-05-14
  • 作者简介:陈 群(1987-),男,硕士研究生,主研方向:模式识别,数字图像信号处理;杨东勇,教授、博士生导师;卢 瑾,实验师、博士研究生。
  • 基金项目:
    浙江省自然科学基金资助项目(Y1080533)。

Video Speed Measurement Based on Boundary Location of License Plate Characters

CHEN Qun, YANG Dong-yong, LU Jin   

  1. (College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China)
  • Received:2013-02-27 Online:2014-05-15 Published:2014-05-14

摘要: 针对卡口环境下视频测速误差大的问题,提出一种提高测速精度的方法。采用以车牌第2个字符作为车辆定位的特征块,利用小波变换分解字符的外部边界特征曲线,在低分辨率下实现目标字符的模板匹配,并获取该曲线相对模板的偏移量,在原分辨率上进行边界坐标的精细调整,完成车辆特征块的精确定位。结合字符高度固定的先验知识,确定车辆特征块所处的实际坐标系,以提高对车辆行驶距离的计算。在实际环境下,对该方法进行长达2个多小时的测试,并对测试结果与线圈测速、基于车牌定位的视频测速进行对比,结果表明,在车辆正常行驶的速度下,与线圈测速相比,该方法视频测速误差在3 km/h以内。

关键词: 视频测速, 字符定位, 小波分解, 模板匹配, 摄像机标定, 消失点

Abstract: Aiming at the problem that video speed measurement has a large error under bayonet socket environment, a method to improve the velocity precision is proposed. The second character of license plate as a feature of vehicle positioning block is used, wavelet decomposition is used to decompose the characteristic curve of the characters outer boundary, the feature matching is made and the offset of the curve about the template is obtained at low resolution, the outer boundary is adjusted in the initial resolution to complete the vehicle precise location. The actual coordinate of the block is determined combined with the height fixed of character, improves the distance of the vehicle traveling. In actual environment, it tests the algorithm for longer than two hours, and compared with coil speed and video speed measurement by license plate location. Results show that, under normal speed, the error is within 3 km/h compared with the coil speed.

Key words: video speed measurement, character location, wavelet decomposition, template matching, camera calibration, vanishing points

中图分类号: