交通运输系统工程与信息

交通运输系统工程与信息 ›› 2014, Vol. 14 ›› Issue (1): 47-52.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于特征颜色和SNCC的交通标志识别与跟踪

房泽平1,2，段建民*1，郑榜贵1   

  1. 1. 北京工业大学 电子信息与控制工程学院，北京 100124; 2. 中原工学院 电子信息学院，郑州 450007
  • 收稿日期:2013-04-18 修回日期:2013-08-28 出版日期:2014-02-25 发布日期:2014-07-07
  • 作者简介:房泽平（1975-），男，满族，辽宁开原人，讲师，博士生.

Traffic Signs Recognition and Tracking Based on Feature Color and SNCC Algorithm

FANG Ze-ping1,2, DUAN Jian-min1,ZHENG Bang-gui1   

  1. 1. School of Electronic Information and Control Engineering , Beijing University of Technology, Beijing 100124,China;2. School of Electronic Information, Zhongyuan Institute of Technology, Zhengzhou 450007,China
  • Received:2013-04-18 Revised:2013-08-28 Online:2014-02-25 Published:2014-07-07

PDF

被引次数

9

摘要：

提出了基于特征颜色和SNCC的交通标志识别与跟踪方案，该方案用于智能车辆的交通标志识别与跟踪.在YCbCr色彩空间对交通场景图像进行颜色阈值分割，提取交通标志所在区域.根据标准交通标志的背景和内景特征颜色，设计标准交通标志的背景和内景颜色特征匹配模板.以背景和内景颜色特征匹配模板作为模板，采用模板匹配技术和SNCC计算匹配度，识别潜在交通标志图像和交通标志.在Matlab/Simulink环境下，基于视频与图像处理模块集和用户自定义函数模块构建仿真模型，进行仿真研究，给出了交通场景视频中交通标志的识别和跟踪轨迹仿真结果.结果表明，采用本文的交通标志识别与跟踪方案，计算量少，提高系统的效率，达到了较好的识别效果.

关键词: 智能交通, 交通标志识别, 简化归一化互相关法, 智能车辆, YCbCr空间, 模板匹配, 跟踪轨迹

Abstract:

This paper proposes a scheme of traffic signs recognition and tracking based on feature color and SNCC algorithm, which is used in traffic signs recognition and tracking of intelligent vehicles. In YCbCr color space, color segmentation of the traffic scene images is calculated, and traffic sign regions are obtained. According to background and interior color feature of the standard traffic signs, background and interior color matching templates of traffic signs color feature are designed. The background and the interior color matching templates are as the matching templates, the template matching technology and the SNCC algorithm to calculate matching degree are used to draw and recognize the images of traffic signs. In the Matlab/Simulink environment, the simulation model is established by using video and image processing blockset and User-Defined Functions module. Based on simulation model, recognition results and the tracking of the traffic signs in the traffic scene video are given. The experimental results show that the scheme of traffic signs recognition and tracking can improve the efficiency of the system, and has less calculation amount, and has the better recognition effect.

Key words: intelligent transportation, traffic sign recognition, simplified normalized cross correlation;intelligent vehicles, YCbCr color space, template matching, tracking

中图分类号: