计算机应用 ›› 2010, Vol. 30 ›› Issue (4): 974-976.

• 模式识别 • 上一篇    下一篇

基于边缘分布函数的车道标识线识别方法

闫旭琴1,吴晓兵2,车晓波2,张云2,王知学2   

  1. 1. 山东省科学院自动化研究所
    2.
  • 收稿日期:2009-10-10 修回日期:2009-11-25 发布日期:2010-04-15 出版日期:2010-04-01
  • 通讯作者: 闫旭琴

Lane mark identification method based on edge distribution function

  • Received:2009-10-10 Revised:2009-11-25 Online:2010-04-15 Published:2010-04-01

摘要: 为了得到较理想的车道标识线的边缘,考虑车道标识线的方向特性,提出一种基于边缘分布函数(EDF)的图像预处理方法。将图像分区处理,在对图像中的噪声特性进行EDF分析的基础上,对处理区域作如下处理:首先将梯度角量化为4-方向,去除与车道标识线方向不一致的噪声,得到边缘图像;然后利用EDF对边缘图像滤波,确定车道标识线角度初值;最后应用Hough变换定位出车道标识线。实验结果表明,该方法能够更加有效地强化车道标识线信息,去除噪声,具有较好的鲁棒性和实时性。

关键词: 车道标识线识别, 边缘分布函数, 4-方向梯度角, Hough变换, 梯度算子, 梯度幅值, 梯度方向

Abstract: In order to get an ideal lane marks’ edge, an image preprocessing method based on edge distribution function (EDF) was proposed considering the directional characteristics of lane marks. Images were divided into regions, and the following processing was made to regions based on applying EDF analysis to noise characteristics of images: firstly, by changing the gradient angle into 4-direction, edge images were obtained after removing the noise inconsistent with lane marks’ direction. Then initial value of lane marks angle was calculated using EDF filter to edge images. Finally Hough transformation was applied to localizing lane marks. The experimental result shows the method can intensify the information of lane marks and eliminate noise in images effectively. The algorithm is characterized by robustness and real-time.

Key words: lane mark identification, Edge Distribution Function (EDF), 4-directional gradient angle, Hough transformation, gradient operator, gradient magnitude, gradient direction