计算机科学与探索 ›› 2012, Vol. 6 ›› Issue (10): 919-926.DOI: 10.3778/j.issn.1673-9418.2012.10.007

• 学术研究 • 上一篇    下一篇

缩微交通环境下的车道标识线检测

储卫东+,王国胤,王  进   

  1. 重庆邮电大学 计算智能重庆市重点实验室,重庆 400065
  • 出版日期:2012-10-01 发布日期:2012-09-28

Lane Detection in Micro-Traffic Environment

CHU Weidong, WANG Guoyin, WANG Jin   

  1. Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Online:2012-10-01 Published:2012-09-28

摘要: 为了解决缩微交通环境下的车道标识线检测问题,提出了一种数学形态学与概率霍夫变换相结合的车道标识线检测方法。首先运用灰值腐蚀膨胀对道路图像进行滤光处理,去除光照影响,然后利用自适应阈值二值化图像,最后利用概率霍夫变换寻找车道标识线。实验结果表明,在缩微交通环境下该方法能够准确地检测出车道标识线,具有很强的鲁棒性。

关键词: 缩微智能车, 车道标识线检测, 数学形态学, 二值化, 概率霍夫变换

Abstract: In order to realize the lane detection in a micro-traffic environment, this paper proposes a lane detection method based on mathematical morphology and probabilistic Hough transform. Firstly, the road images are preprocessed with a grayscale dilation and erosion operation to filter light. Then, an adaptive threshold binarization algorithm is used to extract the lines from the gray images. Finally, a probabilistic Hough transform is employed to detect lanes. The experimental results show that the proposed method can detect the lane accurately and has good robustness.

Key words: miniature intelligent vehicle, lane detection, mathematical morphology, binarization, probabilistic Hough transform