采用Hough变换的道路边界检测算法

基于计算机视觉的路况信息识别是当前智能交通领域的热点课题,对道路边界的检测能够有效去除路况图像中与路况特征无关的大面积区域,是提高路况信息获取实时性的关键技术之一,提出一种适用于一般场景中直线道路和弯曲道路的边界检测算法.该算法采用直方图均衡和Otsu二值分割增强道路边界特征,使用均值滤波降噪和二值形态学方法获取特征边界,最终利用分空间的Hough变换方法实现道路边界检测.实验结果表明,该方法能够准确地检测道路边界线并进行道路区域分割,为后续的路况分类工作提供了有效保障.

A road edge detection algorithm based on the Hough transform

Traffic information detection has become a hot topic in the field of computer vision and intelligent transportation systems.The detection of the road edge can effectively remove a large area which has nothing to do with traffic information in order to improve real-time traffic information detection performance.A road edge detection algorithm for straight and serpentine roads was proposed.Histogram equalization and binary segmentation by Otsu method were used to enhance the road edge features,while a mean filter and morphological binary edge were adopted to get rid of noise and obtain features.The Hough transform was used in different spaces to detect the road edge.Experimental results demonstrate that the road edges were detected accurately and the road area was extracted effectively by the proposed methods,guaranteeing the subsequent work of traffic information assorting.