摘要
基于视觉导航的高速智能车,提出一种改进的道路快速检测算法。用改进的水平均值投影法划分道路和背景区域,结合边缘检测算子和最大类间方差法(大津算法),构成双阈值法对道路区域图像进行二值化处理,利用先验知识改进的霍夫变换,在路面存在阴影和噪声干扰的条件下,能准确地检测车道标识线;对动态预测划分感兴趣区域,采用菱形搜索法进行车道线跟踪,融合初始检测和后续跟踪两层算法循环处理道路图像序列。实车试验表明,算法具有良好的实时性和鲁棒性,满足智能车高速行驶要求。
Based on a high-speed intelligent vehicle with vision navigation,an improved algorithm of lane fast detection was proposed.The horizontal projection of the mean of pixels＇ gray value was improved to divide image into the road area and background area.Double-threshold method was generated by combining edge detection operator and the largest between-class variance（Otsu Algorithm） so that the grayscale of road region can be converted into binary image.The algorithm firstly improved Hough transfer using the transcendental knowledge,and then delineated the dynamic predicted region of interest.Finally,it introduced diamond search algorithm for tracking lane line.It can well and truly detect lane marking even if there are some interference factors in the road such as shadow,yawp,etc.and processed sequences of road images by means of recycling using initial testing and subsequent tracking modules.The Experimental result shows that this algorithm with high efficiency and robustness can meet the requirement of intelligent vehicle＇s fast driving.
出处
《计算机仿真》
CSCD
北大核心
2012年第4期362-366,共5页
Computer Simulation
关键词
智能交通
车道线检测
水平投影法
最大类间方差法
霍夫变换
Intelligent transportation
Lane detection
Horizontal projection
The largest between-class variance
Hough transfer
