摘要
在结构化道路情况下,车道检测简化为白线检测。文章利用图像处理技术和优化技术,提出了一种在结构化道路中精确检测车道的两层算法。同时利用白线的局部特性和全局特性,鲁棒的提取特征;将感兴趣区域分为近视野和远视野,按照″拟和-判断-拟和″的流程,用直线或直线与二次曲线的光滑组合匹配白线;并针对具体应用环境,为优化算法添加适当的权值因子,提高算法抗噪性。测试结果表明算法能够自动、快速、准确的检测白线。
A two-step method based on image processing technique and optimization algorithm was proposed to detect lane in structural road environment.The method used not only the local characters but the global characters of the input images to recognize lane more robustly,and divides every image to two portions in which the regression is processed respectively.With appending appropriate factors,the optimization algorithm can get more antinoise capability.Experimental results showes that the proposed method can detect structural road automatically,rapidly and exactly.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第1期203-206,共4页
Computer Engineering and Applications
基金
国家自然科学基金重点项目(编号:60134010)
关键词
智能车
视觉导航
白线检测
结构化道路
intelligent vehicle,vision-based navigation,white line detection,structural road
