摘要
OTSU法(最大类间方差法)被认为是图像分割中阈值自动选取的最优方法之一,针对自主开发的视觉导航区域交通智能车辆(CyberCar)的导航路径在强光照条件下不能直接应用此方法取得准确分割效果的问题,提出了一种基于区域的罗伯特梯度算子的图像分割方法。分割实验表明,与OTSU法分割效果相比,采用的图像分割方法能够准确地对强光照条件下的导航路径图像进行分割,并具有更好的实时性。
The OTSU algorithm (maximization of interclass variance) is considered as one of the superior threshold selection meth- ods.But this method can not segment the path mark image successfully for our indigenous design and manufactured vision navigation intelligent vehicle(Cyber Car) under bright illumination.A new method based on regional Roberts gradient is proposed in or- der to solve this problem.The segmentation experimental results of bright path mark images show that the new method can segment the navigation path accurately and quickly.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第26期236-238,共3页
Computer Engineering and Applications
基金
吉林省杰出青年科学研究计划项目(No20060117)
中国博士后基金项目(No2004036397)
关键词
图像分割
梯度
智能车辆
最大类间方差
image segmentation
gradient
intelligent vehicle
maximization of interclass variance