首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于机器视觉的非结构化道路检测与障碍物识别方法
引用本文:宋怀波,何东健,辛湘俊.基于机器视觉的非结构化道路检测与障碍物识别方法[J].农业工程学报,2011,27(6):225-230.
作者姓名:宋怀波  何东健  辛湘俊
作者单位:西北农林科技大学机电学院,杨凌,712100
基金项目:国家自然科学基金资助(31000670、60975007);西北农林科技大学人才专项资金资助(Z1110209005)
摘    要:为了实现非结构化道路检测与障碍物的识别,提出了一种基于最小错误率贝叶斯决策与Hough变换相结合的非结构化道路检测与障碍物识别算法。算法首先将Otsu多阈值理论引入到最小错误率贝叶斯决策中并进行图像分割,然后利用Hough变换进行道路检测、提取出纯路面区域并再次进行路面分割,最后根据分割结果进行路面障碍物定位。结果表明,该算法能够有效实现非结构化道路的检测与障碍物的识别,在光影、照度变化、水渍等不利因素影响较小的情况下,具有较好的鲁棒性。

关 键 词:车辆,导航,非结构化道路,贝叶斯决策,Hough变换,障碍物识别
收稿时间:2010/8/27 0:00:00
修稿时间:2010/10/23 0:00:00

Unstructured road detection and obstacle recognition algorithm based on machine vision
Song Huaibo,He Dongjian and Xin Xiangjun.Unstructured road detection and obstacle recognition algorithm based on machine vision[J].Transactions of the Chinese Society of Agricultural Engineering,2011,27(6):225-230.
Authors:Song Huaibo  He Dongjian and Xin Xiangjun
Institution:Song Huaibo,He Dongjian,Xin Xiangjun (College of Mechanical and Electronic Engineering,Northwest Agriculture and Forestry University,Yangling,Shanxi 712100,China)
Abstract:To realize the unstructured road detection and obstacle recognition,a hybrid algorithm based on minimum error Bayesian decision theory and Hough transform was presented.The Otsu muti-threshold method was introduced into the minimum error Bayesian decision theory and the image was divided into road area and the other area.And then,Hough transform was used to detect the road and off-road borders,and the road area was re-segmented to detect the obstacles on the road.At last,the obstacles were located by outer ...
Keywords:vehicles  navigation  unstructured road  Bayesian decision  Hough transform  obstacle recognition
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《农业工程学报》浏览原始摘要信息
点击此处可从《农业工程学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号