计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (33): 236-239.

• 工程与应用 • 上一篇    下一篇

结合先验知识和图像特征的道路提取方法

林丽群1,肖 俊2   

  1. 1.湖北大学 资源与环境学院,武汉 430062
    2.武汉大学 测绘遥感信息工程国家重点实验室,武汉 430079
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-21 发布日期:2011-11-21

Combined prior knowledge and image characteristics for lane detection method

LIN Liqun1,XIAO Jun2   

  1. 1.School of Resources and Environmental Science,Hubei University,Wuhan 430062,China
    2.The State Key Lab of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-21 Published:2011-11-21

摘要: 致力于在复杂环境下能对多种道路进行检测,提出了一种先验知识库与自适应区域增长相融合的道路检测方法,通过少量的道路样本采集,建立样本库,训练挖掘出道路知识模型,并结合区域增长方法对分割的实时道路影像进行道路区域增长。实验结果表明,该方法适用于多种不同环境道路的提取,鲁棒性强。

关键词: 道路检测, 计算机视觉, 区域增长

Abstract: In the complex environment,this paper presents a lane detection method with the ability to deal with both structured and unstructured roads.The method combines a priori knowledge database with adaptive region growing method.It establishes a priori knowledge database through a set of road sampling,training,data mining and knowledge discovery,combines adaptive road region growing method using this database process on real-time segmented images.The experimental results show that this method is able to robustly find the road area on different types of roads in various environments.

Key words: road detection, computer vision, region growing