| 在高分辨率遥感影像中提取无清晰连续边缘线的道路 |
| |
| 引用本文： | ZHOU Shao-guang,徐勇.在高分辨率遥感影像中提取无清晰连续边缘线的道路[J].测绘学报,2008,37(3):0-402. |
| |
| 作者姓名： | ZHOU Shao-guang 徐勇 |
| |
| 作者单位： | 河海大学,测绘工程系,江苏,南京,210098 |
| |
| 摘 要： | 现有的许多道路提取算法均利用道路的外边缘线信息来实现道路的提取,当边缘线清晰连续时,采用这些方法都可以取得很好的提取效果.不过,在高分辨率的城市遥感影像中,常常会存在一些低对比度区域,处于其中的道路边缘线非常之弱,以致难以直接检测出单个的边缘点.如果受到树木、房屋及车辆的干扰,这些原本就很弱的边缘还会发生断裂.通过现有方法提取具有如此边缘线的道路难度很大.本文给出一种旨在解决这一问题的新方法.首先借鉴相位编组原理形成边缘线支持区并对其进行连接;然后利用动态规划方法从支持区中检测出边缘线并对这些线进行平滑;最后连接由边缘线构成的道路段,得出道路提取结果.实验表明,本方法可以较好地提取出无清晰连续边缘线的道路,对于边缘对比度较大的道路则可取得更为令人满意的结果.
|
| 关 键 词： | 边缘检测 道路提取 相位编组 动态规划 |
To Extract Roads with No Clear and Continuous Boundaries in RS Images |
| |
| ZHOU Shao-guang,XU Yong.To Extract Roads with No Clear and Continuous Boundaries in RS Images[J].Acta Geodaetica et Cartographica Sinica,2008,37(3):0-402. |
| |
| Authors: | ZHOU Shao-guang XU Yong |
| |
| Abstract: | Much attention has been paid on road extraction in RS images in recent years,and a lot of algorithms have been developed.Many existing algorithms are implemented by using the information of outside boundaries of roads,and they can be performed well if only the roads' boundaries are clear and continuous.However,in high resolution RS images there are always some parts of a city where the contrast is low.The roads' boundaries in these areas are weak,and they may even be broken as being influenced by vehicles and shadows of trees and buildings.It is very difficult to extract the roads with this type of edge lines.To solve this problem a new strategy for road extraction is presented in this paper.The first step in the proposed scheme is to produce edge line-support regions with the aid of an improved Burns' method and to link them.Dynamic programming principle is then used to detect edge lines in the linked regions,and the detected edge lines are smoothed.Based on these smoothed edge lines road segments are formed.The final output is generated by connecting road segments.Experiments on high-resolution satellite images show that our approach can extract most of the roads with weak and broken boundaries,and can get more satisfying results in high contrast areas. |
| |
| Keywords: | edge detection road extraction phase-grouping dynamic programming |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《测绘学报》浏览原始摘要信息 |
| 点击此处可从《测绘学报》下载免费的PDF全文 |
|
