节点文献
基于高分辨率SAR图像的道路自动提取
Automatic road extraction in high-resolution SAR images
【摘要】 在传统算法的基础上,用多条件加权法进行道路边缘点的判断,充分利用道路的物理特性,将道路边缘点像素上下文特性作为判断的条件,以实现道路边缘线段的识别。桥接模式的思想是根据道路边缘线平行且宽度一定的特性,通过算法找出两条边缘线段之间的对应点,连接对应点以实现道路提取。经实验测试,该算法能消除地物间的影响和噪声干扰,有效地提高了道路提取的精度和速率。
【Abstract】 Based on the traditional algorithm,the paper presented a new method which used multi-weighted terms to judge the road edge.Made full use of the physical characteristics of the road,and made the road edge pixels context as a judge,in order to recognize the edges segment of the road.According to the characteristics of the road parallel lines and certain width,bridge-link mode found out the corresponding points on two marginalized segment and connected the one-to-one points in order to achieve road extraction.Experimental results demonstrate the algorithm can eliminate features and noise,effectively improve the accuracy and velocity of the road extraction.
【Key words】 road extraction; remote sensing image; multi-weighted terms; bridge-link mode;
- 【文献出处】 计算机应用研究 ,Application Research of Computers , 编辑部邮箱 ,2008年12期
- 【分类号】TP751
- 【被引频次】5
- 【下载频次】226