计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (34): 187-189.

• 图形、图像、模式识别 • 上一篇    下一篇

基于纹理-模糊连接度的遥感影像道路自动提取

钱 厦,盛庆红,宗 鹏   

  1. 南京航空航天大学 航天学院,南京 210016
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-12-01 发布日期:2011-12-01

Automatic road extraction from remote sensing images based on texture-fuzzy connectedness

QIAN Xia,SHENG Qinghong,ZONG Peng   

  1. College of Astronautics,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-12-01 Published:2011-12-01

摘要: 提出一种基于纹理-模糊连接度的遥感影像道路信息全自动提取算法。利用Canny算子对影像进行边缘检测,通过道路阈值和分类算法的联合优化,提取出道路种子点。定义了包含纹理能量的模糊连接度,对影像中各像素相对于多种子点的连接度进行遍历计算,寻址最优路径,从而识别出完整的道路。实验结果表明,该道路提取算法相对于模糊连接度算法精度更高,具有较强的通用性。

关键词: 模糊连接度, 纹理能量, 道路提取

Abstract: Road extraction from remote sensing images has always been an important research topic in the field of remote sensing.This paper presents an improved automatic road extraction algorithm based on fuzzy connectedness.The algorithm detects the edge of the image with Canny operator,and extracts road seeds by combined optimization of road threshold and classification algorithm.Then by introducing the fuzzy connection containing texture energy and calculating connectedness of the points to the seeds by ergodic process,the entire road profile will be uncovered.In many trials of treating remote sensing images as objects,the performance of extraction algorithm is better with higher accuracy.

Key words: fuzzy connectedness, texture energy, road extraction